You will get Offline Reinforcement Learning for Clinical Decision Modelling (EHR)
Rising Talent
Rising Talent
Project details
I develop research-grade Offline Reinforcement Learning (ORL) solutions for clinical and sequential decision modeling. This project implements Dueling Double DQN (Duel DDQN) tailored for structured EHR or time-series datasets, with a strong emphasis on measurable performance and reproducibility.
Each pipeline includes structured preprocessing, reward design, action-space formulation, model training, and offline policy evaluation (e.g., importance sampling or FQE when required). Deliverables include performance metrics such as cumulative reward trends, Q-value stability, policy comparison results, and 4–10 analytical visualizations depending on the selected tier.
My background in biomedical engineering and applied machine learning enables me to bridge domain knowledge with rigorous modeling practices, ensuring that results are not only technically sound but also clinically interpretable.
This service is suited for research studies, academic work, healthcare analytics prototypes, and decision optimization systems.
All implementations are intended for research and modeling purposes only.
Each pipeline includes structured preprocessing, reward design, action-space formulation, model training, and offline policy evaluation (e.g., importance sampling or FQE when required). Deliverables include performance metrics such as cumulative reward trends, Q-value stability, policy comparison results, and 4–10 analytical visualizations depending on the selected tier.
My background in biomedical engineering and applied machine learning enables me to bridge domain knowledge with rigorous modeling practices, ensuring that results are not only technically sound but also clinically interpretable.
This service is suited for research studies, academic work, healthcare analytics prototypes, and decision optimization systems.
All implementations are intended for research and modeling purposes only.
Machine Learning Tools
Google Sheets, NumPy, pandas, Python, Python Scikit-Learn, PyTorch, scikit-learn, SciPyWhat's included
| Service Tiers |
Starter
$180
|
Standard
$420
|
Advanced
$950
|
|---|---|---|---|
| Delivery Time | 7 days | 14 days | 21 days |
Number of Revisions | 1 | 2 | 3 |
Number of Model Variations | 1 | 2 | 3 |
Number of Scenarios | 1 | 2 | 3 |
Number of Graphs/Charts | 4 | 7 | 9 |
Model Validation/Testing | |||
Model Documentation | - | ||
Data Source Connectivity | - | - | |
Source Code |
Optional add-ons
You can add these on the next page.
Fast Delivery
+$65 - $200
Additional Model Variation
(+ 3 Days)
+$100
Additional Scenario
(+ 1 Day)
+$75About Fatima Hasya
Computer Vision | Medical Imaging | AI Engineering | ML & DL Pipelines
Surabaya, Indonesia - 9:19 am local time
With 3+ years of experience leading technical and organizational projects, I combine analytical rigor with practical system development to deliver reliable AI solutions aligned with real-world needs.
Steps for completing your project
After purchasing the project, send requirements so Fatima Hasya can start the project.
Delivery time starts when Fatima Hasya receives requirements from you.
Fatima Hasya works on your project following the steps below.
Revisions may occur after the delivery date.
Project Scoping & Data Review
Review dataset structure, feature definitions, action space, and reward objective. Confirm modeling scope, evaluation criteria, and expected deliverables.
Data Preprocessing & Environment Setup
Clean and structure data, define state-action representation, and configure the offline RL environment for training and evaluation.