fhir-reada 0.1.0__tar.gz

fhir_reada-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 Tobenna Oduah
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights  
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell  
+copies of the Software, and to permit persons to whom the Software is  
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all  
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR  
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,  
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE  
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER  
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,  
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE  
+SOFTWARE.

fhir_reada-0.1.0/PKG-INFO

@@ -0,0 +1,9 @@
+Metadata-Version: 2.1
+Name: fhir-reada
+Version: 0.1.0
+Summary: A FHIR cohort extractor and de-identification tool for clinical research.
+Author-email: Tobenna Oduah <tjlite81@gmail.com>
+License: MIT
+License-File: LICENSE
+Requires-Dist: requests
+Requires-Dist: python-dateutil

fhir_reada-0.1.0/README.md

@@ -0,0 +1,75 @@
+# FHIR-READA
+
+**FHIR Research Extractor And De-identified Analyzer**
+
+A Python CLI tool for extracting, de-identifying, and exporting patient data from FHIR servers — built for research teams, clinicians, and medical institutions.
+
+---
+
+## 🔍 Features
+
+- Filter patients by age range and diagnosis  
+- Extract from any FHIR-compliant server  
+- Fetch Conditions and Observations  
+- Automatically de-identify patient IDs  
+- Export results to CSV  
+- Easy-to-use CLI with flexible filters
+
+---
+
+## 💻 Installation
+
+**From PyPI**
+
+```bash
+pip install fhir-reada
+```
+
+**From Source (for development or testing)**
+
+```bash
+git clone https://github.com/TOduah/fhir-reada.git
+cd fhir-reada
+pip install -e .
+```
+
+---
+
+## 🚀 Usage (CLI)
+
+```bash
+fhir-reada --url https://hapi.fhir.org/baseR4 --min-age 25 --max-age 40 --diagnosis diabetes --out output.csv
+```
+
+---
+
+## ⚙️ CLI Options
+
+| Option         | Description                                          |
+|----------------|------------------------------------------------------|
+| `--url`        | FHIR base URL (e.g. `https://hapi.fhir.org/baseR4`) |
+| `--min-age`    | Minimum age for cohort (e.g. `25`)                  |
+| `--max-age`    | Maximum age for cohort (e.g. `40`)                  |
+| `--diagnosis`  | Diagnosis keyword (optional, e.g. `diabetes`)       |
+| `--out`        | Output filename for CSV export                      |
+
+---
+
+## 🏥 Who Is This For?
+
+- Research institutions running clinical studies  
+- Hospital data science or IT departments  
+- Medical schools teaching FHIR and analytics  
+- Independent developers working with public or private FHIR APIs
+
+---
+
+## 📄 License
+
+This project is licensed under the [MIT License](LICENSE).
+
+---
+
+## 💬 Author
+
+Built by [Tobenna Oduah](https://github.com/toduah).

fhir_reada-0.1.0/fhir_reada/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.1.0"

fhir_reada-0.1.0/fhir_reada/cli.py

@@ -0,0 +1,43 @@
+import argparse
+from fhir_reada.fhir_connector import FHIRClient
+from fhir_reada.cohort_builder import build_cohort
+from fhir_reada.deid_utils import deidentify_patient_bundle
+from fhir_reada.exporter import export_to_csv
+
+def run_cli(url, min_age, max_age, diagnosis, output_file):
+    client = FHIRClient(url)
+    age_range = (min_age, max_age)
+
+    print(f"Fetching patients aged {min_age}–{max_age} from {url}...")
+    patients = build_cohort(client, age_range)
+
+    bundles = []
+    for patient in patients:
+        pid = patient["id"]
+        conditions = client.get_conditions(pid)
+
+        if diagnosis and not any(diagnosis.lower() in c.lower() for c in conditions):
+            continue
+
+        observations = client.get_observations(pid)
+        bundles.append({
+            "patient": patient,
+            "conditions": conditions,
+            "observations": observations
+        })
+
+    print("De-identifying and exporting to CSV...")
+    deidentified = [deidentify_patient_bundle(b) for b in bundles]
+    export_to_csv(deidentified, filename=output_file)
+    print(f"Exported to {output_file}")
+
+def main():
+    parser = argparse.ArgumentParser(description="FHIR Cohort Extractor")
+    parser.add_argument("--url", required=True, help="FHIR base URL (e.g., https://hapi.fhir.org/baseR4)")
+    parser.add_argument("--min-age", type=int, default=3)
+    parser.add_argument("--max-age", type=int, default=90)
+    parser.add_argument("--diagnosis", help="Filter for specific condition keyword (e.g., diabetes)")
+    parser.add_argument("--out", required=True, help="Output CSV file")
+
+    args = parser.parse_args()
+    run_cli(args.url, args.min_age, args.max_age, args.diagnosis, args.out)

fhir_reada-0.1.0/fhir_reada/cohort_builder.py

@@ -0,0 +1,28 @@
+from datetime import date, timedelta
+
+def calculate_birthdate_range(age_range):
+    today = date.today()
+    oldest_birthdate = today - timedelta(days=age_range[1]*365.25)
+    youngest_birthdate = today - timedelta(days=age_range[0]*365.25)
+    return (oldest_birthdate.isoformat(), youngest_birthdate.isoformat())
+
+def extract_patient_info(entry):
+    resource = entry["resource"]
+    name = resource.get("name", [{}])[0]
+    return {
+        "id": resource.get("id"),
+        "name": " ".join(name.get("given", [])) + " " + name.get("family", ""),
+        "gender": resource.get("gender"),
+        "birthDate": resource.get("birthDate"),
+    }
+
+def build_cohort(client, age_range):
+    birthdate_range = calculate_birthdate_range(age_range)
+    entries = client.search_patients(birthdate_range)
+
+    patients = []
+    for entry in entries:
+        patient = extract_patient_info(entry)
+        patients.append(patient)
+
+    return patients

fhir_reada-0.1.0/fhir_reada/deid_utils.py

@@ -0,0 +1,17 @@
+from hashlib import sha256
+
+def deidentify_patient_bundle(bundle):
+    patient = bundle["patient"]
+    conditions = bundle["conditions"]
+    observations = bundle["observations"]
+
+    patient_id = patient.get("id", "")
+    pseudo_id = sha256(patient_id.encode()).hexdigest()[:10]
+
+    return {
+        "id": pseudo_id,
+        "gender": patient.get("gender"),
+        "birthDate": patient.get("birthDate"),
+        "conditions": "; ".join(conditions) if conditions else "None",
+        "observations": "; ".join(observations) if observations else "None"
+    }

fhir_reada-0.1.0/fhir_reada/exporter.py

@@ -0,0 +1,12 @@
+import csv
+
+def export_to_csv(patients, filename="cohort.csv"):
+    if not patients:
+        print("No data to export.")
+        return
+
+    keys = patients[0].keys()
+    with open(filename, "w", newline="", encoding="utf-8") as f:
+        writer = csv.DictWriter(f, fieldnames=keys)
+        writer.writeheader()
+        writer.writerows(patients)

fhir_reada-0.1.0/fhir_reada/fhir_connector.py

@@ -0,0 +1,34 @@
+import requests
+
+class FHIRClient:
+    def __init__(self, base_url):
+        self.base_url = base_url.rstrip('/')
+
+    def search_patients(self, birthdate_range=None):
+        params = {}
+        if birthdate_range:
+            params["birthdate"] = [f"ge{birthdate_range[0]}", f"le{birthdate_range[1]}"]
+        response = requests.get(f"{self.base_url}/Patient", params=params)
+        response.raise_for_status()
+        return response.json().get("entry", [])
+
+    def get_conditions(self, patient_id):
+        url = f"{self.base_url}/Condition?patient={patient_id}"
+        response = requests.get(url)
+        response.raise_for_status()
+        entries = response.json().get("entry", [])
+        return [entry["resource"].get("code", {}).get("text", "Unknown") for entry in entries]
+
+    def get_observations(self, patient_id):
+        url = f"{self.base_url}/Observation?patient={patient_id}"
+        response = requests.get(url)
+        response.raise_for_status()
+        entries = response.json().get("entry", [])
+        result = []
+        for entry in entries:
+            obs = entry["resource"]
+            code = obs.get("code", {}).get("text", "Unknown")
+            value = obs.get("valueQuantity", {}).get("value", "N/A")
+            unit = obs.get("valueQuantity", {}).get("unit", "")
+            result.append(f"{code}: {value} {unit}".strip())
+        return result

fhir_reada-0.1.0/fhir_reada.egg-info/PKG-INFO

@@ -0,0 +1,9 @@
+Metadata-Version: 2.1
+Name: fhir-reada
+Version: 0.1.0
+Summary: A FHIR cohort extractor and de-identification tool for clinical research.
+Author-email: Tobenna Oduah <tjlite81@gmail.com>
+License: MIT
+License-File: LICENSE
+Requires-Dist: requests
+Requires-Dist: python-dateutil

fhir_reada-0.1.0/fhir_reada.egg-info/SOURCES.txt

@@ -0,0 +1,15 @@
+LICENSE
+README.md
+pyproject.toml
+fhir_reada/__init__.py
+fhir_reada/cli.py
+fhir_reada/cohort_builder.py
+fhir_reada/deid_utils.py
+fhir_reada/exporter.py
+fhir_reada/fhir_connector.py
+fhir_reada.egg-info/PKG-INFO
+fhir_reada.egg-info/SOURCES.txt
+fhir_reada.egg-info/dependency_links.txt
+fhir_reada.egg-info/entry_points.txt
+fhir_reada.egg-info/requires.txt
+fhir_reada.egg-info/top_level.txt

fhir_reada-0.1.0/fhir_reada.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

fhir_reada-0.1.0/fhir_reada.egg-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+fhir-reada = fhir_reada.cli:main

fhir_reada-0.1.0/fhir_reada.egg-info/requires.txt

@@ -0,0 +1,2 @@
+requests
+python-dateutil

fhir_reada-0.1.0/fhir_reada.egg-info/top_level.txt

@@ -0,0 +1 @@
+fhir_reada

fhir_reada-0.1.0/pyproject.toml

@@ -0,0 +1,13 @@
+[project]
+name = "fhir-reada"
+version = "0.1.0"
+description = "A FHIR cohort extractor and de-identification tool for clinical research."
+authors = [{name = "Tobenna Oduah", email = "tjlite81@gmail.com"}]
+license = {text = "MIT"}
+dependencies = [
+    "requests",
+    "python-dateutil"
+]
+
+[project.scripts]
+fhir-reada = "fhir_reada.cli:main"

fhir_reada-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+