bolade/bio-performx
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: Enhance context generation and report generation services with improved data handling and structure

Browse Source
This commit is contained in:
bolade
2025-10-04 10:25:10 +01:00
parent d66f3fd18b
commit 358898b7db
7 changed files with 163 additions and 48 deletions
Download Patch File Download Diff File Expand all files Collapse all files
app/services/context_generator.py
+142 -42
View File
@@ -6,7 +6,6 @@ of the medical report. It performs analysis on Pnoe, Spirometry, and SECA data.
"""
from datetime import datetime
from pathlib import Path
from typing import Dict, List, Optional, Tuple
import pandas as pd
@@ -35,28 +34,59 @@ class ContextGenerator:
def _preprocess_pnoe_data(self):
"""Apply preprocessing steps to Pnoe data"""
self.pnoe_df = self.pnoe_df.apply(pd.to_numeric, errors="ignore")
self.pnoe_df["VO2 Pulse"] = self.pnoe_df["VO2(ml/min)"] / self.pnoe_df["HR(bpm)"]
self.pnoe_df["VO2 Breath"] = self.pnoe_df["VO2(ml/min)"] / self.pnoe_df["BF(bpm)"]
self.pnoe_df["CHO"] = self.pnoe_df["EE(kcal/min)"] * self.pnoe_df["CARBS(%)"] / 100
self.pnoe_df["FAT"] = self.pnoe_df["EE(kcal/min)"] * self.pnoe_df["FAT(%)"] / 100
# Convert numeric columns
for col in self.pnoe_df.columns:
try:
self.pnoe_df[col] = pd.to_numeric(self.pnoe_df[col])
except (ValueError, TypeError):
pass
self.pnoe_df["VO2 Pulse"] = (
self.pnoe_df["VO2(ml/min)"] / self.pnoe_df["HR(bpm)"]
)
self.pnoe_df["VO2 Breath"] = (
self.pnoe_df["VO2(ml/min)"] / self.pnoe_df["BF(bpm)"]
)
self.pnoe_df["CHO"] = (
self.pnoe_df["EE(kcal/min)"] * self.pnoe_df["CARBS(%)"] / 100
)
self.pnoe_df["FAT"] = (
self.pnoe_df["EE(kcal/min)"] * self.pnoe_df["FAT(%)"] / 100
)
window_size = 10
columns_to_smooth = ["VO2(ml/min)", "VCO2(ml/min)", "HR(bpm)", "VT(l)", "BF(bpm)", "VE(l/min)", "VO2 Pulse", "VO2 Breath", "CHO", "FAT"]
columns_to_smooth = [
"VO2(ml/min)",
"VCO2(ml/min)",
"HR(bpm)",
"VT(l)",
"BF(bpm)",
"VE(l/min)",
"VO2 Pulse",
"VO2 Breath",
"CHO",
"FAT",
]
for col in columns_to_smooth:
if col in self.pnoe_df.columns:
self.pnoe_df[f"{col}_smoothed"] = self.pnoe_df[col].rolling(window=window_size, min_periods=1).mean()
self.pnoe_df[f"{col}_smoothed"] = (
self.pnoe_df[col].rolling(window=window_size, min_periods=1).mean()
)
def extract_patient_info(self, patient_name: str) -> Dict:
"""Extract patient information from SECA dataset"""
if self.seca_df is not None:
patient_data = self.seca_df[self.seca_df["LastName"].str.contains(patient_name, case=False, na=False)]
patient_data = self.seca_df[
self.seca_df["LastName"].str.contains(
patient_name, case=False, na=False
)
]
if not patient_data.empty:
row = patient_data.iloc[0]
weight_kg = float(row.get("Weight", 0))
fat_pct = float(row.get("Adult_FMP", 0))
self.patient_info = {
"name": f"{row.get('FirstName', '')} {row.get('LastName', '')}",
"first_name": row.get("FirstName", ""),
@@ -75,9 +105,11 @@ class ContextGenerator:
"""Calculate spirometry-related metrics"""
metrics = {}
for param in ["FVC", "FEV1", "FEV1/FVC%"]:
row = self.spirometry_df.loc[self.spirometry_df["Parameters"].str.strip() == param]
row = self.spirometry_df.loc[
self.spirometry_df["Parameters"].str.strip() == param
]
if not row.empty:
param_key = param.lower().replace('/', '_').replace('%', '_pct')
param_key = param.lower().replace("/", "_").replace("%", "_pct")
metrics[f"{param_key}_best"] = row["Best"].values[0]
metrics[f"{param_key}_pred"] = row["%Pred."].values[0]
return metrics
@@ -87,21 +119,21 @@ class ContextGenerator:
metrics = {}
metrics["vo2_max"] = self.pnoe_df["VO2(ml/min)_smoothed"].max()
metrics["vo2_max_per_kg"] = metrics["vo2_max"] / self.patient_info["weight"]
peak_vt_idx = self.pnoe_df["VT(l)_smoothed"].idxmax()
peak_vt_row = self.pnoe_df.loc[peak_vt_idx]
metrics["peak_vt"] = peak_vt_row["VT(l)_smoothed"]
metrics["peak_vt_hr"] = peak_vt_row["HR(bpm)_smoothed"]
fat_max_idx = self.pnoe_df["FAT_smoothed"].idxmax()
fat_max_row = self.pnoe_df.loc[fat_max_idx]
metrics["fat_max_value"] = fat_max_row["FAT_smoothed"]
metrics["fat_max_hr"] = fat_max_row["HR(bpm)_smoothed"]
vt1, vt2 = self._detect_thresholds()
metrics["vt1"] = vt1
metrics["vt2"] = vt2
zones = self._calculate_hr_zones(vt1, vt2, fat_max_row)
metrics.update(zones)
return metrics
@@ -110,25 +142,35 @@ class ContextGenerator:
"""Detect VT1 and VT2 thresholds"""
condition = self.pnoe_df["CHO_smoothed"] > self.pnoe_df["FAT_smoothed"]
crossover_indices = condition[condition].index
vt1 = None
if len(crossover_indices) > 0:
vt1_idx = crossover_indices[0]
vt1_row = self.pnoe_df.loc[vt1_idx]
vt1 = {"HeartRate": vt1_row["HR(bpm)_smoothed"], "Speed": vt1_row["Speed"], "Time": vt1_row["T(sec)"]}
vt1 = {
"HeartRate": vt1_row["HR(bpm)_smoothed"],
"Speed": vt1_row["Speed"],
"Time": vt1_row["T(sec)"],
}
ve_slope = self.pnoe_df["VE(l/min)_smoothed"].diff()
second_derivative = ve_slope.diff()
vt2_idx = second_derivative.idxmax()
vt2 = None
if pd.notna(vt2_idx):
vt2_row = self.pnoe_df.loc[vt2_idx]
vt2 = {"HeartRate": vt2_row["HR(bpm)_smoothed"], "Speed": vt2_row["Speed"], "Time": vt2_row["T(sec)"]}
vt2 = {
"HeartRate": vt2_row["HR(bpm)_smoothed"],
"Speed": vt2_row["Speed"],
"Time": vt2_row["T(sec)"],
}
return vt1, vt2
def _calculate_hr_zones(self, vt1: Optional[Dict], vt2: Optional[Dict], fat_max_row: pd.Series) -> Dict:
def _calculate_hr_zones(
self, vt1: Optional[Dict], vt2: Optional[Dict], fat_max_row: pd.Series
) -> Dict:
"""Calculate heart rate zones based on thresholds"""
zones = {}
if vt1 and vt2:
@@ -137,7 +179,7 @@ class ContextGenerator:
zone_3_start = vt1["HeartRate"]
zone_4_start = vt2["HeartRate"] - 10
zone_5_start = vt2["HeartRate"] + 10
zones["zone1_bpm"] = f"{int(zone_1_start)}-{int(zone_2_start)}bpm"
zones["zone2_bpm"] = f"{int(zone_2_start)}-{int(vt1['HeartRate'])}bpm"
zones["zone3_bpm"] = f"{int(zone_3_start)}-{int(zone_4_start)}bpm"
@@ -152,29 +194,87 @@ class ContextGenerator:
zones["zone5_bpm"] = f"{int(max_hr * 0.95)}+bpm"
return zones
def generate_all_contexts(self, patient_name: str, graphs: Dict[str, str]) -> List[Dict]:
def generate_all_contexts(
self, patient_name: str, graphs: Dict[str, str]
) -> List[Dict]:
"""Main method to generate all page contexts"""
self.extract_patient_info(patient_name)
spirometry_metrics = self.calculate_spirometry_metrics()
pnoe_metrics = self.calculate_pnoe_metrics()
contexts = []
contexts.append({"name": self.patient_info["name"], "surname": self.patient_info["last_name"], "date": datetime.now().strftime("%B %d, %Y")})
contexts.append({"patient_name": self.patient_info["name"], "test_date": datetime.now().strftime("%B %d, %Y")})
contexts.append(
{
"name": self.patient_info["name"],
"surname": self.patient_info["last_name"],
"date": datetime.now().strftime("%B %d, %Y"),
}
)
contexts.append(
{
"patient_name": self.patient_info["name"],
"test_date": datetime.now().strftime("%B %d, %Y"),
}
)
for i in range(4):
contexts.append({"patient_name": self.patient_info["name"], "page_number": i + 3})
contexts.append(
{"patient_name": self.patient_info["name"], "page_number": i + 3}
)
fev1_percentage = 0
if spirometry_metrics.get("fvc_best"):
fev1_percentage = (pnoe_metrics["peak_vt"] / spirometry_metrics["fvc_best"]) * 100
contexts.append({"peak_vt": f"{pnoe_metrics['peak_vt']:.2f}", "peak_vt_bpm": f"{int(pnoe_metrics['peak_vt_hr'])}", "fev1_percentage": f"{fev1_percentage:.1f}", "lung_analysis_chart": graphs.get("spirometry_chart", ""), "respiratory_analysis_chart": graphs.get("respiratory", "")})
contexts.append({"vo2_max_value": f"{pnoe_metrics['vo2_max_per_kg']:.1f}", "age_range": f"{self.patient_info['age'] // 10 * 10}-{self.patient_info['age'] // 10 * 10 + 9}", "zone1_bpm": pnoe_metrics.get("zone1_bpm", ""), "zone2_bpm": pnoe_metrics.get("zone2_bpm", ""), "zone3_bpm": pnoe_metrics.get("zone3_bpm", ""), "zone4_bpm": pnoe_metrics.get("zone4_bpm", ""), "zone5_bpm": pnoe_metrics.get("zone5_bpm", ""), "vo2_pulse_chart": graphs.get("vo2_pulse", "")})
contexts.append({"fat_max_value": f"{pnoe_metrics['fat_max_value']:.2f}", "fat_max_hr": f"{int(pnoe_metrics['fat_max_hr'])}", "fuel_utilization_chart": graphs.get("fuel_utilization", ""), "fat_metabolism_chart": graphs.get("fat_metabolism", "")})
contexts.append({"fat_percentage": f"{self.patient_info['fat_percentage']:.1f}", "fat_mass_lbs": f"{self.patient_info['fat_mass_lbs']:.1f}", "lean_mass_lbs": f"{self.patient_info['lean_mass_lbs']:.1f}", "body_composition_chart": graphs.get("body_composition", ""), "body_fat_percent_chart": graphs.get("body_fat_percent", "")})
fev1_percentage = (
pnoe_metrics["peak_vt"] / spirometry_metrics["fvc_best"]
) * 100
contexts.append(
{
"peak_vt": f"{pnoe_metrics['peak_vt']:.2f}",
"peak_vt_bpm": f"{int(pnoe_metrics['peak_vt_hr'])}",
"fev1_percentage": f"{fev1_percentage:.1f}",
"lung_analysis_chart": graphs.get("spirometry_chart", ""),
"respiratory_analysis_chart": graphs.get("respiratory", ""),
}
)
contexts.append(
{
"vo2_max_value": f"{pnoe_metrics['vo2_max_per_kg']:.1f}",
"age_range": f"{self.patient_info['age'] // 10 * 10}-{self.patient_info['age'] // 10 * 10 + 9}",
"zone1_bpm": pnoe_metrics.get("zone1_bpm", ""),
"zone2_bpm": pnoe_metrics.get("zone2_bpm", ""),
"zone3_bpm": pnoe_metrics.get("zone3_bpm", ""),
"zone4_bpm": pnoe_metrics.get("zone4_bpm", ""),
"zone5_bpm": pnoe_metrics.get("zone5_bpm", ""),
"vo2_pulse_chart": graphs.get("vo2_pulse", ""),
}
)
contexts.append(
{
"fat_max_value": f"{pnoe_metrics['fat_max_value']:.2f}",
"fat_max_hr": f"{int(pnoe_metrics['fat_max_hr'])}",
"fuel_utilization_chart": graphs.get("fuel_utilization", ""),
"fat_metabolism_chart": graphs.get("fat_metabolism", ""),
}
)
contexts.append(
{
"fat_percentage": f"{self.patient_info['fat_percentage']:.1f}",
"fat_mass_lbs": f"{self.patient_info['fat_mass_lbs']:.1f}",
"lean_mass_lbs": f"{self.patient_info['lean_mass_lbs']:.1f}",
"body_composition_chart": graphs.get("body_composition", ""),
"body_fat_percent_chart": graphs.get("body_fat_percent", ""),
}
)
for i in range(9):
contexts.append({"patient_name": self.patient_info["name"], "page_number": i + 11, "vo2_breath_chart": graphs.get("vo2_breath", ""), "recovery_chart": graphs.get("recovery", "")})
contexts.append(
{
"patient_name": self.patient_info["name"],
"page_number": i + 11,
"vo2_breath_chart": graphs.get("vo2_breath", ""),
"recovery_chart": graphs.get("recovery", ""),
}
)
return contexts