{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "223a0201",
   "metadata": {},
   "source": [
    "# Fair Code - Audit 06: Healthcare Readmission - Clinical Bias\n",
    "\n",
    "> *A hospital readmission model flags patients for high clinical risk using payer code and discharge destination - variables that measure insurance access, not medical severity.*\n",
    "\n",
    "**Dataset:** Diabetes 130-US Hospitals 1999–2008 - `diabetic_data.csv` (101,766 records)  \n",
    "**Protected attributes:** Race, Gender, Age  \n",
    "**Proxy variables:** `payer_code` (Medicaid rate differs by race), `discharge_disposition_id` (SNF access differs by race), `medical_specialty` (encodes insurance access), `number_inpatient` (prior hospitalisations encode preventive care gaps)  \n",
    "**Fairness metric:** Demographic Parity  \n",
    "**Model:** Random Forest Classifier  \n",
    "\n",
    "---\n",
    "\n",
    "Pipeline:\n",
    "1. Load and explore the dataset\n",
    "2. Identify the proxy variables (four of them)\n",
    "3. Train the biased model (protected attributes + proxies included)\n",
    "4. Measure the fairness gaps across three dimensions\n",
    "5. Train the fair model (all removed)\n",
    "6. Compare results"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1c4a57ea",
   "metadata": {},
   "source": [
    "## 1. Setup"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "c588824d",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-09-24T03:34:39.637007Z",
     "iopub.status.busy": "2026-09-24T03:34:39.636774Z",
     "iopub.status.idle": "2026-09-24T03:34:41.829514Z",
     "shell.execute_reply": "2026-09-24T03:34:41.829048Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Libraries loaded.\n"
     ]
    }
   ],
   "source": [
    "import pandas as pd\n",
    "from pathlib import Path\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "import matplotlib.patches as mpatches\n",
    "from sklearn.ensemble import RandomForestClassifier\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.metrics import accuracy_score\n",
    "from sklearn.preprocessing import LabelEncoder\n",
    "from scipy.stats import chi2_contingency\n",
    "\n",
    "# Consistent styling across all Fair Code notebooks\n",
    "plt.rcParams.update({\n",
    "    'figure.facecolor': '#0d0f14',\n",
    "    'axes.facecolor': '#131620',\n",
    "    'axes.edgecolor': '#1e2130',\n",
    "    'axes.labelcolor': '#b0aec0',\n",
    "    'xtick.color': '#b0aec0',\n",
    "    'ytick.color': '#b0aec0',\n",
    "    'text.color': '#d4cfc0',\n",
    "    'grid.color': '#1e2130',\n",
    "    'grid.linestyle': '--',\n",
    "    'font.family': 'monospace',\n",
    "    'figure.dpi': 120\n",
    "})\n",
    "\n",
    "ACCENT = '#c9a84c'   # Fair Code gold\n",
    "DANGER = '#9b2335'   # red - bias\n",
    "SAFE   = '#4a7c6f'   # teal - mitigated\n",
    "MUTED  = '#b0aec0'\n",
    "\n",
    "print('Libraries loaded.')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "079ce54b",
   "metadata": {},
   "source": [
    "## 2. Load and Explore the Dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "51a7828c",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-09-24T03:34:41.833944Z",
     "iopub.status.busy": "2026-09-24T03:34:41.833721Z",
     "iopub.status.idle": "2026-09-24T03:34:59.467047Z",
     "shell.execute_reply": "2026-09-24T03:34:59.466438Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Dataset: 101,766 rows, 50 columns\n",
      "\n",
      "Columns: ['encounter_id', 'patient_nbr', 'race', 'gender', 'age', 'weight', 'admission_type_id', 'discharge_disposition_id', 'admission_source_id', 'time_in_hospital', 'payer_code', 'medical_specialty', 'num_lab_procedures', 'num_procedures', 'num_medications', 'number_outpatient', 'number_emergency', 'number_inpatient', 'diag_1', 'diag_2', 'diag_3', 'number_diagnoses', 'max_glu_serum', 'A1Cresult', 'metformin', 'repaglinide', 'nateglinide', 'chlorpropamide', 'glimepiride', 'acetohexamide', 'glipizide', 'glyburide', 'tolbutamide', 'pioglitazone', 'rosiglitazone', 'acarbose', 'miglitol', 'troglitazone', 'tolazamide', 'examide', 'citoglipton', 'insulin', 'glyburide-metformin', 'glipizide-metformin', 'glimepiride-pioglitazone', 'metformin-rosiglitazone', 'metformin-pioglitazone', 'change', 'diabetesMed', 'readmitted']\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>encounter_id</th>\n",
       "      <th>patient_nbr</th>\n",
       "      <th>race</th>\n",
       "      <th>gender</th>\n",
       "      <th>age</th>\n",
       "      <th>weight</th>\n",
       "      <th>admission_type_id</th>\n",
       "      <th>discharge_disposition_id</th>\n",
       "      <th>admission_source_id</th>\n",
       "      <th>time_in_hospital</th>\n",
       "      <th>...</th>\n",
       "      <th>citoglipton</th>\n",
       "      <th>insulin</th>\n",
       "      <th>glyburide-metformin</th>\n",
       "      <th>glipizide-metformin</th>\n",
       "      <th>glimepiride-pioglitazone</th>\n",
       "      <th>metformin-rosiglitazone</th>\n",
       "      <th>metformin-pioglitazone</th>\n",
       "      <th>change</th>\n",
       "      <th>diabetesMed</th>\n",
       "      <th>readmitted</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2278392</td>\n",
       "      <td>8222157</td>\n",
       "      <td>Caucasian</td>\n",
       "      <td>Female</td>\n",
       "      <td>[0-10)</td>\n",
       "      <td>?</td>\n",
       "      <td>6</td>\n",
       "      <td>25</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>NO</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>149190</td>\n",
       "      <td>55629189</td>\n",
       "      <td>Caucasian</td>\n",
       "      <td>Female</td>\n",
       "      <td>[10-20)</td>\n",
       "      <td>?</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>7</td>\n",
       "      <td>3</td>\n",
       "      <td>...</td>\n",
       "      <td>No</td>\n",
       "      <td>Up</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>Ch</td>\n",
       "      <td>Yes</td>\n",
       "      <td>&gt;30</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>64410</td>\n",
       "      <td>86047875</td>\n",
       "      <td>AfricanAmerican</td>\n",
       "      <td>Female</td>\n",
       "      <td>[20-30)</td>\n",
       "      <td>?</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>7</td>\n",
       "      <td>2</td>\n",
       "      <td>...</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>No</td>\n",
       "      <td>Yes</td>\n",
       "      <td>NO</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>3 rows × 50 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   encounter_id  patient_nbr             race  gender      age weight  \\\n",
       "0       2278392      8222157        Caucasian  Female   [0-10)      ?   \n",
       "1        149190     55629189        Caucasian  Female  [10-20)      ?   \n",
       "2         64410     86047875  AfricanAmerican  Female  [20-30)      ?   \n",
       "\n",
       "   admission_type_id  discharge_disposition_id  admission_source_id  \\\n",
       "0                  6                        25                    1   \n",
       "1                  1                         1                    7   \n",
       "2                  1                         1                    7   \n",
       "\n",
       "   time_in_hospital  ... citoglipton insulin  glyburide-metformin  \\\n",
       "0                 1  ...          No      No                   No   \n",
       "1                 3  ...          No      Up                   No   \n",
       "2                 2  ...          No      No                   No   \n",
       "\n",
       "   glipizide-metformin  glimepiride-pioglitazone  metformin-rosiglitazone  \\\n",
       "0                   No                        No                       No   \n",
       "1                   No                        No                       No   \n",
       "2                   No                        No                       No   \n",
       "\n",
       "   metformin-pioglitazone  change diabetesMed readmitted  \n",
       "0                      No      No          No         NO  \n",
       "1                      No      Ch         Yes        >30  \n",
       "2                      No      No         Yes         NO  \n",
       "\n",
       "[3 rows x 50 columns]"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "CSV = Path('Healthcare Readmission') / 'diabetic_data.csv'\n",
    "if not CSV.exists():\n",
    "    CSV = Path('..') / 'Healthcare Readmission' / 'diabetic_data.csv'\n",
    "\n",
    "df_raw = pd.read_csv(CSV)\n",
    "print(f'Dataset: {df_raw.shape[0]:,} rows, {df_raw.shape[1]} columns')\n",
    "print(f'\\nColumns: {list(df_raw.columns)}')\n",
    "df_raw.head(3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "3368ba3c",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-09-24T03:34:59.474580Z",
     "iopub.status.busy": "2026-09-24T03:34:59.474444Z",
     "iopub.status.idle": "2026-09-24T03:34:59.661454Z",
     "shell.execute_reply": "2026-09-24T03:34:59.660857Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Protected group breakdown:\n",
      "  Female patients   : 53.8%\n",
      "  Racial minorities : 22.9%\n",
      "  Elderly (70+)     : 45.2%\n",
      "\n",
      "Overall 30-day readmission rate: 11.2%\n",
      "\n",
      "30-day readmission rate by gender (raw data):\n",
      "  Female    : 11.31%\n",
      "  Male      : 11.12%\n",
      "  Raw gap: 0.19 percentage points\n",
      "\n",
      "30-day readmission rate by race (raw data):\n",
      "  Caucasian/Asian : 11.28%\n",
      "  Other minorities: 11.04%\n",
      "  Raw gap: 0.24 percentage points\n"
     ]
    }
   ],
   "source": [
    "df = df_raw.copy()\n",
    "\n",
    "# Remove invalid entries\n",
    "df = df[~df['race'].isin(['?'])]\n",
    "df = df[df['gender'] != 'Unknown/Invalid']\n",
    "\n",
    "# Target: 1 = readmitted within 30 days (flagged as high clinical risk)\n",
    "#         0 = not readmitted within 30 days\n",
    "# In a real hospital tool this flag drives discharge planning and resource allocation\n",
    "df['target'] = (df['readmitted'] == '<30').astype(int)\n",
    "\n",
    "# Protected attribute flags - retained for fairness measurement only\n",
    "df['is_female']   = (df['gender'] == 'Female').astype(int)\n",
    "df['is_minority'] = (~df['race'].isin(['Caucasian', 'Asian'])).astype(int)\n",
    "df['age_numeric'] = df['age'].str.extract(r'\\[(\\d+)').astype(int)\n",
    "df['is_elderly']  = (df['age_numeric'] >= 70).astype(int)\n",
    "\n",
    "print('Protected group breakdown:')\n",
    "print(f'  Female patients   : {df[\"is_female\"].mean():.1%}')\n",
    "print(f'  Racial minorities : {df[\"is_minority\"].mean():.1%}')\n",
    "print(f'  Elderly (70+)     : {df[\"is_elderly\"].mean():.1%}')\n",
    "\n",
    "print(f'\\nOverall 30-day readmission rate: {df[\"target\"].mean():.1%}')\n",
    "\n",
    "print('\\n30-day readmission rate by gender (raw data):')\n",
    "gender_raw = df.groupby('gender')['target'].mean() * 100\n",
    "for g, v in gender_raw.items():\n",
    "    print(f'  {g:<10}: {v:.2f}%')\n",
    "print(f'  Raw gap: {abs(gender_raw[\"Male\"] - gender_raw[\"Female\"]):.2f} percentage points')\n",
    "\n",
    "print('\\n30-day readmission rate by race (raw data):')\n",
    "race_raw = df.groupby('is_minority')['target'].mean() * 100\n",
    "print(f'  Caucasian/Asian : {race_raw[0]:.2f}%')\n",
    "print(f'  Other minorities: {race_raw[1]:.2f}%')\n",
    "print(f'  Raw gap: {abs(race_raw[0] - race_raw[1]):.2f} percentage points')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "7bd4759e",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-09-24T03:34:59.662926Z",
     "iopub.status.busy": "2026-09-24T03:34:59.662839Z",
     "iopub.status.idle": "2026-09-24T03:35:00.418845Z",
     "shell.execute_reply": "2026-09-24T03:35:00.417998Z"
    }
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/var/folders/cd/j1lnk_z97vg07zgzfwvp03yr0000gn/T/ipykernel_41537/1679713148.py:42: UserWarning: Tight layout not applied. The bottom and top margins cannot be made large enough to accommodate all Axes decorations.\n",
      "  plt.tight_layout()\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1680x420 with 3 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Note: the raw gaps exist in the data before any model is trained.\n"
     ]
    }
   ],
   "source": [
    "fig, axes = plt.subplots(1, 3, figsize=(14, 3.5))\n",
    "\n",
    "# Readmission rate by gender\n",
    "gender_plot = df.groupby('gender')['target'].mean() * 100\n",
    "labels_g = ['Male', 'Female']\n",
    "vals_g = [gender_plot['Male'], gender_plot['Female']]\n",
    "bars = axes[0].bar(labels_g, vals_g, color=[MUTED, DANGER], width=0.4)\n",
    "for bar, val in zip(bars, vals_g):\n",
    "    axes[0].text(bar.get_x() + bar.get_width()/2, val + 0.03,\n",
    "                 f'{val:.2f}%', ha='center', color=ACCENT, fontsize=10)\n",
    "axes[0].set_title('30-day readmission by gender (raw)', color=MUTED, fontsize=10)\n",
    "axes[0].set_ylabel('% readmitted within 30 days')\n",
    "axes[0].set_ylim(0, 1.5)\n",
    "axes[0].grid(axis='y', alpha=0.3)\n",
    "\n",
    "# Readmission rate by race\n",
    "race_plot = df.groupby('is_minority')['target'].mean() * 100\n",
    "labels_r = ['Caucasian/Asian', 'Other minorities']\n",
    "vals_r = [race_plot[0], race_plot[1]]\n",
    "bars2 = axes[1].bar(labels_r, vals_r, color=[MUTED, DANGER], width=0.4)\n",
    "for bar, val in zip(bars2, vals_r):\n",
    "    axes[1].text(bar.get_x() + bar.get_width()/2, val + 0.03,\n",
    "                 f'{val:.2f}%', ha='center', color=ACCENT, fontsize=10)\n",
    "axes[1].set_title('30-day readmission by race (raw)', color=MUTED, fontsize=10)\n",
    "axes[1].set_ylabel('% readmitted within 30 days')\n",
    "axes[1].set_ylim(0, 1.5)\n",
    "axes[1].grid(axis='y', alpha=0.3)\n",
    "\n",
    "# Readmission rate by age group\n",
    "age_plot = df.groupby('is_elderly')['target'].mean() * 100\n",
    "labels_a = ['Under 70', '70+ (elderly)']\n",
    "vals_a = [age_plot[0], age_plot[1]]\n",
    "bars3 = axes[2].bar(labels_a, vals_a, color=[MUTED, DANGER], width=0.4)\n",
    "for bar, val in zip(bars3, vals_a):\n",
    "    axes[2].text(bar.get_x() + bar.get_width()/2, val + 0.03,\n",
    "                 f'{val:.2f}%', ha='center', color=ACCENT, fontsize=10)\n",
    "axes[2].set_title('30-day readmission by age (raw)', color=MUTED, fontsize=10)\n",
    "axes[2].set_ylabel('% readmitted within 30 days')\n",
    "axes[2].set_ylim(0, 1.5)\n",
    "axes[2].grid(axis='y', alpha=0.3)\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.show()\n",
    "print('Note: the raw gaps exist in the data before any model is trained.')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "64ebd294",
   "metadata": {},
   "source": [
    "## 3. Identify the Proxy Variables\n",
    "\n",
    "A proxy variable correlates with a protected attribute strongly enough to smuggle the bias back through the model - even after the protected column is removed.\n",
    "\n",
    "This audit has **four** proxy variables:\n",
    "\n",
    "| Proxy | Protected attribute | Mechanism |\n",
    "|---|---|---|\n",
    "| `payer_code` | Race | Medicaid rates: Hispanic 9.0%, AfricanAmerican 5.5%, Caucasian 2.7%. Insurance type encodes income, which is racially stratified. |\n",
    "| `discharge_disposition_id` | Race | SNF discharge rates: Caucasian 17.3% vs AfricanAmerican 10.7%. Post-acute care access is determined by insurance and geography, not clinical need. |\n",
    "| `medical_specialty` | Race, Income | Specialty access is stratified by insurance type and zip code. |\n",
    "| `number_inpatient` | Race | AfricanAmerican patients average 0.70 prior inpatient visits vs 0.48 for Asian patients - a gap driven by preventive care access, not clinical severity alone. |"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "7a7c1651",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-09-24T03:35:00.422115Z",
     "iopub.status.busy": "2026-09-24T03:35:00.421999Z",
     "iopub.status.idle": "2026-09-24T03:35:00.460451Z",
     "shell.execute_reply": "2026-09-24T03:35:00.459967Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "payer_code                p=0.0          proxy=True\n",
      "medical_specialty         p=0.0          proxy=True\n",
      "discharge_disposition_id  p=0.0          proxy=True\n",
      "number_inpatient          Pearson r=0.0146 (positive = minorities have higher prior counts)\n"
     ]
    }
   ],
   "source": [
    "def check_proxy(df, feature, protected_col):\n",
    "    \"\"\"Chi-squared test of independence. p < 0.05 = likely proxy.\"\"\"\n",
    "    contingency = pd.crosstab(df[feature], df[protected_col])\n",
    "    chi2, p, dof, _ = chi2_contingency(contingency)\n",
    "    return {'feature': feature, 'protected_attr': protected_col,\n",
    "            'p_value': round(p, 6), 'is_proxy': p < 0.05}\n",
    "\n",
    "# Test categorical proxies against race\n",
    "for feat in ['payer_code', 'medical_specialty']:\n",
    "    r = check_proxy(df, feat, 'race')\n",
    "    print(f\"{r['feature']:<25} p={r['p_value']:<12} proxy={r['is_proxy']}\")\n",
    "\n",
    "# Test discharge_disposition_id against race\n",
    "r = check_proxy(df, 'discharge_disposition_id', 'race')\n",
    "print(f\"{r['feature']:<25} p={r['p_value']:<12} proxy={r['is_proxy']}\")\n",
    "\n",
    "# number_inpatient - continuous, use correlation\n",
    "inpt_corr = df[['number_inpatient', 'is_minority']].corr().iloc[0, 1]\n",
    "print(f'number_inpatient          Pearson r={inpt_corr:.4f} (positive = minorities have higher prior counts)')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "5b8968db",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-09-24T03:35:00.461670Z",
     "iopub.status.busy": "2026-09-24T03:35:00.461603Z",
     "iopub.status.idle": "2026-09-24T03:35:00.476223Z",
     "shell.execute_reply": "2026-09-24T03:35:00.475827Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Medicaid payer rate by race:\n",
      "  AfricanAmerican        5.5%\n",
      "  Asian                  7.3%\n",
      "  Caucasian              2.7%\n",
      "  Hispanic               9.0%\n",
      "  Other                  7.7%\n",
      "  → Medicaid encodes low income, which is racially stratified.\n",
      "    Hispanic: 9.0%, AfricanAmerican: 5.5%, Caucasian: 2.7%\n",
      "\n",
      "SNF (skilled nursing) discharge rate by race:\n",
      "  AfricanAmerican        10.7%\n",
      "  Asian                  14.2%\n",
      "  Caucasian              17.3%\n",
      "  Hispanic               9.6%\n",
      "  Other                  12.6%\n",
      "  → SNF access requires insurance and nearby facility.\n",
      "    Caucasian: 17.3% vs AfricanAmerican: 10.7%.\n",
      "    Lower SNF access → higher home readmission risk - encoding\n",
      "    structural inequality as individual clinical risk.\n",
      "\n",
      "Mean prior inpatient visits by race:\n",
      "  AfricanAmerican        0.702\n",
      "  Asian                  0.482\n",
      "  Caucasian              0.634\n",
      "  Hispanic               0.611\n",
      "  Other                  0.454\n",
      "  → AfricanAmerican patients average 0.70 prior visits vs\n",
      "    0.48 for Asian patients. Gap reflects differential access\n",
      "    to preventive care, not higher inherent clinical risk.\n"
     ]
    }
   ],
   "source": [
    "# payer_code x race - Medicaid rate\n",
    "print('Medicaid payer rate by race:')\n",
    "df['is_medicaid'] = (df['payer_code'] == 'MD').astype(int)\n",
    "medicaid_race = df.groupby('race')['is_medicaid'].mean().round(3)\n",
    "for r, v in medicaid_race.items():\n",
    "    print(f'  {r:<22} {v:.1%}')\n",
    "print('  → Medicaid encodes low income, which is racially stratified.')\n",
    "print('    Hispanic: 9.0%, AfricanAmerican: 5.5%, Caucasian: 2.7%')\n",
    "\n",
    "# discharge_disposition_id x race - SNF access\n",
    "print('\\nSNF (skilled nursing) discharge rate by race:')\n",
    "df['discharged_to_snf'] = df['discharge_disposition_id'].isin([2, 3]).astype(int)\n",
    "snf_race = df.groupby('race')['discharged_to_snf'].mean().round(3)\n",
    "for r, v in snf_race.items():\n",
    "    print(f'  {r:<22} {v:.1%}')\n",
    "print('  → SNF access requires insurance and nearby facility.')\n",
    "print('    Caucasian: 17.3% vs AfricanAmerican: 10.7%.')\n",
    "print('    Lower SNF access → higher home readmission risk - encoding')\n",
    "print('    structural inequality as individual clinical risk.')\n",
    "\n",
    "# number_inpatient x race - prior hospitalisation gap\n",
    "print('\\nMean prior inpatient visits by race:')\n",
    "prior_in = df.groupby('race')['number_inpatient'].mean().round(3)\n",
    "for r, v in prior_in.items():\n",
    "    print(f'  {r:<22} {v:.3f}')\n",
    "print('  → AfricanAmerican patients average 0.70 prior visits vs')\n",
    "print('    0.48 for Asian patients. Gap reflects differential access')\n",
    "print('    to preventive care, not higher inherent clinical risk.')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "31b4f354",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-09-24T03:35:00.477444Z",
     "iopub.status.busy": "2026-09-24T03:35:00.477378Z",
     "iopub.status.idle": "2026-09-24T03:35:00.669585Z",
     "shell.execute_reply": "2026-09-24T03:35:00.669143Z"
    }
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1440x480 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig, axes = plt.subplots(1, 2, figsize=(12, 4))\n",
    "fig.suptitle('Proxy variable analysis - what the model learns without being told', color=ACCENT, fontsize=12, y=1.02)\n",
    "\n",
    "# Medicaid rate by race\n",
    "med_plot = df.groupby('race')['is_medicaid'].mean().sort_values() * 100\n",
    "bar_colors_m = [DANGER if r not in ['Caucasian', 'Asian'] else MUTED for r in med_plot.index]\n",
    "axes[0].barh(med_plot.index, med_plot.values, color=bar_colors_m, alpha=0.85)\n",
    "axes[0].set_xlabel('% on Medicaid')\n",
    "axes[0].set_title('Medicaid rate by race - payer_code is a race proxy', color=MUTED, fontsize=10)\n",
    "axes[0].grid(axis='x', alpha=0.3)\n",
    "\n",
    "# SNF discharge rate by race\n",
    "snf_plot = df.groupby('race')['discharged_to_snf'].mean().sort_values() * 100\n",
    "bar_colors_s = [DANGER if r not in ['Caucasian', 'Asian'] else MUTED for r in snf_plot.index]\n",
    "axes[1].barh(snf_plot.index, snf_plot.values, color=bar_colors_s, alpha=0.85)\n",
    "axes[1].set_xlabel('% discharged to SNF')\n",
    "axes[1].set_title('SNF discharge rate by race - discharge_disposition is a race proxy', color=MUTED, fontsize=10)\n",
    "axes[1].grid(axis='x', alpha=0.3)\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "bc9e4d89",
   "metadata": {},
   "source": [
    "## 4. Train the Biased Model\n",
    "\n",
    "Features include `race`, `gender`, and `age` directly **and** all four proxy variables."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "13682e05",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-09-24T03:35:00.671378Z",
     "iopub.status.busy": "2026-09-24T03:35:00.671268Z",
     "iopub.status.idle": "2026-09-24T03:35:00.843218Z",
     "shell.execute_reply": "2026-09-24T03:35:00.842796Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Categorical columns encoded.\n"
     ]
    }
   ],
   "source": [
    "# Encode categoricals\n",
    "cat_cols = [\n",
    "    'race', 'gender', 'age', 'payer_code', 'medical_specialty',\n",
    "    'diag_1', 'diag_2', 'diag_3', 'max_glu_serum', 'A1Cresult',\n",
    "    'metformin', 'insulin', 'change', 'diabetesMed'\n",
    "]\n",
    "df_enc = df.copy()\n",
    "le = LabelEncoder()\n",
    "for col in cat_cols:\n",
    "    df_enc[col] = le.fit_transform(df_enc[col].astype(str))\n",
    "\n",
    "print('Categorical columns encoded.')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "195e0026",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-09-24T03:35:00.844620Z",
     "iopub.status.busy": "2026-09-24T03:35:00.844551Z",
     "iopub.status.idle": "2026-09-24T03:35:08.996558Z",
     "shell.execute_reply": "2026-09-24T03:35:08.995786Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Model Accuracy: 88.79%\n",
      "\n",
      " - High-Risk Flag Rate by Gender -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  - \n",
      "  Male patients      : 0.22% flagged high-risk\n",
      "  Female patients    : 0.24% flagged high-risk\n",
      "\n",
      "  Fairness Gap (Gender): 0.02%\n",
      "\n",
      " - High-Risk Flag Rate by Race -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  - \n",
      "  Caucasian/Asian    : 0.25% flagged high-risk\n",
      "  Other minorities   : 0.17% flagged high-risk\n",
      "\n",
      "  Fairness Gap (Race): 0.08%\n",
      "\n",
      " - High-Risk Flag Rate by Age -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  - \n",
      "  Under 70           : 0.36% flagged high-risk\n",
      "  70+ (elderly)      : 0.08% flagged high-risk\n",
      "\n",
      "  Fairness Gap (Age): 0.28%\n"
     ]
    }
   ],
   "source": [
    "biased_features = [\n",
    "    'race',                      # protected attribute ✗\n",
    "    'gender',                    # protected attribute ✗\n",
    "    'age',                       # protected attribute ✗\n",
    "    'payer_code',                # proxy: encodes income + race ✗\n",
    "    'discharge_disposition_id',  # proxy: encodes insurance/wealth ✗\n",
    "    'medical_specialty',         # proxy: encodes insurance access ✗\n",
    "    'number_inpatient',          # proxy: encodes preventive care access ✗\n",
    "    'admission_type_id',\n",
    "    'admission_source_id',\n",
    "    'time_in_hospital',\n",
    "    'num_lab_procedures',\n",
    "    'num_procedures',\n",
    "    'num_medications',\n",
    "    'number_outpatient',\n",
    "    'number_emergency',\n",
    "    'number_diagnoses',\n",
    "    'max_glu_serum',\n",
    "    'A1Cresult',\n",
    "    'insulin',\n",
    "    'change',\n",
    "    'diabetesMed',\n",
    "    'diag_1',\n",
    "    'diag_2',\n",
    "    'diag_3',\n",
    "]\n",
    "\n",
    "X_biased = df_enc[biased_features]\n",
    "y = df_enc['target']\n",
    "\n",
    "X_train, X_test, y_train, y_test = train_test_split(\n",
    "    X_biased, y, test_size=0.2, random_state=42\n",
    ")\n",
    "\n",
    "biased_model = RandomForestClassifier(n_estimators=100, random_state=42)\n",
    "biased_model.fit(X_train, y_train)\n",
    "biased_preds    = biased_model.predict(X_test)\n",
    "biased_accuracy = accuracy_score(y_test, biased_preds)\n",
    "\n",
    "results_b = X_test.copy()\n",
    "results_b['pred']        = biased_preds\n",
    "results_b['is_female']   = df.loc[X_test.index, 'is_female'].values\n",
    "results_b['is_minority'] = df.loc[X_test.index, 'is_minority'].values\n",
    "results_b['is_elderly']  = df.loc[X_test.index, 'is_elderly'].values\n",
    "\n",
    "sex_b  = results_b.groupby('is_female')['pred'].mean() * 100\n",
    "race_b = results_b.groupby('is_minority')['pred'].mean() * 100\n",
    "age_b  = results_b.groupby('is_elderly')['pred'].mean() * 100\n",
    "\n",
    "print(f'Model Accuracy: {biased_accuracy:.2%}')\n",
    "print()\n",
    "print(' - High-Risk Flag Rate by Gender -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  - ')\n",
    "print(f'  Male patients      : {sex_b[0]:.2f}% flagged high-risk')\n",
    "print(f'  Female patients    : {sex_b[1]:.2f}% flagged high-risk')\n",
    "sex_gap_b = abs(sex_b[0] - sex_b[1])\n",
    "print(f'\\n  Fairness Gap (Gender): {sex_gap_b:.2f}%')\n",
    "print()\n",
    "print(' - High-Risk Flag Rate by Race -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  - ')\n",
    "print(f'  Caucasian/Asian    : {race_b[0]:.2f}% flagged high-risk')\n",
    "print(f'  Other minorities   : {race_b[1]:.2f}% flagged high-risk')\n",
    "race_gap_b = abs(race_b[0] - race_b[1])\n",
    "print(f'\\n  Fairness Gap (Race): {race_gap_b:.2f}%')\n",
    "print()\n",
    "print(' - High-Risk Flag Rate by Age -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  - ')\n",
    "print(f'  Under 70           : {age_b[0]:.2f}% flagged high-risk')\n",
    "print(f'  70+ (elderly)      : {age_b[1]:.2f}% flagged high-risk')\n",
    "age_gap_b = abs(age_b[0] - age_b[1])\n",
    "print(f'\\n  Fairness Gap (Age): {age_gap_b:.2f}%')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "db9530e6",
   "metadata": {},
   "source": [
    "## 5. Train the Fair Model\n",
    "\n",
    "All three protected attributes **and** all four proxy variables are removed. Only objective clinical signals from the current admission remain."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "6fb410b8",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-09-24T03:35:08.999955Z",
     "iopub.status.busy": "2026-09-24T03:35:08.999851Z",
     "iopub.status.idle": "2026-09-24T03:35:17.687975Z",
     "shell.execute_reply": "2026-09-24T03:35:17.686481Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Model Accuracy: 88.74%\n",
      "\n",
      " - High-Risk Flag Rate by Gender -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  - \n",
      "  Male patients      : 0.11% flagged high-risk\n",
      "  Female patients    : 0.06% flagged high-risk\n",
      "\n",
      "  New Fairness Gap (Gender): 0.04%\n",
      "\n",
      " - High-Risk Flag Rate by Race -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  - \n",
      "  Caucasian/Asian    : 0.10% flagged high-risk\n",
      "  Other minorities   : 0.04% flagged high-risk\n",
      "\n",
      "  New Fairness Gap (Race): 0.06%\n",
      "\n",
      " - High-Risk Flag Rate by Age -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  - \n",
      "  Under 70           : 0.13% flagged high-risk\n",
      "  70+ (elderly)      : 0.03% flagged high-risk\n",
      "\n",
      "  New Fairness Gap (Age): 0.09%\n"
     ]
    }
   ],
   "source": [
    "fair_features = [\n",
    "    # race                    removed (protected attribute)\n",
    "    # gender                  removed (protected attribute)\n",
    "    # age                     removed (protected attribute)\n",
    "    # payer_code              removed (proxy: encodes income + race)\n",
    "    # discharge_disposition_id removed (proxy: encodes post-acute access)\n",
    "    # medical_specialty       removed (proxy: encodes insurance/geography)\n",
    "    # number_inpatient        removed (proxy: encodes preventive care access gap)\n",
    "    'admission_type_id',       # retained: emergency vs elective admission\n",
    "    'admission_source_id',     # retained: ER vs referral vs transfer\n",
    "    'time_in_hospital',        # retained: length of stay - severity proxy\n",
    "    'num_lab_procedures',      # retained: diagnostic intensity this visit\n",
    "    'num_procedures',          # retained: clinical procedures this visit\n",
    "    'num_medications',         # retained: medication burden this visit\n",
    "    'number_outpatient',       # retained: outpatient visits\n",
    "    'number_emergency',        # retained: emergency visits (acute events)\n",
    "    'number_diagnoses',        # retained: comorbidity count\n",
    "    'max_glu_serum',           # retained: glucose reading this admission\n",
    "    'A1Cresult',               # retained: HbA1c - direct diabetes control measure\n",
    "    'insulin',                 # retained: treatment decision this visit\n",
    "    'change',                  # retained: medication change flag\n",
    "    'diabetesMed',             # retained: on diabetes medication flag\n",
    "    'diag_1',                  # retained: primary ICD diagnosis code\n",
    "    'diag_2',                  # retained: secondary ICD diagnosis code\n",
    "    'diag_3',                  # retained: tertiary ICD diagnosis code\n",
    "]\n",
    "\n",
    "# Encode only the retained categorical columns for fair model\n",
    "cat_cols_fair = [\n",
    "    'diag_1', 'diag_2', 'diag_3',\n",
    "    'max_glu_serum', 'A1Cresult',\n",
    "    'insulin', 'change', 'diabetesMed'\n",
    "]\n",
    "df_enc_fair = df.copy()\n",
    "le2 = LabelEncoder()\n",
    "for col in cat_cols_fair:\n",
    "    df_enc_fair[col] = le2.fit_transform(df_enc_fair[col].astype(str))\n",
    "\n",
    "X_fair = df_enc_fair[fair_features]\n",
    "\n",
    "X_train_f, X_test_f, y_train_f, y_test_f = train_test_split(\n",
    "    X_fair, y, test_size=0.2, random_state=42\n",
    ")\n",
    "\n",
    "fair_model = RandomForestClassifier(n_estimators=100, random_state=42)\n",
    "fair_model.fit(X_train_f, y_train_f)\n",
    "fair_preds    = fair_model.predict(X_test_f)\n",
    "fair_accuracy = accuracy_score(y_test_f, fair_preds)\n",
    "\n",
    "results_f = X_test_f.copy()\n",
    "results_f['pred']        = fair_preds\n",
    "results_f['is_female']   = df.loc[X_test_f.index, 'is_female'].values\n",
    "results_f['is_minority'] = df.loc[X_test_f.index, 'is_minority'].values\n",
    "results_f['is_elderly']  = df.loc[X_test_f.index, 'is_elderly'].values\n",
    "\n",
    "sex_f  = results_f.groupby('is_female')['pred'].mean() * 100\n",
    "race_f = results_f.groupby('is_minority')['pred'].mean() * 100\n",
    "age_f  = results_f.groupby('is_elderly')['pred'].mean() * 100\n",
    "\n",
    "print(f'Model Accuracy: {fair_accuracy:.2%}')\n",
    "print()\n",
    "print(' - High-Risk Flag Rate by Gender -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  - ')\n",
    "print(f'  Male patients      : {sex_f[0]:.2f}% flagged high-risk')\n",
    "print(f'  Female patients    : {sex_f[1]:.2f}% flagged high-risk')\n",
    "sex_gap_f = abs(sex_f[0] - sex_f[1])\n",
    "print(f'\\n  New Fairness Gap (Gender): {sex_gap_f:.2f}%')\n",
    "print()\n",
    "print(' - High-Risk Flag Rate by Race -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  - ')\n",
    "print(f'  Caucasian/Asian    : {race_f[0]:.2f}% flagged high-risk')\n",
    "print(f'  Other minorities   : {race_f[1]:.2f}% flagged high-risk')\n",
    "race_gap_f = abs(race_f[0] - race_f[1])\n",
    "print(f'\\n  New Fairness Gap (Race): {race_gap_f:.2f}%')\n",
    "print()\n",
    "print(' - High-Risk Flag Rate by Age -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  -  - ')\n",
    "print(f'  Under 70           : {age_f[0]:.2f}% flagged high-risk')\n",
    "print(f'  70+ (elderly)      : {age_f[1]:.2f}% flagged high-risk')\n",
    "age_gap_f = abs(age_f[0] - age_f[1])\n",
    "print(f'\\n  New Fairness Gap (Age): {age_gap_f:.2f}%')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1468176f",
   "metadata": {},
   "source": [
    "## 6. Compare Results"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "048ae6ac",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-09-24T03:35:17.699767Z",
     "iopub.status.busy": "2026-09-24T03:35:17.699646Z",
     "iopub.status.idle": "2026-09-24T03:35:17.903200Z",
     "shell.execute_reply": "2026-09-24T03:35:17.902691Z"
    }
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1800x480 with 3 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "Summary\n",
      "-------\n",
      "Gender gap  before: 0.02%   after: 0.04%   +100.0% increase\n",
      "Race gap    before: 0.08%   after: 0.06%   28.2% reduction\n",
      "Age gap     before: 0.28%   after: 0.09%   66.0% reduction\n",
      "\n",
      "Note: gender gap increased slightly after proxy removal.\n",
      "Proxy variables did not carry strong gender signal - their\n",
      "removal shifted prediction patterns in a way that widened\n",
      "the gender gap by ~0.02pp. Race and age gaps reduced substantially.\n"
     ]
    }
   ],
   "source": [
    "# Recompute gaps using the actual scalar values from each model's results\n",
    "gap_sex_b  = abs(sex_b[0]  - sex_b[1])\n",
    "gap_sex_f  = abs(sex_f[0]  - sex_f[1])\n",
    "gap_race_b = abs(race_b[0] - race_b[1])\n",
    "gap_race_f = abs(race_f[0] - race_f[1])\n",
    "gap_age_b  = abs(age_b[0]  - age_b[1])\n",
    "gap_age_f  = abs(age_f[0]  - age_f[1])\n",
    "\n",
    "# Gender gap increased - show direction correctly\n",
    "def gap_change(before, after):\n",
    "    if before == 0:\n",
    "        return 'N/A'\n",
    "    pct = (after - before) / before * 100\n",
    "    if pct < 0:\n",
    "        return f'{abs(pct):.1f}% reduction'\n",
    "    else:\n",
    "        return f'+{pct:.1f}% increase'\n",
    "\n",
    "fig, axes = plt.subplots(1, 3, figsize=(15, 4))\n",
    "fig.suptitle('Healthcare Readmission - Biased vs Mitigated Model', color=ACCENT, fontsize=13, y=1.02)\n",
    "\n",
    "dims = [\n",
    "    (axes[0], [sex_b[0],  sex_b[1]],  [sex_f[0],  sex_f[1]],\n",
    "     ['Male', 'Female'],               gap_sex_b,  gap_sex_f,  'Gender'),\n",
    "    (axes[1], [race_b[0], race_b[1]], [race_f[0], race_f[1]],\n",
    "     ['Caucasian/Asian', 'Minorities'], gap_race_b, gap_race_f, 'Race'),\n",
    "    (axes[2], [age_b[0],  age_b[1]],  [age_f[0],  age_f[1]],\n",
    "     ['Under 70', '70+ elderly'],      gap_age_b,  gap_age_f,  'Age'),\n",
    "]\n",
    "\n",
    "for ax, vals_b, vals_f, groups, gb, gf, label in dims:\n",
    "    x = np.arange(len(groups))\n",
    "    width = 0.35\n",
    "    bars_b = ax.bar(x - width/2, vals_b, width, color=DANGER, label='Biased',    alpha=0.85)\n",
    "    bars_f = ax.bar(x + width/2, vals_f, width, color=SAFE,   label='Mitigated', alpha=0.85)\n",
    "    for bar, val in list(zip(bars_b, vals_b)) + list(zip(bars_f, vals_f)):\n",
    "        ax.text(bar.get_x() + bar.get_width()/2, val + 0.005,\n",
    "                f'{val:.2f}%', ha='center', fontsize=9, color=ACCENT)\n",
    "    ax.set_xticks(x)\n",
    "    ax.set_xticklabels(groups, fontsize=9)\n",
    "    ax.set_ylim(0, max(max(vals_b), max(vals_f)) * 1.4)\n",
    "    ax.set_ylabel('% flagged high-risk')\n",
    "    ax.set_title(f'{label}: {gb:.2f}% → {gf:.2f}%', color=MUTED, fontsize=10)\n",
    "    ax.legend(fontsize=8)\n",
    "    ax.grid(axis='y', alpha=0.3)\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.show()\n",
    "\n",
    "print(f'\\nSummary')\n",
    "print(f'-------')\n",
    "print(f'Gender gap  before: {gap_sex_b:.2f}%   after: {gap_sex_f:.2f}%   {gap_change(gap_sex_b, gap_sex_f)}')\n",
    "print(f'Race gap    before: {gap_race_b:.2f}%   after: {gap_race_f:.2f}%   {gap_change(gap_race_b, gap_race_f)}')\n",
    "print(f'Age gap     before: {gap_age_b:.2f}%   after: {gap_age_f:.2f}%   {gap_change(gap_age_b, gap_age_f)}')\n",
    "print()\n",
    "print('Note: gender gap increased slightly after proxy removal.')\n",
    "print('Proxy variables did not carry strong gender signal - their')\n",
    "print('removal shifted prediction patterns in a way that widened')\n",
    "print('the gender gap by ~0.02pp. Race and age gaps reduced substantially.')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9be9912d",
   "metadata": {},
   "source": [
    "## Key Insight\n",
    "\n",
    "Removing `race`, `gender`, and `age` alone is not enough. Four proxy variables reconstruct protected-class signal even after the demographic columns are gone.\n",
    "\n",
    "`payer_code` is the most structurally loaded: Medicaid status encodes poverty, and poverty is racially stratified by decades of structural inequality in employment and insurance access. `discharge_disposition_id` encodes whether a patient can access a skilled nursing facility - a function of insurance coverage and geographic proximity, not clinical trajectory. Where a patient goes after discharge depends on what their insurer will cover and whether there is a facility nearby: a model that learns \"this patient goes home → higher readmission risk\" is encoding a resource gap as a patient-level risk factor. `medical_specialty` access is determined upstream by insurance and geography. And `number_inpatient` carries racial signal because AfricanAmerican patients average 0.70 prior hospitalisations vs 0.48 for Asian patients - a gap that reflects underinvestment in preventive care in minority communities, not higher individual clinical risk.\n",
    "\n",
    "One result is honest and worth noting: the gender gap increased slightly (from 0.02% to 0.04%) after proxy removal. The proxy variables removed did not carry significant gender signal - their removal shifted the model's prediction landscape in a way that slightly widened the male/female gap. This is a real outcome of this specific mitigation, not an artefact. Race and age gaps reduced substantially: 28% and 66% respectively.\n",
    "\n",
    "**The fix:** Drop everything that encodes structural inequality as individual risk. Retain only the clinical record of this admission - diagnosis codes, lab and procedure counts, glucose control, medication management, and how the patient arrived. These are the signals a clinician would use to assess readmission risk without reference to who the patient is demographically.\n",
    "\n",
    "---\n",
    "\n",
    "*Part of the [Fair Code project](https://github.com/yakew7/Fair-Code) by [@thefaircodeproject](https://instagram.com/thefaircodeproject)*"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.13.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}