bio-machine-learning-survival-analysis

Kaplan-Meier Curves

from lifelines import KaplanMeierFitter
import matplotlib.pyplot as plt

kmf = KaplanMeierFitter()

## Compare Groups with Log-Rank Test

```python
from lifelines import KaplanMeierFitter
from lifelines.statistics import logrank_test
import matplotlib.pyplot as plt

fig, ax = plt.subplots(figsize=(8, 6))

for group, color in zip(['high', 'low'], ['red', 'blue']):
    mask = df['risk_group'] == group
    kmf = KaplanMeierFitter()
    kmf.fit(df.loc[mask, 'time'], event_observed=df.loc[mask, 'event'], label=group)
    kmf.plot_survival_function(ax=ax, color=color)

## Log-rank test

high = df[df['risk_group'] == 'high']
low = df[df['risk_group'] == 'low']
results = logrank_test(high['time'], low['time'], event_observed_A=high['event'], event_observed_B=low['event'])
print(f'Log-rank p-value: {results.p_value:.4e}')

ax.set_xlabel('Time (months)')
ax.set_ylabel('Survival probability')
ax.set_title(f'Log-rank p = {results.p_value:.4e}')
plt.savefig('km_comparison.png', dpi=150)