Model description

This model was created following the instructions in the following Kaggle notebook: https://www.kaggle.com/code/thedankdel/disease-symptom-prediction-ml-99

This model allows you to predict diseases through their symptoms.

The possible classified diseases are:

'Acne', 'Hyperthyroidism', 'AIDS', 'Chronic cholestasis', 'Hypertension', 'Hypoglycemia', 'Arthritis', 'Hepatitis B', 'Migraine', 'Urinary tract infection', 'Diabetes', 'Hepatitis D', 'Psoriasis', 'Alcoholic hepatitis', 'Dimorphic hemmorhoids(piles)', 'Hepatitis E', 'Cervical spondylosis', 'Bronchial Asthma', 'hepatitis A', 'Allergy', 'Hepatitis C', 'Pneumonia', 'Hypothyroidism', 'Gastroenteritis', 'Varicose veins', 'Jaundice', 'Drug Reaction', '(vertigo) Paroymsal Positional Vertigo', 'Heart attack', 'Tuberculosis', 'Typhoid', 'Common Cold', 'Peptic ulcer diseae', 'Paralysis (brain hemorrhage)', 'Fungal infection', 'Impetigo', 'GERD', 'Dengue', 'Malaria', 'Chicken pox', 'Osteoarthristis'

The possible symptoms are:

'itching', 'skin rash', 'nodal skin eruptions', 'continuous sneezing', 'shivering', 'chills', 'joint pain', 'stomach pain', 'acidity', 'ulcers on tongue', 'muscle wasting', 'vomiting', 'burning micturition', 'spotting urination', 'fatigue', 'weight gain', 'anxiety', 'cold hands and feets', 'mood swings', 'weight loss', 'restlessness', 'lethargy', 'patches in throat', 'irregular sugar level', 'cough', 'high fever', 'sunken eyes', 'breathlessness', 'sweating', 'dehydration', 'indigestion', 'headache', 'yellowish skin', 'dark urine', 'nausea', 'loss of appetite', 'pain behind the eyes', 'back pain', 'constipation', 'abdominal pain', 'diarrhoea', 'mild fever', 'yellow urine', 'yellowing of eyes', 'acute liver failure', 'fluid overload', 'swelling of stomach', 'swelled lymph nodes', 'malaise', 'blurred and distorted vision', 'phlegm', 'throat irritation', 'redness of eyes', 'sinus pressure', 'runny nose', 'congestion', 'chest pain', 'weakness in limbs', 'fast heart rate', 'pain during bowel movements', 'pain in anal region', 'bloody stool', 'irritation in anus', 'neck pain', 'dizziness', 'cramps', 'bruising', 'obesity', 'swollen legs', 'swollen blood vessels', 'puffy face and eyes', 'enlarged thyroid', 'brittle nails', 'swollen extremeties', 'excessive hunger', 'extra marital contacts', 'drying and tingling lips', 'slurred speech', 'knee pain', 'hip joint pain', 'muscle weakness', 'stiff neck', 'swelling joints', 'movement stiffness', 'spinning movements', 'loss of balance', 'unsteadiness', 'weakness of one body side', 'loss of smell', 'bladder discomfort', 'foul smell ofurine', 'continuous feel of urine', 'passage of gases', 'internal itching', 'toxic look (typhos)', 'depression', 'irritability', 'muscle pain', 'altered sensorium', 'red spots over body', 'belly pain', 'abnormal menstruation', 'dischromic patches', 'watering from eyes', 'increased appetite', 'polyuria', 'family history', 'mucoid sputum', 'rusty sputum', 'lack of concentration', 'visual disturbances', 'receiving blood transfusion', 'receiving unsterile injections', 'coma', 'stomach bleeding', 'distention of abdomen', 'history of alcohol consumption', 'blood in sputum', 'prominent veins on calf', 'palpitations', 'painful walking', 'pus filled pimples', 'blackheads', 'scurring', 'skin peeling', 'silver like dusting', 'small dents in nails', 'inflammatory nails', 'blister', 'red sore around nose', 'yellow crust ooze', 'prognosis'

Intended uses & limitations

This model follows the limitations of the Apache 2.0 license.

Hyperparameters

Click to expand

Hyperparameter	Value
bootstrap	True
ccp_alpha	0.0
class_weight
criterion	gini
max_depth	13
max_features	sqrt
max_leaf_nodes
max_samples
min_impurity_decrease	0.0
min_samples_leaf	1
min_samples_split	2
min_weight_fraction_leaf	0.0
n_estimators	500
n_jobs
oob_score	False
random_state	42
verbose	0
warm_start	False

Model Plot

RandomForestClassifier(max_depth=13, n_estimators=500, random_state=42)

In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.

Evaluation Results

Metric	Value
accuracy	0.995935
f1 score	0.995935

How to Get Started with the Model

This model can be tested by running the code contained in this Github notebook: https://github.com/gianlab/machine-learning-notebooks/blob/main/Disease_prediction_random_forest.ipynb