bbjonah/Maternal-Mortality-Risk-Prediction-in-Low-Resource-Settings
Domain:
healthcareRecord type:
model
Creator:
bbj
Host:
This project uses machine learning to predict maternal mortality risk in low-resource settings using synthetic healthcare data. It analyzes maternal health, clinical, and healthcare access factors to identify high-risk pregnancies, generate risk scores, and support data-driven maternal health interventions and early risk detection.
# ==========================================================
# Maternal Mortality Risk Prediction in Low-Resource Settings
# ==========================================================
# Author: Jona Buka
# Description:
# Machine Learning pipeline for predicting maternal mortality
# risk using synthetic maternal healthcare data.
# ==========================
# IMPORT LIBRARIES
# ==========================
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import warnings
warnings.filterwarnings("ignore")
from sklearn.model_selection import train_test_split
from sklearn.impute import SimpleImputer
from sklearn.preprocessing import LabelEncoder
from sklearn.metrics import (
classification_report,
confusion_matrix,
accuracy_score,
roc_auc_score,
roc_curve
)
from sklearn.ensemble import RandomForestClassifier
from sklearn.compose import ColumnTransformer
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import OneHotEncoder
from sklearn.impute import SimpleImputer
from sklearn.metrics import ConfusionMatrixDisplay
from imblearn.over_sampling import SMOTE
import joblib
# ==========================
# LOAD DATASET
# ==========================
df = pd.read_csv("maternal_mortality_dataset.csv")
print("Dataset Shape:", df.shape)
print(df.head())
# ==========================
# TARGET VARIABLE
# ==========================
target = "maternal_death"
# ==========================
# REMOVE DATA LEAKAGE FEATURES
# ==========================
# These variables directly indicate death outcome
leakage_columns = [
"time_to_death_hours",
"cause_of_death",
"maternal_near_miss"
]
# Drop patient identifier
id_columns = ["patient_id"]
columns_to_drop = leakage_columns + id_columns
existing_cols = [col for col in columns_to_drop if col in df.columns]
df.drop(columns=existing_cols, inplace=True)
# ==========================
# HANDLE DATE COLUMN
# ==========================
if "admission_date" in df.columns:
df["admission_date"] = …