[ { "keys": [ "proj_pda1fj0a1", "DataSet", "CFG", "health_risk_dataset", "na", "na" ], "values": { "dataset_name": "health_risk_dataset", "basis_sql_filter": "", "final_sql_filter": "", "start_timestamp": "2025-03-25 13:00:00", "end_timestamp": "2025-04-01 00:00:00", "features": { "monitor_time": { "type": "basis", "feature_name": "monitor_time", "description": "", "is_label": false, "materialize": true, "datatype": "timestamp", "featureset_name": "wearable_data_sink", "feature": "monitor_time", "use_datasource": false }, "PatientID": { "type": "basis", "feature_name": "PatientID", "description": "", "is_label": false, "materialize": true, "datatype": "long", "featureset_name": "wearable_data_sink", "feature": "PatientID", "use_datasource": false }, "Checkup": { "entity_key_map": { "PatientID": "PatientID" }, "entity_value_map": {}, "type": "static_contextual", "feature_name": "Checkup", "description": "", "is_label": false, "materialize": true, "datatype": "string", "featureset_name": "health_factors_sink", "entities": [ "PatientID" ], "value": "Checkup", "missing_strategy": "fill_with_const", "missing_value": "", "outage_strategy": "" }, "General_Health": { "entity_key_map": { "PatientID": "PatientID" }, "entity_value_map": {}, "type": "static_contextual", "feature_name": "General_Health", "description": "", "is_label": false, "materialize": true, "datatype": "string", "featureset_name": "health_factors_sink", "entities": [ "PatientID" ], "value": "General_Health", "missing_strategy": "fill_with_const", "missing_value": "", "outage_strategy": "" }, "Exercise": { "entity_key_map": { "PatientID": "PatientID" }, "entity_value_map": {}, "type": "static_contextual", "feature_name": "Exercise", "description": "", "is_label": false, "materialize": true, "datatype": "string", "featureset_name": "health_factors_sink", "entities": [ "PatientID" ], "value": "Exercise", "missing_strategy": "fill_with_const", "missing_value": "", "outage_strategy": "" }, "Heart_Disease": { "entity_key_map": { "PatientID": "PatientID" }, "entity_value_map": {}, "type": "static_contextual", "feature_name": "Heart_Disease", "description": "", "is_label": true, "materialize": true, "datatype": "string", "featureset_name": "health_factors_sink", "entities": [ "PatientID" ], "value": "Heart_Disease", "missing_strategy": "fill_with_const", "missing_value": "", "outage_strategy": "" }, "Skin_Cancer": { "entity_key_map": { "PatientID": "PatientID" }, "entity_value_map": {}, "type": "static_contextual", "feature_name": "Skin_Cancer", "description": "", "is_label": false, "materialize": true, "datatype": "string", "featureset_name": "health_factors_sink", "entities": [ "PatientID" ], "value": "Skin_Cancer", "missing_strategy": "fill_with_const", "missing_value": "", "outage_strategy": "" }, "Other_Cancer": { "entity_key_map": { "PatientID": "PatientID" }, "entity_value_map": {}, "type": "static_contextual", "feature_name": "Other_Cancer", "description": "", "is_label": false, "materialize": true, "datatype": "string", "featureset_name": "health_factors_sink", "entities": [ "PatientID" ], "value": "Other_Cancer", "missing_strategy": "fill_with_const", "missing_value": "", "outage_strategy": "" }, "Depression": { "entity_key_map": { "PatientID": "PatientID" }, "entity_value_map": {}, "type": "static_contextual", "feature_name": "Depression", "description": "", "is_label": false, "materialize": true, "datatype": "string", "featureset_name": "health_factors_sink", "entities": [ "PatientID" ], "value": "Depression", "missing_strategy": "fill_with_const", "missing_value": "", "outage_strategy": "" }, "Diabetes": { "entity_key_map": { "PatientID": "PatientID" }, "entity_value_map": {}, "type": "static_contextual", "feature_name": "Diabetes", "description": "", "is_label": false, "materialize": true, "datatype": "string", "featureset_name": "health_factors_sink", "entities": [ "PatientID" ], "value": "Diabetes", "missing_strategy": "fill_with_const", "missing_value": "", "outage_strategy": "" }, "Arthritis": { "entity_key_map": { "PatientID": "PatientID" }, "entity_value_map": {}, "type": "static_contextual", "feature_name": "Arthritis", "description": "", "is_label": false, "materialize": true, "datatype": "string", "featureset_name": "health_factors_sink", "entities": [ "PatientID" ], "value": "Arthritis", "missing_strategy": "fill_with_const", "missing_value": "", "outage_strategy": "" }, "Sex": { "entity_key_map": { "PatientID": "PatientID" }, "entity_value_map": {}, "type": "static_contextual", "feature_name": "Sex", "description": "", "is_label": false, "materialize": true, "datatype": "string", "featureset_name": "health_factors_sink", "entities": [ "PatientID" ], "value": "Sex", "missing_strategy": "fill_with_const", "missing_value": "", "outage_strategy": "" }, "Age_Category": { "entity_key_map": { "PatientID": "PatientID" }, "entity_value_map": {}, "type": "static_contextual", "feature_name": "Age_Category", "description": "", "is_label": false, "materialize": true, "datatype": "string", "featureset_name": "health_factors_sink", "entities": [ "PatientID" ], "value": "Age_Category", "missing_strategy": "fill_with_const", "missing_value": "", "outage_strategy": "" }, "Height_cm": { "entity_key_map": { "PatientID": "PatientID" }, "entity_value_map": {}, "type": "static_contextual", "feature_name": "Height_cm", "description": "", "is_label": false, "materialize": true, "datatype": "int", "featureset_name": "health_factors_sink", "entities": [ "PatientID" ], "value": "Height_cm", "missing_strategy": "fill_with_const", "missing_value": "", "outage_strategy": "" }, "Weight_kg": { "entity_key_map": { "PatientID": "PatientID" }, "entity_value_map": {}, "type": "static_contextual", "feature_name": "Weight_kg", "description": "", "is_label": false, "materialize": true, "datatype": "double", "featureset_name": "health_factors_sink", "entities": [ "PatientID" ], "value": "Weight_kg", "missing_strategy": "fill_with_const", "missing_value": "", "outage_strategy": "" }, "BMI": { "entity_key_map": { "PatientID": "PatientID" }, "entity_value_map": {}, "type": "static_contextual", "feature_name": "BMI", "description": "", "is_label": false, "materialize": true, "datatype": "double", "featureset_name": "health_factors_sink", "entities": [ "PatientID" ], "value": "BMI", "missing_strategy": "fill_with_const", "missing_value": "", "outage_strategy": "" }, "Smoking_History": { "entity_key_map": { "PatientID": "PatientID" }, "entity_value_map": {}, "type": "static_contextual", "feature_name": "Smoking_History", "description": "", "is_label": false, "materialize": true, "datatype": "string", "featureset_name": "health_factors_sink", "entities": [ "PatientID" ], "value": "Smoking_History", "missing_strategy": "fill_with_const", "missing_value": "", "outage_strategy": "" }, "Alcohol_Consumption": { "entity_key_map": { "PatientID": "PatientID" }, "entity_value_map": {}, "type": "static_contextual", "feature_name": "Alcohol_Consumption", "description": "", "is_label": false, "materialize": true, "datatype": "int", "featureset_name": "health_factors_sink", "entities": [ "PatientID" ], "value": "Alcohol_Consumption", "missing_strategy": "fill_with_const", "missing_value": "", "outage_strategy": "" }, "Fruit_Consumption": { "entity_key_map": { "PatientID": "PatientID" }, "entity_value_map": {}, "type": "static_contextual", "feature_name": "Fruit_Consumption", "description": "", "is_label": false, "materialize": true, "datatype": "int", "featureset_name": "health_factors_sink", "entities": [ "PatientID" ], "value": "Fruit_Consumption", "missing_strategy": "fill_with_const", "missing_value": "", "outage_strategy": "" }, "Green_Vegetables_Consumption": { "entity_key_map": { "PatientID": "PatientID" }, "entity_value_map": {}, "type": "static_contextual", "feature_name": "Green_Vegetables_Consumption", "description": "", "is_label": false, "materialize": true, "datatype": "int", "featureset_name": "health_factors_sink", "entities": [ "PatientID" ], "value": "Green_Vegetables_Consumption", "missing_strategy": "fill_with_const", "missing_value": "", "outage_strategy": "" }, "FriedPotato_Consumption": { "entity_key_map": { "PatientID": "PatientID" }, "entity_value_map": {}, "type": "static_contextual", "feature_name": "FriedPotato_Consumption", "description": "", "is_label": false, "materialize": true, "datatype": "int", "featureset_name": "health_factors_sink", "entities": [ "PatientID" ], "value": "FriedPotato_Consumption", "missing_strategy": "fill_with_const", "missing_value": "", "outage_strategy": "" }, "heart_rate_grt_100": { "entity_key_map": {}, "entity_value_map": {}, "type": "agg", "feature_name": "heart_rate_grt_100", "description": "", "is_label": false, "materialize": true, "datatype": "long", "featureset_name": "wearable_data_sink", "entities": [], "function": "count", "source_expr": "HR", "condition": "HR>100.0", "timestamp_column": "monitor_time", "window_start": "-4h", "window_end": "0h", "params": {}, "missing_strategy": "", "missing_value": "", "outage_strategy": "", "aggr_data_type": "long", "f_aggr_suffix": "HR_count_5", "featureset_suffix": "_agg_ypwj4x2y" }, "last_1h_avg_systolic": { "entity_key_map": { "PatientID": "PatientID" }, "entity_value_map": {}, "type": "agg", "feature_name": "last_1h_avg_systolic", "description": "", "is_label": false, "materialize": true, "datatype": "double", "featureset_name": "wearable_data_sink", "entities": [ "PatientID" ], "function": "avg", "source_expr": "Systolic", "condition": "", "timestamp_column": "monitor_time", "window_start": "-1h", "window_end": "0h", "params": {}, "missing_strategy": "", "missing_value": "", "outage_strategy": "", "aggr_data_type": "double", "f_aggr_suffix": "Systolic_avg_2", "featureset_suffix": "_agg_zhuwgdlz" }, "last_1h_avg_diastolic": { "entity_key_map": { "PatientID": "PatientID" }, "entity_value_map": {}, "type": "agg", "feature_name": "last_1h_avg_diastolic", "description": "", "is_label": false, "materialize": true, "datatype": "double", "featureset_name": "wearable_data_sink", "entities": [ "PatientID" ], "function": "avg", "source_expr": "Diastolic", "condition": "", "timestamp_column": "monitor_time", "window_start": "-1h", "window_end": "0h", "params": {}, "missing_strategy": "", "missing_value": "", "outage_strategy": "", "aggr_data_type": "double", "f_aggr_suffix": "Diastolic_avg_4", "featureset_suffix": "_agg_zhuwgdlz" } }, "version": 1, "featureset_mlfiles": [], "dataset_type": "type-1", "synthesize_basis_data": false, "randomize_timestamp": false, "created_time": "2026-05-14 19:33:33", "created_by": "aizendev", "modified_time": "2026-05-14 19:33:33", "modified_by": "aizendev", "stride": "300" } }, { "keys": [ "proj_pda1fj0a1", "DataSet", "Name", "health_risk_dataset", "na", "na" ], "values": "na" }, { "keys": [ "proj_pda1fj0a1", "DataSink", "CFG", "health_factors_sink", "na", "na" ], "values": { "name": "health_factors_sink", "table": { "name": "health_factors_sink", "type": "static", "entities": [ "PatientID" ], "mark_data_gap_as_outage": false, "sources": [ { "source_name": "aws", "source_table_name": "health_risk_factors", "type": "backfill" } ], "columns": [ { "name": "PatientID", "data_type": "long", "meta": { "ml_type": "text" }, "format_type": "UNKNOWN" }, { "name": "General_Health", "data_type": "string", "meta": { "ml_type": "category" }, "format_type": "UNKNOWN" }, { "name": "Checkup", "data_type": "string", "meta": { "ml_type": "category" }, "format_type": "UNKNOWN" }, { "name": "Exercise", "data_type": "string", "meta": { "ml_type": "category" }, "format_type": "UNKNOWN" }, { "name": "Heart_Disease", "data_type": "string", "meta": { "ml_type": "category" }, "format_type": "UNKNOWN" }, { "name": "Skin_Cancer", "data_type": "string", "meta": { "ml_type": "category" }, "format_type": "UNKNOWN" }, { "name": "Other_Cancer", "data_type": "string", "meta": { "ml_type": "category" }, "format_type": "UNKNOWN" }, { "name": "Depression", "data_type": "string", "meta": { "ml_type": "category" }, "format_type": "UNKNOWN" }, { "name": "Diabetes", "data_type": "string", "meta": { "ml_type": "category" }, "format_type": "UNKNOWN" }, { "name": "Arthritis", "data_type": "string", "meta": { "ml_type": "category" }, "format_type": "UNKNOWN" }, { "name": "Sex", "data_type": "string", "meta": { "ml_type": "category" }, "format_type": "UNKNOWN" }, { "name": "Age_Category", "data_type": "string", "meta": { "ml_type": "category" }, "format_type": "UNKNOWN" }, { "name": "Height_cm", "data_type": "int", "meta": { "ml_type": "category" }, "format_type": "UNKNOWN" }, { "name": "Weight_kg", "data_type": "double", "meta": { "ml_type": "category" }, "format_type": "UNKNOWN" }, { "name": "BMI", "data_type": "double", "meta": { "ml_type": "category" }, "format_type": "UNKNOWN" }, { "name": "Smoking_History", "data_type": "string", "meta": { "ml_type": "category" }, "format_type": "UNKNOWN" }, { "name": "Alcohol_Consumption", "data_type": "int", "meta": { "ml_type": "category" }, "format_type": "UNKNOWN" }, { "name": "Fruit_Consumption", "data_type": "int", "meta": { "ml_type": "category" }, "format_type": "UNKNOWN" }, { "name": "Green_Vegetables_Consumption", "data_type": "int", "meta": { "ml_type": "category" }, "format_type": "UNKNOWN" }, { "name": "FriedPotato_Consumption", "data_type": "int", "meta": { "ml_type": "category" }, "format_type": "UNKNOWN" } ] }, "tables": {}, "transformations": null, "ml_file": null, "constraints": false, "metrics": false, "constraints_file": null, "constraints_file_data": null, "metrics_file": null, "metrics_file_data": null, "created_time": "2026-05-11 16:16:43", "createdBy": null, "update_time": null, "updatedBy": null, "version": 1, "created_by": "aizendev", "modified_time": "2026-05-11 16:16:43", "modified_by": "aizendev" } }, { "keys": [ "proj_pda1fj0a1", "DataSink", "CFG", "wearable_data_sink", "na", "na" ], "values": { "name": "wearable_data_sink", "table": { "name": "wearable_data_sink", "type": "event", "entities": [ "PatientID" ], "timestamp_column": "monitor_time", "min_aggregation_interval": "5m", "max_aggregation_window": "1d", "late_arrival_window": "", "backfill_start_datetime": "2025-03-25T13:00", "backfill_end_datetime": "2025-04-01T00:00", "mark_data_gap_as_outage": true, "sources": [ { "source_name": "aws", "source_table_name": "wearable_device_source", "type": "backfill" } ], "columns": [ { "name": "monitor_time", "data_type": "timestamp", "meta": { "ml_type": "datetime" }, "format_type": "YYYY-MM-DD HH:MM:SS" }, { "name": "PatientID", "data_type": "long", "meta": { "ml_type": "category" }, "format_type": "UNKNOWN" }, { "name": "HR", "data_type": "double", "meta": { "ml_type": "category" }, "format_type": "UNKNOWN" }, { "name": "HRV", "data_type": "double", "meta": { "ml_type": "category" }, "format_type": "UNKNOWN" }, { "name": "SpO2", "data_type": "double", "meta": { "ml_type": "category" }, "format_type": "UNKNOWN" }, { "name": "RespRate", "data_type": "double", "meta": { "ml_type": "category" }, "format_type": "UNKNOWN" }, { "name": "Temp", "data_type": "double", "meta": { "ml_type": "category" }, "format_type": "UNKNOWN" }, { "name": "Steps", "data_type": "long", "meta": { "ml_type": "category" }, "format_type": "UNKNOWN" }, { "name": "ECGAnomaly", "data_type": "string", "meta": { "ml_type": "category" }, "format_type": "UNKNOWN" }, { "name": "Systolic", "data_type": "long", "meta": { "ml_type": "category" }, "format_type": "UNKNOWN" }, { "name": "Diastolic", "data_type": "long", "meta": { "ml_type": "category" }, "format_type": "UNKNOWN" }, { "name": "Weight", "data_type": "double", "meta": { "ml_type": "category" }, "format_type": "UNKNOWN" }, { "name": "SleepQuality", "data_type": "double", "meta": { "ml_type": "category" }, "format_type": "UNKNOWN" }, { "name": "SymptomLogged", "data_type": "string", "meta": { "ml_type": "category" }, "format_type": "UNKNOWN" } ] }, "tables": {}, "transformations": null, "ml_file": null, "constraints": false, "metrics": false, "constraints_file": null, "constraints_file_data": null, "metrics_file": null, "metrics_file_data": null, "created_time": "2026-05-11 16:20:35", "createdBy": null, "update_time": null, "updatedBy": null, "version": 1, "created_by": "aizendev", "modified_time": "2026-05-11 16:20:35", "modified_by": "aizendev", "backfill_end_time": "2025-04-01 00:00:00" } }, { "keys": [ "proj_pda1fj0a1", "DataSink", "FeatureSet", "wearable_data_sink", "wearable_data_sink_agg_u1hombna", "na" ], "values": { "source_fs": "wearable_data_sink", "query_type": "featureset", "entities": [], "max_aggregation_window": "1d", "mark_data_gap_as_outage": true, "late_arrival_window": "", "outage_report_trigger": "", "featureset_name": "wearable_data_sink_agg_u1hombna", "aggregates": [ { "name": "HR_count_0", "datatype": "long", "source_expr": "HR>=100.0", "function": "count", "params": {}, "condition": "", "featureset_suffix": "_agg_u1hombna", "description": "", "timestamp_column": "monitor_time" } ] } }, { "keys": [ "proj_pda1fj0a1", "DataSink", "FeatureSet", "wearable_data_sink", "wearable_data_sink_agg_ypwj4x2y", "na" ], "values": { "source_fs": "wearable_data_sink", "query_type": "featureset", "entities": [], "max_aggregation_window": "1d", "mark_data_gap_as_outage": true, "late_arrival_window": "", "outage_report_trigger": "", "featureset_name": "wearable_data_sink_agg_ypwj4x2y", "aggregates": [ { "name": "HR_count_5", "datatype": "long", "source_expr": "HR", "function": "count", "params": {}, "condition": "HR>100.0", "featureset_suffix": "_agg_ypwj4x2y", "description": "", "timestamp_column": "monitor_time" } ] } }, { "keys": [ "proj_pda1fj0a1", "DataSink", "FeatureSet", "wearable_data_sink", "wearable_data_sink_agg_zhuwgdlz", "na" ], "values": { "source_fs": "wearable_data_sink", "query_type": "featureset", "entities": [ "PatientID" ], "max_aggregation_window": "1d", "mark_data_gap_as_outage": true, "late_arrival_window": "", "outage_report_trigger": "", "featureset_name": "wearable_data_sink_agg_zhuwgdlz", "aggregates": [ { "name": "Systolic_max_1", "datatype": "int", "source_expr": "Systolic", "function": "max", "params": {}, "condition": "", "featureset_suffix": "_agg_zhuwgdlz", "description": "", "timestamp_column": "monitor_time" }, { "name": "Systolic_avg_2", "datatype": "double", "source_expr": "Systolic", "function": "avg", "params": {}, "condition": "", "featureset_suffix": "_agg_zhuwgdlz", "description": "", "timestamp_column": "monitor_time" }, { "name": "Diastolic_max_3", "datatype": "int", "source_expr": "Diastolic", "function": "max", "params": {}, "condition": "", "featureset_suffix": "_agg_zhuwgdlz", "description": "", "timestamp_column": "monitor_time" }, { "name": "Diastolic_avg_4", "datatype": "double", "source_expr": "Diastolic", "function": "avg", "params": {}, "condition": "", "featureset_suffix": "_agg_zhuwgdlz", "description": "", "timestamp_column": "monitor_time" } ] } }, { "keys": [ "proj_pda1fj0a1", "DataSink", "FeatureSetUser", "health_factors_sink", "health_factors_sink", "health_risk_dataset" ], "values": "na" }, { "keys": [ "proj_pda1fj0a1", "DataSink", "FeatureSetUser", "wearable_data_sink", "wearable_data_sink", "health_risk_dataset" ], "values": "na" }, { "keys": [ "proj_pda1fj0a1", "DataSink", "FeatureSetUser", "wearable_data_sink", "wearable_data_sink_agg_u1hombna", "health_risk_dataset" ], "values": "na" }, { "keys": [ "proj_pda1fj0a1", "DataSink", "FeatureSetUser", "wearable_data_sink", "wearable_data_sink_agg_ypwj4x2y", "health_risk_dataset" ], "values": "na" }, { "keys": [ "proj_pda1fj0a1", "DataSink", "FeatureSetUser", "wearable_data_sink", "wearable_data_sink_agg_zhuwgdlz", "health_risk_dataset" ], "values": "na" }, { "keys": [ "proj_pda1fj0a1", "DataSink", "Name", "health_factors_sink", "na", "na" ], "values": "na" }, { "keys": [ "proj_pda1fj0a1", "DataSink", "Name", "wearable_data_sink", "na", "na" ], "values": "na" }, { "keys": [ "proj_pda1fj0a1", "DataSource", "CFG", "health_risk_factors", "na", "na" ], "values": { "meta": { "display_source_name": "AWS S3", "source_type": "aws", "source_format": "csv", "s3_endpoint_url": "https://s3.us-west-2.amazonaws.com", "path": "s3a://aizen-public/aizen_foresight_validation/health_risk_dataset/CVD_cleaned_100.csv", "delimiter": ",", "multi_line": true, "escape": "\"", "quote": "\"", "anon": true, "credentials_name": "", "is_schema_required": true, "url": "", "table_name": "", "batch_schedule": "", "driver": "", "topic": "", "offset": "latest", "streaming_window": "", "retention_period": "", "timestamp_column": null, "timezone": "UTC", "date_format": "", "timestamp_format": "", "http_endpoint": "", "http_method": "GET", "preprocessor": [], "credentials_type": "aws" }, "name": "health_risk_factors", "description": "", "columns": [ { "name": "PatientID", "data_type": "long", "format_type": "UNKNOWN", "meta": { "ml_type": "text" }, "ml_type": "text", "description": "A unique identifier for each patient, represented as a long integer, serving as a primary key. This column is categorical and static, with no inherent predictive value, but crucial for data integrity and joining operations. It should be free of missing values and duplicates, ensuring consistent patient tracking across datasets." }, { "name": "General_Health", "data_type": "string", "format_type": "UNKNOWN", "meta": { "ml_type": "category" }, "ml_type": "category", "description": "A categorical string indicating the patient's self-reported health status, potentially ranging from 'Excellent' to 'Poor'. This column may correlate with other health indicators like 'Exercise' and 'Heart_Disease' and can be encoded for ML tasks. Missing values may exist due to subjective reporting, and it is a dynamic attribute reflecting changes over time." }, { "name": "Checkup", "data_type": "string", "format_type": "UNKNOWN", "meta": { "ml_type": "category" }, "ml_type": "category", "description": "A categorical string detailing the frequency of medical checkups, such as 'Annual', 'Bi-annual', or 'Rarely'. This feature can be transformed into ordinal values for predictive modeling and might correlate with 'General_Health' and 'Heart_Disease'. It is a dynamic attribute, potentially indicating preventive health behavior." }, { "name": "Exercise", "data_type": "string", "format_type": "UNKNOWN", "meta": { "ml_type": "category" }, "ml_type": "category", "description": "A categorical string describing the regularity of physical activity, such as 'Daily', 'Weekly', or 'Never'. This dynamic feature is crucial for predicting health outcomes and may correlate with 'BMI' and 'Heart_Disease'. Encoding and binning can enhance its utility in ML models, and missing values could indicate sedentary behavior." }, { "name": "Heart_Disease", "data_type": "string", "format_type": "UNKNOWN", "meta": { "ml_type": "category" }, "ml_type": "category", "description": "A binary categorical string indicating the presence ('Yes') or absence ('No') of heart disease. This column is a critical target variable for health-related prediction tasks and may correlate with 'BMI', 'Exercise', and 'Smoking_History'. Data quality is paramount, with potential for missing values impacting model accuracy." }, { "name": "Skin_Cancer", "data_type": "string", "format_type": "UNKNOWN", "meta": { "ml_type": "category" }, "ml_type": "category", "description": "A binary categorical string denoting the presence ('Yes') or absence ('No') of skin cancer. This static feature may correlate with 'General_Health' and 'Smoking_History', and is important for risk assessment models. Ensuring accurate and complete data is essential for reliable predictions." }, { "name": "Other_Cancer", "data_type": "string", "format_type": "UNKNOWN", "meta": { "ml_type": "category" }, "ml_type": "category", "description": "A binary categorical string indicating the presence ('Yes') or absence ('No') of cancers other than skin cancer. This column is significant for comprehensive health risk modeling and may correlate with 'Smoking_History' and 'Alcohol_Consumption'. Data completeness is critical to avoid bias in predictions." }, { "name": "Depression", "data_type": "string", "format_type": "UNKNOWN", "meta": { "ml_type": "category" }, "ml_type": "category", "description": "A binary categorical string representing whether the patient has been diagnosed with depression ('Yes' or 'No'). This feature is dynamic and may correlate with 'General_Health' and 'Exercise', influencing mental health prediction models. Missing values should be addressed to maintain model robustness." }, { "name": "Diabetes", "data_type": "string", "format_type": "UNKNOWN", "meta": { "ml_type": "category" }, "ml_type": "category", "description": "A binary categorical string indicating the presence ('Yes') or absence ('No') of diabetes. This static feature is vital for health risk prediction and may correlate with 'BMI', 'Exercise', and 'Dietary Habits'. Ensuring data accuracy and completeness is crucial for effective modeling." }, { "name": "Arthritis", "data_type": "string", "format_type": "UNKNOWN", "meta": { "ml_type": "category" }, "ml_type": "category", "description": "A binary categorical string indicating whether the patient has arthritis ('Yes' or 'No'). This static feature may correlate with 'Age_Category' and 'Exercise', impacting quality of life assessments. Data quality considerations include completeness and accuracy for reliable predictions." }, { "name": "Sex", "data_type": "string", "format_type": "UNKNOWN", "meta": { "ml_type": "category" }, "ml_type": "category", "description": "A categorical string representing the patient's gender, typically 'Male' or 'Female'. This static feature is essential for demographic analysis and may correlate with 'Heart_Disease' and 'Cancer' risks. Data should be complete and accurately recorded to avoid bias in gender-specific models." }, { "name": "Age_Category", "data_type": "string", "format_type": "UNKNOWN", "meta": { "ml_type": "category" }, "ml_type": "category", "description": "A categorical string representing age groups, such as '18-24', '25-34', etc. This static feature is crucial for demographic segmentation and may correlate with 'Arthritis' and 'Heart_Disease'. Encoding into ordinal values can enhance its utility in predictive models." }, { "name": "Height_cm", "data_type": "int", "format_type": "UNKNOWN", "meta": { "ml_type": "category" }, "ml_type": "category", "description": "A continuous integer representing the patient's height in centimeters. This static feature is essential for calculating 'BMI' and may correlate with 'Weight_kg'. Data quality considerations include ensuring realistic values and handling outliers appropriately." }, { "name": "Weight_kg", "data_type": "double", "format_type": "UNKNOWN", "meta": { "ml_type": "category" }, "ml_type": "category", "description": "A continuous double representing the patient's weight in kilograms. This dynamic feature is critical for calculating 'BMI' and may correlate with 'Exercise' and 'Dietary Habits'. Outliers and missing values should be addressed to maintain model accuracy." }, { "name": "BMI", "data_type": "double", "format_type": "UNKNOWN", "meta": { "ml_type": "category" }, "ml_type": "category", "description": "A continuous double representing the Body Mass Index, calculated from 'Height_cm' and 'Weight_kg'. This dynamic feature is crucial for predicting health risks like 'Heart_Disease' and 'Diabetes'. Ensuring accurate calculation and addressing outliers are vital for reliable predictions." }, { "name": "Smoking_History", "data_type": "string", "format_type": "UNKNOWN", "meta": { "ml_type": "category" }, "ml_type": "category", "description": "A categorical string indicating the patient's smoking status, such as 'Never', 'Former', or 'Current'. This dynamic feature is significant for health risk assessments and may correlate with 'Heart_Disease' and 'Cancer'. Encoding and handling missing values can enhance its predictive power." }, { "name": "Alcohol_Consumption", "data_type": "int", "format_type": "UNKNOWN", "meta": { "ml_type": "category" }, "ml_type": "category", "description": "A discrete integer representing the frequency of alcohol consumption, possibly measured in units per week. This dynamic feature may correlate with 'Liver Disease' and 'General_Health', and can be binned for ML tasks. Data quality considerations include addressing outliers and missing values." }, { "name": "Fruit_Consumption", "data_type": "int", "format_type": "UNKNOWN", "meta": { "ml_type": "category" }, "ml_type": "category", "description": "A discrete integer indicating the frequency of fruit intake, potentially measured in servings per week. This dynamic feature may correlate with 'General_Health' and 'BMI', and can be transformed into categorical bins for modeling. Ensuring accurate reporting and addressing missing values are important for data quality." }, { "name": "Green_Vegetables_Consumption", "data_type": "int", "format_type": "UNKNOWN", "meta": { "ml_type": "category" }, "ml_type": "category", "description": "A discrete integer representing the frequency of green vegetable intake, possibly in servings per week. This dynamic feature may correlate with 'General_Health' and 'BMI', and can be binned for enhanced model utility. Data quality considerations include accurate reporting and handling missing values." }, { "name": "FriedPotato_Consumption", "data_type": "int", "format_type": "UNKNOWN", "meta": { "ml_type": "category" }, "ml_type": "category", "description": "A discrete integer indicating the frequency of fried potato consumption, potentially measured in servings per week. This dynamic feature may negatively correlate with 'BMI' and 'Heart_Disease', and can be transformed into categorical bins for ML tasks. Addressing outliers and missing values is crucial for maintaining data integrity." } ], "target_columns": [], "targetColumns": [], "modified_time": "2026-05-14 19:33:33", "modified_by": "aizendev", "version": 1, "created_time": "2026-05-14 19:33:33", "created_by": "aizendev" } }, { "keys": [ "proj_pda1fj0a1", "DataSource", "CFG", "wearable_device_source", "na", "na" ], "values": { "meta": { "display_source_name": "AWS S3", "source_type": "aws", "source_format": "csv", "s3_endpoint_url": "https://s3.us-west-2.amazonaws.com", "path": "s3a://aizen-public/aizen_foresight_validation/health_risk_dataset/heart_patient_wearable_data_100rows.csv", "delimiter": ",", "multi_line": true, "escape": "\"", "quote": "\"", "anon": true, "credentials_name": "", "is_schema_required": true, "url": "", "table_name": "", "batch_schedule": "", "driver": "", "topic": "", "offset": "latest", "streaming_window": "", "retention_period": "", "timestamp_column": "monitor_time", "timezone": "UTC", "date_format": "", "timestamp_format": "", "http_endpoint": "", "http_method": "GET", "preprocessor": [], "credentials_type": "aws" }, "name": "wearable_device_source", "description": "", "columns": [ { "name": "monitor_time", "data_type": "timestamp", "format_type": "YYYY-MM-DD HH:MM:SS", "meta": { "ml_type": "datetime" }, "ml_type": "datetime", "description": "Timestamp representing the exact time the data was recorded, crucial for time-series analysis and temporal feature engineering. This dynamic, continuous variable is essential for identifying trends, seasonality, and temporal correlations with other health metrics. Missing values are unlikely, but time zone consistency should be verified for accurate temporal analysis." }, { "name": "PatientID", "data_type": "long", "format_type": "UNKNOWN", "meta": { "ml_type": "category" }, "ml_type": "category", "description": "Unique identifier for each patient, serving as a categorical variable for grouping and stratification in analysis. It is crucial for patient-specific trend analysis and longitudinal studies. Ensuring uniqueness and consistency is vital, and it may correlate with demographic or historical health data if available." }, { "name": "HR", "data_type": "double", "format_type": "UNKNOWN", "meta": { "ml_type": "category" }, "ml_type": "category", "description": "Heart Rate recorded as a string, representing a continuous physiological metric. It can be transformed into numerical form for statistical analysis and feature extraction, such as calculating averages or detecting anomalies. Potential correlations exist with other vital signs like HRV and SpO2, and data quality checks should address potential outliers or erroneous entries." }, { "name": "HRV", "data_type": "double", "format_type": "UNKNOWN", "meta": { "ml_type": "category" }, "ml_type": "category", "description": "Heart Rate Variability, a string representing a continuous measure of the variation in time between heartbeats. It is a key indicator of autonomic nervous system function and can be numerically transformed for advanced analysis. Correlations with stress levels, HR, and ECGAnomaly are expected, and data may contain noise or outliers." }, { "name": "SpO2", "data_type": "double", "format_type": "UNKNOWN", "meta": { "ml_type": "category" }, "ml_type": "category", "description": "Oxygen saturation level, recorded as a string, indicating the percentage of oxygen-saturated hemoglobin in the blood. This continuous variable is critical for assessing respiratory function and can be numerically analyzed for trends or anomalies. It may correlate with RespRate and Temp, and data integrity checks are necessary to handle potential outliers." }, { "name": "RespRate", "data_type": "double", "format_type": "UNKNOWN", "meta": { "ml_type": "category" }, "ml_type": "category", "description": "Respiratory Rate, a string representing the number of breaths per minute, serving as a continuous measure of respiratory health. Transforming this into a numerical format enables trend analysis and anomaly detection. It may correlate with SpO2 and Temp, and data quality considerations include handling missing values and outliers." }, { "name": "Temp", "data_type": "double", "format_type": "UNKNOWN", "meta": { "ml_type": "category" }, "ml_type": "category", "description": "Body Temperature recorded as a string, a continuous variable crucial for detecting fever or hypothermia. Numerical transformation allows for statistical analysis and anomaly detection, with potential correlations to HR and RespRate. Data quality checks should address potential measurement errors or outliers." }, { "name": "Steps", "data_type": "long", "format_type": "UNKNOWN", "meta": { "ml_type": "category" }, "ml_type": "category", "description": "Number of steps taken, recorded as a string, representing a discrete measure of physical activity. This can be transformed into a numerical format for activity trend analysis and correlation with other health metrics like Weight and SleepQuality. Data may contain zeros or missing values, especially if the device was not worn." }, { "name": "ECGAnomaly", "data_type": "string", "format_type": "UNKNOWN", "meta": { "ml_type": "category" }, "ml_type": "category", "description": "Indicator of any detected anomalies in the ECG, recorded as a string, typically categorical (e.g., 'normal', 'anomaly'). This is crucial for cardiac health assessment and may correlate with HR and HRV. Data quality checks should ensure consistency in anomaly labeling and address potential false positives or negatives." }, { "name": "Systolic", "data_type": "long", "format_type": "UNKNOWN", "meta": { "ml_type": "category" }, "ml_type": "category", "description": "Systolic blood pressure, recorded as a string, representing a continuous measure of cardiovascular health. Numerical transformation facilitates trend analysis and correlation with Diastolic and HR. Data quality considerations include handling outliers and ensuring accurate measurement units." }, { "name": "Diastolic", "data_type": "long", "format_type": "UNKNOWN", "meta": { "ml_type": "category" }, "ml_type": "category", "description": "Diastolic blood pressure, a string representing a continuous measure of cardiovascular health, complementary to Systolic. Transforming this into a numerical format allows for comprehensive blood pressure analysis and correlation with Systolic and HR. Data quality checks should address potential outliers and measurement accuracy." }, { "name": "Weight", "data_type": "double", "format_type": "UNKNOWN", "meta": { "ml_type": "category" }, "ml_type": "category", "description": "Patient's weight recorded as a string, a continuous variable important for assessing overall health and correlating with Steps and Temp. Numerical transformation enables trend analysis and anomaly detection. Data quality considerations include handling missing values and ensuring consistent measurement units." }, { "name": "SleepQuality", "data_type": "double", "format_type": "UNKNOWN", "meta": { "ml_type": "category" }, "ml_type": "category", "description": "Qualitative assessment of sleep quality, recorded as a string, typically categorical (e.g., 'good', 'poor'). This is important for understanding rest patterns and may correlate with Steps and HRV. Data quality checks should ensure consistency in categorization and address potential subjective biases." }, { "name": "SymptomLogged", "data_type": "string", "format_type": "UNKNOWN", "meta": { "ml_type": "category" }, "ml_type": "category", "description": "Indicator of any symptoms logged by the patient, recorded as a string, typically categorical (e.g., 'none', 'headache'). This is crucial for contextualizing other health metrics and may correlate with Temp and HR. Data quality considerations include ensuring consistency in symptom labeling and addressing potential underreporting." } ], "target_columns": [], "targetColumns": [], "modified_time": "2026-05-14 19:33:33", "modified_by": "aizendev", "version": 1, "created_time": "2026-05-14 19:33:33", "created_by": "aizendev" } }, { "keys": [ "proj_pda1fj0a1", "DataSource", "Name", "health_risk_factors", "na", "na" ], "values": "na" }, { "keys": [ "proj_pda1fj0a1", "DataSource", "Name", "wearable_device_source", "na", "na" ], "values": "na" }, { "keys": [ "proj_pda1fj0a1", "DataSource", "User", "health_risk_factors", "health_factors_sink", "na" ], "values": "na" }, { "keys": [ "proj_pda1fj0a1", "DataSource", "User", "wearable_device_source", "wearable_data_sink", "na" ], "values": "na" }, { "keys": [ "proj_pda1fj0a1", "Flow", "CFG", "health_risk_pipeline_demo", "na", "na" ], "values": { "name": "health_risk_pipeline_demo", "metadata": { "description": "", "created_time": "2026-05-14 19:33:33", "modified_time": "2026-05-14T22:05:15.088964", "created_by": "aizendev", "modified_by": "aizendev", "project": "proj_pda1fj0a1", "node_count": 7, "version": 1 }, "nodes": [ { "id": "datasource-1778314452645-604", "type": "customNode", "position": { "x": -1584, "y": -32 }, "data": { "id": "datasource-1778314452645-604", "label": "wearable_device_source", "type": "datasource", "icon": { "type": { "displayName": "Table" }, "key": null, "ref": null, "props": { "className": "h-4 w-4" }, "_owner": null }, "status": "configured", "configuredName": "wearable_device_source", "config": { "name": "wearable_device_source", "type": "aws", "sourceNames": [ "csv" ] } }, "width": 221, "height": 86, "selected": false, "positionAbsolute": { "x": -1584, "y": -32 }, "dragging": false }, { "id": "training-1778501377716-403", "type": "customNode", "position": { "x": -448, "y": -144 }, "data": { "id": "training-1778501377716-403", "label": "health_risk_exp", "type": "training", "icon": { "type": { "displayName": "FlaskConical" }, "key": null, "ref": null, "props": { "className": "h-4 w-4" }, "_owner": null }, "status": "completed", "configuredName": "health_risk_exp", "config": { "name": "health_risk_exp", "exp_type": "Deep Learning", "model_name": "health_risk_model", "dataset_name": "health_risk_dataset", "input_features": [ "Checkup", "General_Health", "Exercise", "Skin_Cancer", "Other_Cancer", "Depression", "Diabetes", "Arthritis", "Sex", "Age_Category", "Height_cm", "Weight_kg", "BMI", "Smoking_History", "Alcohol_Consumption", "Fruit_Consumption", "Green_Vegetables_Consumption", "FriedPotato_Consumption", "heart_rate_grt_100", "last_1h_avg_systolic", "last_1h_avg_diastolic" ], "output_features": [ "Heart_Disease" ], "ml_type": "regression", "ml_algo": [], "num_clusters": 5, "forecast_horizon": 3 } }, "width": 212, "height": 86, "selected": false, "positionAbsolute": { "x": -448, "y": -144 }, "dragging": false }, { "id": "datasource-1778516042985-940", "type": "customNode", "position": { "x": -1584, "y": -208 }, "data": { "id": "datasource-1778516042985-940", "label": "health_risk_factors", "type": "datasource", "icon": { "type": { "displayName": "Table" }, "key": null, "ref": null, "props": { "className": "h-4 w-4" }, "_owner": null }, "status": "configured", "configuredName": "health_risk_factors", "config": { "name": "health_risk_factors", "type": "aws", "sourceNames": [ "csv" ] } }, "width": 221, "height": 86, "selected": false, "positionAbsolute": { "x": -1584, "y": -208 }, "dragging": false }, { "id": "datasink-1778516562506-482", "type": "customNode", "position": { "x": -1216, "y": -208 }, "data": { "id": "datasink-1778516562506-482", "label": "health_factors_sink", "type": "datasink", "icon": { "type": { "displayName": "Anchor" }, "key": null, "ref": null, "props": { "className": "h-4 w-4" }, "_owner": null }, "status": "completed", "config": { "name": "health_factors_sink", "type": "static", "sourceNames": [ "health_risk_factors" ], "sourceTypes": [ "aws" ], "sourceTypesDetailed": [ "backfill" ] }, "configuredName": "health_factors_sink" }, "width": 205, "height": 86, "selected": false, "positionAbsolute": { "x": -1216, "y": -208 }, "dragging": false }, { "id": "datasink-1778516709344-806", "type": "customNode", "position": { "x": -1168, "y": -16 }, "data": { "id": "datasink-1778516709344-806", "label": "wearable_data_sink", "type": "datasink", "icon": { "type": { "displayName": "Anchor" }, "key": null, "ref": null, "props": { "className": "h-4 w-4" }, "_owner": null }, "status": "completed", "config": { "name": "wearable_data_sink", "type": "event", "sourceNames": [ "wearable_device_source" ], "sourceTypes": [ "aws" ], "sourceTypesDetailed": [ "backfill" ] }, "configuredName": "wearable_data_sink" }, "width": 205, "height": 86, "selected": false, "positionAbsolute": { "x": -1168, "y": -16 }, "dragging": false }, { "id": "dataset-1778517958182-94", "type": "customNode", "position": { "x": -800, "y": -128 }, "data": { "id": "dataset-1778517958182-94", "label": "health_risk_dataset", "type": "dataset", "icon": { "type": { "displayName": "Database" }, "key": null, "ref": null, "props": { "className": "h-4 w-4" }, "_owner": null }, "status": "completed", "config": { "name": "health_risk_dataset", "type": "type-1", "featurecount": 24, "timestampcount": 1, "datasourcecount": 4, "datasinkcount": 4 }, "configuredName": "health_risk_dataset" }, "width": 201, "height": 86, "selected": false, "positionAbsolute": { "x": -800, "y": -128 }, "dragging": false }, { "id": "serving-1778562875696-709", "type": "customNode", "position": { "x": -160, "y": -400 }, "data": { "id": "serving-1778562875696-709", "label": "heart_risk_pred", "type": "serving", "icon": { "type": { "displayName": "Rocket" }, "key": null, "ref": null, "props": { "className": "h-4 w-4" }, "_owner": null }, "status": "running", "config": { "name": "heart_risk_pred", "model_name": "health_risk_model", "model_version": 1, "source_type": "http", "source_name": "", "dest_type": "http", "dest_name": "" }, "configuredName": "heart_risk_pred" }, "width": 189, "height": 86, "selected": true, "positionAbsolute": { "x": -160, "y": -400 }, "dragging": false } ], "edges": [ { "source": "datasource-1778516042985-940", "sourceHandle": null, "target": "datasink-1778516562506-482", "targetHandle": null, "id": "reactflow__edge-datasource-1778516042985-940-datasink-1778516562506-482" }, { "source": "datasource-1778314452645-604", "sourceHandle": null, "target": "datasink-1778516709344-806", "targetHandle": null, "id": "reactflow__edge-datasource-1778314452645-604-datasink-1778516709344-806" }, { "source": "datasink-1778516562506-482", "sourceHandle": null, "target": "dataset-1778517958182-94", "targetHandle": null, "id": "reactflow__edge-datasink-1778516562506-482-dataset-1778517958182-94" }, { "source": "datasink-1778516709344-806", "sourceHandle": null, "target": "dataset-1778517958182-94", "targetHandle": null, "id": "reactflow__edge-datasink-1778516709344-806-dataset-1778517958182-94" }, { "source": "dataset-1778517958182-94", "sourceHandle": null, "target": "training-1778501377716-403", "targetHandle": null, "id": "reactflow__edge-dataset-1778517958182-94-training-1778501377716-403" }, { "source": "training-1778501377716-403", "sourceHandle": null, "target": "serving-1778562875696-709", "targetHandle": null, "id": "reactflow__edge-training-1778501377716-403-serving-1778562875696-709" } ] } }, { "keys": [ "proj_pda1fj0a1", "Flow", "Name", "health_risk_pipeline_demo", "na", "na" ], "values": "na" }, { "keys": [ "proj_pda1fj0a1", "LLMApp", "CFG", "agent1", "na", "na" ], "values": { "app_name": "agent1", "app_type": "AI agent", "description": "you are an expert on heart disease and patient health.", "advanced_setting": false, "tools": { "agent_tool": { "name": "agent_tool", "type": "Custom Functions", "description": "a tool that predicts the heart disease and health information for a patient.", "use_app_llm": true, "module_file": "health_real_time_pred_tool.py", "class_name": null, "function_names": [ "predict_health_risk_agent" ], "return_direct": false } }, "provider_name": "myopenai", "provider_id": "openai", "model_name": "gpt-4o-mini", "is_chat_model": true } }, { "keys": [ "proj_pda1fj0a1", "LLMApp", "Module", "agent1", "agent_tool", "na" ], "values": "from typing import Optional\nfrom typing_extensions import Annotated\nfrom pydantic import BaseModel, Field\nfrom datetime import datetime\nimport requests\nimport json\n\n# Define Pydantic models for input and output\nclass _InputRequest_(BaseModel):\n PatientID: Annotated[int, Field(description=\"Patientid\")]\n monitor_time: Annotated[Optional[object], Field(description=\"monitor_time\")] = None\n\nclass _OutputResponse_(BaseModel):\n Depression: Annotated[Optional[str], Field(description=\"Depression\")] = None\n Exercise: Annotated[Optional[str], Field(description=\"Exercise\")] = None\n Checkup: Annotated[Optional[str], Field(description=\"Checkup\")] = None\n General_Health: Annotated[Optional[str], Field(description=\"General Health\")] = None\n FriedPotato_Consumption: Annotated[Optional[int], Field(description=\"Friedpotato Consumption\")] = None\n Green_Vegetables_Consumption: Annotated[Optional[int], Field(description=\"Green Vegetables Consumption\")] = None\n Diabetes: Annotated[Optional[str], Field(description=\"Diabetes\")] = None\n Fruit_Consumption: Annotated[Optional[int], Field(description=\"Fruit Consumption\")] = None\n Smoking_History: Annotated[Optional[str], Field(description=\"Smoking History\")] = None\n BMI: Annotated[Optional[float], Field(description=\"Bmi\")] = None\n Weight_kg: Annotated[Optional[float], Field(description=\"Weight Kg\")] = None\n Height_cm: Annotated[Optional[int], Field(description=\"Height Cm\")] = None\n Age_Category: Annotated[Optional[str], Field(description=\"Age Category\")] = None\n Sex: Annotated[Optional[str], Field(description=\"Sex\")] = None\n Alcohol_Consumption: Annotated[Optional[int], Field(description=\"Alcohol Consumption\")] = None\n Arthritis: Annotated[Optional[str], Field(description=\"Arthritis\")] = None\n ECGAnomaly: Annotated[Optional[str], Field(description=\"Ecganomaly\")] = None\n HR_GRT_100: Annotated[Optional[int], Field(description=\"Hr Grt 100\")] = None\n HRV_AVG_1H: Annotated[Optional[float], Field(description=\"Hrv Avg 1H\")] = None\n Diastolic_GRT_90: Annotated[Optional[int], Field(description=\"Diastolic Grt 90\")] = None\n Heart_Disease: Annotated[Optional[str], Field(description=\"Heart Disease\")] = None\n prediction_warning: Annotated[Optional[str], Field(description=\"warning on the prediction output\")] = None\n prediction_error: Annotated[Optional[dict], Field(description=\"prediction error details\")] = None\n\ndef predict_health_risk_agent(req: _InputRequest_) -> _OutputResponse_:\n \"\"\"'predict the heart disease risk for a patient'\"\"\"\n try:\n timestamp_columns = ['monitor_time']\n for ts_col in timestamp_columns:\n if not req.get(ts_col):\n req[ts_col] = datetime.utcnow().isoformat(sep=' ')\n \n url = \"http://172.16.26.120/yogeshv/predictions/az-pr-2cdfb8a73a/health_risk_agent.health_real_time_pred/Heart_Disease\"\n headers = {\"Content-Type\": \"application/json\"}\n payload = [\n { \"rest_request_id\": \"request1\",\n **req\n }\n ]\n response = requests.post(url, data=json.dumps(payload), headers=headers)\n if response.status_code == 200 and response.json():\n output_list = response.json()\n data = output_list[0]\n resp = _OutputResponse_(\n Depression=data.get(\"Depression\", None), Exercise=data.get(\"Exercise\", None), Checkup=data.get(\"Checkup\", None), General_Health=data.get(\"General_Health\", None), FriedPotato_Consumption=data.get(\"FriedPotato_Consumption\", None), Green_Vegetables_Consumption=data.get(\"Green_Vegetables_Consumption\", None), Diabetes=data.get(\"Diabetes\", None), Fruit_Consumption=data.get(\"Fruit_Consumption\", None), Smoking_History=data.get(\"Smoking_History\", None), BMI=data.get(\"BMI\", None), Weight_kg=data.get(\"Weight_kg\", None), Height_cm=data.get(\"Height_cm\", None), Age_Category=data.get(\"Age_Category\", None), Sex=data.get(\"Sex\", None), Alcohol_Consumption=data.get(\"Alcohol_Consumption\", None), Arthritis=data.get(\"Arthritis\", None), ECGAnomaly=data.get(\"ECGAnomaly\", None), HR_GRT_100=data.get(\"HR_GRT_100\", None), HRV_AVG_1H=data.get(\"HRV_AVG_1H\", None), Diastolic_GRT_90=data.get(\"Diastolic_GRT_90\", None), Heart_Disease=data.get(\"Heart_Disease\", None)\n )\n for data in output_list:\n if \"prediction_error\" in data:\n resp.prediction_error = data[\"prediction_error\"]\n elif \"prediction_warning\" in data:\n resp.prediction_warning = data[\"prediction_warning\"]\n return resp\n else:\n response.raise_for_status()\n\n except Exception as e:\n return _OutputResponse_(prediction_error={\"error_detail\": str(e)})\n " }, { "keys": [ "proj_pda1fj0a1", "Prediction", "CFG", "heart_risk_pred", "na", "na" ], "values": { "prediction_name": "heart_risk_pred", "model_name": "health_risk_model", "model_version": 1, "advanced_setting": true, "source_type": "http", "source_name": "", "dest_type": "http", "dest_name": "", "custom_processor": "", "basis_overrides": [], "modified_time": "2026-05-14 22:01:40", "modified_by": "aizendev", "version": 2 } }, { "keys": [ "proj_pda1fj0a1", "ProviderUser", "LLMApp", "myopenai", "agent1", "na" ], "values": "na" }, { "keys": [ "proj_pda1fj0a1", "Resource", "CFG", "CreateDS", "na", "na" ], "values": { "job_type": "dataset", "resource_type": "dataset", "resource_name": "CreateDS", "advanced_setting": true, "remote_gpu": false, "remote_type": "Remote Static Cluster", "provider_name": "", "dataset_size": "100M-1B rows", "dataset": { "num_workers": 4, "cpu": 2, "mem": 16384, "gpu": 0, "driver_cpu": 2, "driver_mem": 8192 }, "featureview": { "num_workers": 1, "cpu_min": 1, "cpu_max": 2, "gpu": 0, "mem_min": 1024, "mem_max": 2048 }, "datasink_size": "0-1M rows", "datasink_rate": "0-10K rows/sec", "prediction_rate": "0-10K req/sec", "llm_rate": "0-10K req/sec", "vectorstore_rate": "0-10K req/sec", "llmapp_rate": "0-10K req/sec", "runtime_size": "small", "featureset": { "realtime": { "num_workers": 2, "cpu": 1, "mem": 2048, "gpu": 0, "driver_cpu": 1, "driver_mem": 1024 } }, "prediction": { "num_workers": 1, "cpu_min": 2, "cpu_max": 2, "gpu": 0, "mem_min": 4096, "mem_max": 8192 }, "llm": { "num_workers": 1, "cpu_min": 4, "cpu_max": 8, "gpu": 0, "mem_min": 16384, "mem_max": 65536 }, "vectorstore": { "num_workers": 1, "cpu_min": 1, "cpu_max": 4, "mem_min": 4096, "mem_max": 8192 }, "llmapp": { "num_workers": 1, "cpu_min": 1, "cpu_max": 4, "mem_min": 4096, "mem_max": 8192 }, "runtime": { "num_workers": 1, "cpu_min": 1, "cpu_max": 4, "gpu": 0, "mem_min": 16384, "mem_max": 32768 } } }, { "keys": [ "proj_pda1fj0a1", "Resource", "CFG", "CreateTrain", "na", "na" ], "values": { "job_type": "training", "resource_type": "dlearn", "datasink_size": "0-1M rows", "datasink_rate": "0-10K rows/sec", "dataset_size": "100M-1B rows", "prediction_rate": "0-10K req/sec", "llm_rate": "0-10K req/sec", "vectorstore_rate": "0-10K req/sec", "llmapp_rate": "0-10K req/sec", "runtime_size": "small", "featureset": { "realtime": { "num_workers": 2, "cpu": 1, "mem": 2048, "gpu": 0, "driver_cpu": 1, "driver_mem": 1024 } }, "dataset": { "num_workers": 4, "cpu": 2, "mem": 16384, "gpu": 0, "driver_cpu": 2, "driver_mem": 8192 }, "featureview": { "num_workers": 1, "cpu_min": 1, "cpu_max": 2, "gpu": 0, "mem_min": 1024, "mem_max": 2048 }, "dlearn": { "num_workers": 2, "cpu_min": 8, "cpu_max": 16, "gpu": 0, "mem_min": 16384, "mem_max": 65536 }, "prediction": { "num_workers": 1, "cpu_min": 2, "cpu_max": 2, "gpu": 0, "mem_min": 4096, "mem_max": 8192 }, "llm": { "num_workers": 1, "cpu_min": 4, "cpu_max": 8, "gpu": 0, "mem_min": 16384, "mem_max": 65536 }, "vectorstore": { "num_workers": 1, "cpu_min": 1, "cpu_max": 4, "mem_min": 4096, "mem_max": 8192 }, "llmapp": { "num_workers": 1, "cpu_min": 1, "cpu_max": 4, "mem_min": 4096, "mem_max": 8192 }, "runtime": { "num_workers": 1, "cpu_min": 1, "cpu_max": 4, "gpu": 0, "mem_min": 16384, "mem_max": 32768 }, "resource_name": "CreateTrain", "advanced_setting": true } }, { "keys": [ "proj_pda1fj0a1", "Resource", "CFG", "dataset_resource", "na", "na" ], "values": { "job_type": "dataset", "resource_name": "dataset_resource", "resource_type": "dataset", "advanced_setting": true, "remote_gpu": false, "remote_type": "Remote Static Cluster", "provider_name": "", "datasink_size": "0-1M rows", "datasink_rate": "0-10K rows/sec", "dataset_size": "0-1M rows", "prediction_rate": "0-10K req/sec", "llm_rate": "0-10K req/sec", "vectorstore_rate": "0-10K req/sec", "llmapp_rate": "0-10K req/sec", "runtime_size": "small", "featureset": {}, "featureview": { "num_workers": 1, "cpu_min": 4, "cpu_max": 4, "gpu": 0, "mem_min": 2048, "mem_max": 4096 }, "dataset": { "num_workers": 2, "cpu": 1, "gpu": 0, "mem": 4096, "driver_cpu": 1, "driver_mem": 4096 }, "dlearn": {}, "mlearn": {}, "prediction": {}, "llm": {}, "vectorstore": {}, "llmapp": {}, "runtime": {} } }, { "keys": [ "proj_pda1fj0a1", "Resource", "CFG", "dl_train_resource", "na", "na" ], "values": { "job_type": "training", "resource_name": "dl_train_resource", "resource_type": "dlearn", "advanced_setting": true, "remote_gpu": false, "remote_type": "Remote Static Cluster", "provider_name": "", "datasink_size": "", "datasink_rate": "", "dataset_size": "1M-100M rows", "prediction_rate": "", "llm_rate": "", "vectorstore_rate": "", "llmapp_rate": "", "runtime_size": "", "featureset": {}, "featureview": {}, "dataset": {}, "dlearn": { "num_workers": 2, "cpu_min": 8, "cpu_max": 16, "gpu": 0, "mem_min": 16384, "mem_max": 32768, "disk_size": 100 }, "mlearn": {}, "prediction": {}, "llm": {}, "vectorstore": {}, "llmapp": {}, "runtime": {} } }, { "keys": [ "proj_pda1fj0a1", "Resource", "CFG", "prediction_resource", "na", "na" ], "values": { "job_type": "prediction", "resource_name": "prediction_resource", "resource_type": "prediction", "advanced_setting": false, "remote_gpu": false, "remote_type": "Remote Static Cluster", "provider_name": "", "datasink_size": "", "datasink_rate": "", "dataset_size": "", "prediction_rate": "0-10K req/sec", "llm_rate": "", "vectorstore_rate": "", "llmapp_rate": "", "runtime_size": "", "featureset": {}, "featureview": { "num_workers": 1, "cpu_min": 1, "cpu_max": 2, "mem_min": 1024, "mem_max": 2048 }, "dataset": {}, "dlearn": {}, "mlearn": {}, "prediction": { "num_workers": 1, "cpu_min": 2, "cpu_max": 2, "gpu": 0, "mem_min": 4096, "mem_max": 8192 }, "llm": {}, "vectorstore": {}, "llmapp": {}, "runtime": {} } }, { "keys": [ "proj_pda1fj0a1", "Resource", "ConfUser", "default", "health_factors_sink", "na" ], "values": "na" }, { "keys": [ "proj_pda1fj0a1", "Resource", "ConfUser", "default", "health_risk_dataset", "na" ], "values": "na" }, { "keys": [ "proj_pda1fj0a1", "Resource", "ConfUser", "default", "health_risk_exp", "na" ], "values": "na" }, { "keys": [ "proj_pda1fj0a1", "Resource", "ConfUser", "default", "heart_risk_pred", "na" ], "values": "na" }, { "keys": [ "proj_pda1fj0a1", "Resource", "ConfUser", "default", "wearable_data_sink", "na" ], "values": "na" }, { "keys": [ "proj_pda1fj0a1", "Resource", "ConfUser", "health_risk_training", "dlearn", "na" ], "values": "na" }, { "keys": [ "proj_pda1fj0a1", "Resource", "ConfUser", "health_risk_training", "undefined", "na" ], "values": "na" }, { "keys": [ "proj_pda1fj0a1", "Resource", "ServiceUser", "dataset", "health_risk_dataset", "default" ], "values": "na" }, { "keys": [ "proj_pda1fj0a1", "Resource", "ServiceUser", "datasink", "health_factors_sink", "default" ], "values": "na" }, { "keys": [ "proj_pda1fj0a1", "Resource", "ServiceUser", "datasink", "wearable_data_sink", "default" ], "values": "na" }, { "keys": [ "proj_pda1fj0a1", "Resource", "ServiceUser", "prediction", "heart_risk_pred", "default" ], "values": "na" }, { "keys": [ "proj_pda1fj0a1", "Resource", "ServiceUser", "training", "dlearn", "health_risk_training" ], "values": "na" }, { "keys": [ "proj_pda1fj0a1", "Resource", "ServiceUser", "training", "health_risk_exp", "default" ], "values": "na" }, { "keys": [ "proj_pda1fj0a1", "Resource", "ServiceUser", "training", "undefined", "health_risk_training" ], "values": "na" }, { "keys": [ "proj_pda1fj0a1", "Resource", "Type", "dataset", "CreateDS", "na" ], "values": "na" }, { "keys": [ "proj_pda1fj0a1", "Resource", "Type", "dataset", "dataset_resource", "na" ], "values": "na" }, { "keys": [ "proj_pda1fj0a1", "Resource", "Type", "dlearn", "CreateTrain", "na" ], "values": "na" }, { "keys": [ "proj_pda1fj0a1", "Resource", "Type", "dlearn", "dl_train_resource", "na" ], "values": "na" }, { "keys": [ "proj_pda1fj0a1", "Resource", "Type", "prediction", "prediction_resource", "na" ], "values": "na" }, { "keys": [ "proj_pda1fj0a1", "Training", "CFG", "health_risk_exp", "na", "na" ], "values": { "exp_name": "health_risk_exp", "model_name": "health_risk_model", "exp_desc": "", "exp_type": "Deep Learning", "train_config_setting": "Basic Settings", "ml_type": "regression", "ml_algo": [], "num_clusters": 5, "forecast_horizon": 3, "llm_finetune": false, "dataset_name": "health_risk_dataset", "column_list": { "monitor_time": { "type": "input", "data_type": "timestamp", "ml_type": "datetime" }, "PatientID": { "type": "input", "data_type": "long", "ml_type": "category" }, "Checkup": { "type": "input", "data_type": "string", "ml_type": "category" }, "General_Health": { "type": "input", "data_type": "string", "ml_type": "category" }, "Exercise": { "type": "input", "data_type": "string", "ml_type": "category" }, "Heart_Disease": { "type": "label", "data_type": "string", "ml_type": "category" }, "Skin_Cancer": { "type": "input", "data_type": "string", "ml_type": "category" }, "Other_Cancer": { "type": "input", "data_type": "string", "ml_type": "category" }, "Depression": { "type": "input", "data_type": "string", "ml_type": "category" }, "Diabetes": { "type": "input", "data_type": "string", "ml_type": "category" }, "Arthritis": { "type": "input", "data_type": "string", "ml_type": "category" }, "Sex": { "type": "input", "data_type": "string", "ml_type": "category" }, "Age_Category": { "type": "input", "data_type": "string", "ml_type": "category" }, "Height_cm": { "type": "input", "data_type": "int", "ml_type": "category" }, "Weight_kg": { "type": "input", "data_type": "double", "ml_type": "category" }, "BMI": { "type": "input", "data_type": "double", "ml_type": "category" }, "Smoking_History": { "type": "input", "data_type": "string", "ml_type": "category" }, "Alcohol_Consumption": { "type": "input", "data_type": "int", "ml_type": "category" }, "Fruit_Consumption": { "type": "input", "data_type": "int", "ml_type": "category" }, "Green_Vegetables_Consumption": { "type": "input", "data_type": "int", "ml_type": "category" }, "FriedPotato_Consumption": { "type": "input", "data_type": "int", "ml_type": "category" }, "heart_rate_grt_100": { "type": "input", "data_type": "long", "ml_type": "numerical" }, "last_1h_avg_systolic": { "type": "input", "data_type": "double", "ml_type": "numerical" }, "last_1h_avg_diastolic": { "type": "input", "data_type": "double", "ml_type": "numerical" } }, "feature_list": { "monitor_time": { "ml_type": "datetime", "feature_config_setting": "Basic Settings", "usage": "unused", "feature_type": "datetime" }, "PatientID": { "ml_type": "category", "feature_config_setting": "Basic Settings", "usage": "unused", "feature_type": "category" }, "Checkup": { "ml_type": "category", "feature_config_setting": "Basic Settings", "usage": "input", "feature_type": "category" }, "General_Health": { "ml_type": "category", "feature_config_setting": "Basic Settings", "usage": "input", "feature_type": "category" }, "Exercise": { "ml_type": "category", "feature_config_setting": "Basic Settings", "usage": "input", "feature_type": "category" }, "Heart_Disease": { "ml_type": "category", "feature_config_setting": "Basic Settings", "usage": "output", "feature_type": "category" }, "Skin_Cancer": { "ml_type": "category", "feature_config_setting": "Basic Settings", "usage": "input", "feature_type": "category" }, "Other_Cancer": { "ml_type": "category", "feature_config_setting": "Basic Settings", "usage": "input", "feature_type": "category" }, "Depression": { "ml_type": "category", "feature_config_setting": "Basic Settings", "usage": "input", "feature_type": "category" }, "Diabetes": { "ml_type": "category", "feature_config_setting": "Basic Settings", "usage": "input", "feature_type": "category" }, "Arthritis": { "ml_type": "category", "feature_config_setting": "Basic Settings", "usage": "input", "feature_type": "category" }, "Sex": { "ml_type": "category", "feature_config_setting": "Basic Settings", "usage": "input", "feature_type": "category" }, "Age_Category": { "ml_type": "category", "feature_config_setting": "Basic Settings", "usage": "input", "feature_type": "category" }, "Height_cm": { "ml_type": "category", "feature_config_setting": "Basic Settings", "usage": "input", "feature_type": "numerical" }, "Weight_kg": { "ml_type": "category", "feature_config_setting": "Basic Settings", "usage": "input", "feature_type": "numerical" }, "BMI": { "ml_type": "category", "feature_config_setting": "Basic Settings", "usage": "input", "feature_type": "numerical" }, "Smoking_History": { "ml_type": "category", "feature_config_setting": "Basic Settings", "usage": "input", "feature_type": "category" }, "Alcohol_Consumption": { "ml_type": "category", "feature_config_setting": "Basic Settings", "usage": "input", "feature_type": "numerical" }, "Fruit_Consumption": { "ml_type": "category", "feature_config_setting": "Basic Settings", "usage": "input", "feature_type": "numerical" }, "Green_Vegetables_Consumption": { "ml_type": "category", "feature_config_setting": "Basic Settings", "usage": "input", "feature_type": "numerical" }, "FriedPotato_Consumption": { "ml_type": "category", "feature_config_setting": "Basic Settings", "usage": "input", "feature_type": "numerical" }, "heart_rate_grt_100": { "ml_type": "numerical", "feature_config_setting": "Basic Settings", "usage": "input", "feature_type": "numerical" }, "last_1h_avg_systolic": { "ml_type": "numerical", "feature_config_setting": "Basic Settings", "usage": "input", "feature_type": "numerical" }, "last_1h_avg_diastolic": { "ml_type": "numerical", "feature_config_setting": "Basic Settings", "usage": "input", "feature_type": "numerical" }, "ECGAnomaly": { "feature_type": "category", "usage": "unused" } }, "input_features": [ "Checkup", "General_Health", "Exercise", "Skin_Cancer", "Other_Cancer", "Depression", "Diabetes", "Arthritis", "Sex", "Age_Category", "Height_cm", "Weight_kg", "BMI", "Smoking_History", "Alcohol_Consumption", "Fruit_Consumption", "Green_Vegetables_Consumption", "FriedPotato_Consumption", "heart_rate_grt_100", "last_1h_avg_systolic", "last_1h_avg_diastolic" ], "output_features": [ "Heart_Disease" ], "llm": {}, "trainer": { "epochs": 20, "early_stops": null, "early_stop": 5, "learning_rate": 0.0001, "optimizer": "adam" }, "version": 1, "created_time": "2026-05-14 19:33:33", "modified_time": "2026-05-14 19:33:33", "created_by": "aizendev", "modified_by": "aizendev" } } ]