Machine Learning Clinical Syndrome Classifier
Summary
Freelancer Client is hiring: Machine Learning Clinical Syndrome Classifier.
Location: Remote
I have a collection of patient cases and my goal is to train a machine-learning model that can reliably assign each case to the appropriate clinical syndrome category. A purely machine learning approach is required rather than rule-based logic; I’m open to the algorithm that best fits the data once we explore its size, balance, and feature types.
I will provide the raw data and domain guidance around the syndrome labels. You will handle data preparation, model development, evaluation, and a concise write-up of the methodology so it can be reproduced or audited later. Python with scikit-learn, TensorFlow, or PyTorch is perfectly acceptable as long as the code is clean and well documented.
Cleaned and pre-processed dataset (with scripts)
Training notebook or script with reproducible random seeds
Trained model file(s) ready for inference
Skills: Python, Software Architecture, Machine Learning (ML), Data Mining, Statistical Analysis, Data Visualization, Data Analysis, Deep Learning
Budget: $15–$25 USD
Source: Freelancer Client via Remote / Online. Apply on the source website.
Original
I have a collection of patient cases and my goal is to train a machine-learning model that can reliably assign each case to the appropriate clinical syndrome category. A purely machine learning approach is required rather than rule-based logic; I’m open to the algorithm that best fits the data once we explore its size, balance, and feature types.
I will provide the raw data and domain guidance around the syndrome labels. You will handle data preparation, model development, evaluation, and a concise write-up of the methodology so it can be reproduced or audited later. Python with scikit-learn, TensorFlow, or PyTorch is perfectly acceptable as long as the code is clean and well documented.
Deliverables:
• Cleaned and pre-processed dataset (with scripts)
• Training notebook or script with reproducible random seeds
• Trained model file(s) ready for inference
• Evaluation report outlining metrics, confusion matrix, and any feature importance/interpretability methods applied
• Short deployment guide (CLI or simple API)
Acceptance criteria: model reaches an agreed-upon accuracy/F1 on a held-out test set and code runs end-to-end on my machine.
Once you review the data we can finalise the exact targets and timeline—looking forward to collaborating on this.
Location & Details
Apply on source →About this listing
This remote opportunity was imported from Freelancer and is shown here for discovery. To apply, follow the link to the original posting.