Disease Risk Prediction

This dataset contains 9,254 synthetic patient records with demographic information, health measurements, lifestyle factors, medical history, medication use, sleep, and stress levels. It is designed for educational machine-learning and statistical analysis, particularly for predicting whether a patient has High or Low disease risk.

Suitable for: Logistic Regression, Classification, Decision Tree, Random Forest, and Feature Importance.

❤️‍🩹 Healthcare Disease Risk Prediction 📦 9,254 rows × 21 cols 💾 922 KB ⬇ 1 downloads

Preview

Patient_ID	Age	Gender	BMI	Blood_Pressure_Systolic	Blood_Pressure_Diastolic	Heart_Rate	Glucose_Level	Cholesterol	HDL	LDL	Triglycerides	Smoking_Status	Alcohol_Use	Physical_Activity	Family_History	Previous_Diagnosis	Medication_Count	Sleep_Hours	Stress_Level	Disease_Risk
PAT00001	39	Other	26.3	117	91	89	82	206.0	20	144	63	Former	Regular	Low	Yes	Heart Disease	3	7.8	Low	High
PAT00002	24	Male	24.3	102	75	68	81	172.0	53	130	224	Never	Occasional	Moderate	Yes	None	5	6.2	Moderate	Low
PAT00003	50	Female	33.6	113	71	82	90	189.0	62	129	153	Never	None	Low	Yes	None	2	4.9	Low	High
PAT00004	45	Female	28.7	152	81	83	101	200.0	47	174	304	Never	Occasional	High	Yes	Hypertension	0	8.9	Moderate	High
PAT00005	67	Female	21.4	104	86	65	114	155.0	52	123	222	Never	None	Moderate	No	None	1	6.0	Moderate	Low
PAT00006	49	Female	32.4	137	81	84	116	167.0	67	178	117	Former	Occasional	Low	No	Heart Disease	0	6.8	Low	High
PAT00007	33	Male	35.1	155	97	69	103	280.0	45	116	176	Former	Occasional	Low	No	None	1	7.3	Moderate	Low
PAT00008	21	Male	31.0	130	60	96	65	169.0	58	113	155	Former	Occasional	Moderate	No	None	2	5.9	High	Low

Showing first 8 rows of 9,254.

Download this dataset

Requires a paid plan or 10 Vault credits.

CSV 🔒 JSON 🔒 Excel (.xlsx) 🔒

Create a free account to preview more, then upgrade or earn credits to download.