Bioinformatics Analyst
CurrentThe project I'm working on focuses on analyzing a clinical dataset from an American hospital where there are different cases and each case has two information: the patients' symptom descriptions and the corresponding ICD9 codes assigned by specialists. ICD codes (International Classification of Diseases) are standardized alphanumeric codes used worldwide to classify and code diagnosis, symptoms and medical procedures, facilitating healthcare reporting and analysis.The primary goal is to identify, through benchmarking, the most effective large language model among a selection of about fifty, for accurately predicting ICD9 codes based on symptom descriptions given as input.