Why show a dataset to doctors?
A dataset is simply a table of consistently organised records. In this example, one row represents one fictional patient and each column represents a recorded item. The aim is to make the connection between bedside documentation and later analysis visible.
Read the coloured columns
- Doctor’s examination: patient details, symptoms and examination findings.
- Vitals kiosk: height, weight, calculated BMI and recorded observations.
- Laboratory: the investigation values included in the example.
- Provisional diagnosis: the example label a prediction model might be asked to learn.
What to look for as you browse
Choose a department and read across one row. Ask whether the findings, units and diagnosis are understandable, whether an item was actually assessed and how a missing result is represented. A shared patient identifier is what would connect entries made by different teams.
How the data might be used
A suitable real dataset could support audits, service planning or research. XGBoost, mentioned in the original project, is one type of prediction software that learns relationships from labelled tables. Doctors do not need to write the model to help define clinically meaningful fields and check whether the labels are trustworthy.
What this example cannot show
The records are synthetic: they were created for demonstration and do not belong to real patients. Each department has only ten example rows. The values and diagnosis labels illustrate a table structure; they are not clinical reference ranges or evidence that a model can diagnose patients.
Do not use this sample to establish model accuracy. Real evaluation would need an appropriate dataset and a clear account of which information was available at the time of each prediction.
Browse the fictional records
| Patient ID | Age | Sex | Fever | Cough | Breathlessness | Generalized weakness / fatigability | Abdominal pain | Chest pain | Headache | Loss of appetite / weight loss | Nausea / vomiting | Swelling of feet (pedal edema) | Pallor | Icterus | Cyanosis | Clubbing | Lymphadenopathy | Edema | JVP | Thyroid swelling | Height (cm) | Weight (kg) | BMI | Pulse (bpm) | Temp (F) | BP (mmHg) | SpO2 (%) | Resp. Rate (/min) | Blood Group | Hb (g/dL) | TLC (/cumm) | ALC (/cumm) | Platelet count (/cumm) | ESR (mm/hr) | CRP (mg/L) | RBS (mg/dL) | HbA1c (%) | Bl. Urea (mg/dL) | Sr. Creatinine (mg/dL) | Sr. Uric acid (mg/dL) | Na (mEq/L) | K (mEq/L) | Cl (mEq/L) | Sr. Bilirubin Total (mg/dL) | Sr. Bilirubin Conjugated (mg/dL) | Sr. Bilirubin Unconjugated (mg/dL) | SGOT / AST (U/L) | SGPT / ALT (U/L) | GGT (U/L) | Albumin (g/dL) | Globulin (g/dL) | Total Protein (g/dL) | ALP (U/L) | PT INR | T3 (ng/dL) | T4 (µg/dL) | TSH (µIU/mL) | Total Cholesterol (mg/dL) | Triglyceride (mg/dL) | LDL (mg/dL) | HDL (mg/dL) | VLDL (mg/dL) | MCV (fL) | Provisional Diagnosis |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| MED-001 | 58 | M | 1 | 1 | 1 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | Absent | Absent | Absent | Absent | Absent | Absent | Not raised | Absent | 171 | 67.5 | 23.1 | 101 | 101.6 | 118/74 | 90 | 27 | B+ | 14.7 | 12592 | 2471 | 229146 | 38 | 66 | 74 | 4.8 | 23 | 0.7 | 5.5 | 136 | 3.6 | 105 | 0.73 | 0.21 | 0.32 | 24 | 27 | 18 | 4.4 | 2.6 | 6.9 | 73 | 1.2 | 120 | 6.5 | 3.32 | 143 | 138 | 51 | 35 | 28 | 92 | Community-acquired pneumonia |
| MED-002 | 31 | F | 1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | Absent | Absent | Absent | Absent | Absent | Present | Not raised | Absent | 156 | 56.3 | 23.1 | 93 | 100.1 | 114/71 | 90 | 26 | O+ | 14 | 8711 | 2362 | 232671 | 35 | 75.3 | 127 | 5.9 | 21 | 0.84 | 5.6 | 142 | 4 | 100 | 0.47 | 0.08 | 0.76 | 39 | 25 | 40 | 4.3 | 2.5 | 7.2 | 116 | 1.05 | 151 | 4.3 | 3.32 | 183 | 118 | 102 | 28 | 24 | 90 | Community-acquired pneumonia |
| MED-003 | 58 | F | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | Absent | Absent | Absent | Absent | Absent | Absent | Raised | Absent | 165 | 58.8 | 21.6 | 89 | 98.1 | 127/80 | 91 | 22 | O+ | 14.3 | 8146 | 2684 | 218408 | 12 | 2.8 | 82 | 5.6 | 29 | 0.9 | 4.9 | 130 | 4 | 100 | 0.56 | 0.18 | 0.68 | 43 | 27 | 33 | 4.2 | 2 | 7 | 86 | 1.25 | 116 | 8.4 | 2.47 | 145 | 176 | 119 | 56 | 19 | 96 | Congestive heart failure |
| MED-004 | 31 | F | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | Absent | Absent | Absent | Absent | Absent | Present | Raised | Absent | 146 | 54.4 | 25.5 | 113 | 97.9 | 115/72 | 91 | 22 | B+ | 11 | 8103 | 1669 | 271312 | 8 | 8.6 | 94 | 5.4 | 33 | 0.65 | 5.5 | 138 | 3.6 | 102 | 0.88 | 0.28 | 0.35 | 17 | 30 | 33 | 4.3 | 2.9 | 6.7 | 90 | 1.07 | 106 | 10.6 | 2.97 | 144 | 156 | 76 | 56 | 35 | 83 | Congestive heart failure |
| MED-005 | 22 | F | 0 | 0 | 0 | 1 | 0 | 0 | 1 | 0 | 0 | 0 | Present | Absent | Absent | Present | Absent | Absent | Not raised | Absent | 161 | 64.9 | 25 | 102 | 99.3 | 118/74 | 96 | 16 | A+ | 7.5 | 7884 | 2371 | 262451 | 20 | 4 | 134 | 5.4 | 46 | 1.03 | 4.3 | 136 | 4.4 | 100 | 1.01 | 0.25 | 0.59 | 21 | 14 | 26 | 4.5 | 2.9 | 6.4 | 88 | 1.08 | 102 | 8.2 | 2.56 | 146 | 144 | 114 | 59 | 34 | 59 | Nutritional anemia |
| MED-006 | 71 | M | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | Absent | Absent | Absent | Absent | Present | Absent | Not recorded / N.A. | Absent | 162 | 66.3 | 25.3 | 100 | 98.7 | 150/94 | 91 | 26 | A+ | 15 | 8977 | 2042 | 284154 | 9 | 3.3 | 99 | 5.5 | 43 | 0.53 | 6 | 129 | 4 | 104 | 0.82 | 0.09 | 0.46 | 33 | 20 | 32 | 4.2 | 2.5 | 8.1 | 98 | 0.89 | 124 | 7.1 | 3.35 | 156 | 125 | 113 | 57 | 16 | 86 | Congestive heart failure |
| MED-007 | 60 | F | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 | 0 | Absent | Absent | Absent | Absent | Present | Present | Not raised | Absent | 152 | 48.9 | 21.2 | 94 | 98.6 | 109/68 | 99 | 22 | O+ | 15.2 | 5721 | 1958 | 307011 | 9 | 5.3 | 122 | 5.1 | 27 | 0.3 | 4.1 | 138 | 3.7 | 106 | 0.37 | 0.16 | 0.63 | 40 | 15 | 42 | 4.2 | 2.4 | 7.2 | 89 | 1 | 121 | 7.5 | 2.61 | 200 | 193 | 69 | 69 | 10 | 87 | Tension-type headache |
| MED-008 | 63 | M | 1 | 1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | Absent | Absent | Absent | Absent | Absent | Absent | Raised | Absent | 172 | 72.3 | 24.4 | 91 | 98.3 | 116/73 | 90 | 25 | O+ | 14.1 | 6961 | 2650 | 263828 | 20 | 5.9 | 93 | 5.3 | 32 | 1.02 | 5.2 | 139 | 4.7 | 99 | 0.96 | 0.18 | 0.56 | 37 | 33 | 38 | 4.7 | 2.8 | 7.3 | 79 | 1.08 | 117 | 8.1 | 3.1 | 155 | 214 | 75 | 36 | 35 | 93 | Congestive heart failure |
| MED-009 | 59 | M | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | Absent | Absent | Absent | Present | Absent | Absent | Not raised | Absent | 172 | 76.1 | 25.7 | 95 | 100.4 | 120/75 | 89 | 25 | B+ | 13.3 | 11524 | 2039 | 268582 | 37 | 39.4 | 112 | 5.6 | 23 | 0.81 | 5.5 | 135 | 3.6 | 99 | 0.74 | 0.23 | 0.9 | 35 | 25 | 30 | 3.8 | 2.8 | 6.9 | 91 | 0.98 | 130 | 10.1 | 2.39 | 192 | 158 | 90 | 50 | 26 | 89 | Community-acquired pneumonia |
| MED-010 | 43 | M | 0 | 0 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 1 | Absent | Absent | Absent | Absent | Absent | Absent | Raised | Absent | 163 | 62.7 | 23.6 | 99 | 99.1 | 127/80 | 94 | 22 | A+ | 14.9 | 8275 | 3295 | 213627 | 8 | 2.2 | 70 | 5.3 | 22 | 0.93 | 5.6 | 145 | 4.6 | 99 | 0.53 | 0.25 | 0.34 | 43 | 35 | 25 | 3.5 | 3.3 | 6.9 | 110 | 0.92 | 108 | 8 | 2.55 | 166 | 155 | 73 | 47 | 27 | 91 | Congestive heart failure |