Personalized Tuberculosis Treatment Recommendation System (PTTRS) version 1: A Precision-Medicine Based Application for Recommending Personalized Treatment to Tuberculosis Patients
ANURAG ANAND, A.; Kumar Mondal, R.; Sarkar, B.; Samanta, S. K.
Show abstract
Tuberculosis is one of the leading causes of death in underdeveloped and developing countries. The limited access to detailed drug susceptibility testing, lack of knowledge of second-line anti-TB drugs in underdeveloped nations, insufficient adherence to drug dosages, and comorbidities challenge the management of drug-resistant TB. Further, the number of deaths due to TB is increasing with time due to reasons such as high levels of resistance mutation in TB strains, lack of on-time delivery of treatment, and lack of personalized medicine. Thus, we have developed a web-based application for aiding in the personalized treatment of TB patients based on their medical condition. The application takes geographical location, age, sex, medical and travel history, AMR report and associated medical conditions (AMCs) of the patient as input, and thereafter, outputs the list of drugs which are safe for the patient. The application also helps in knowing the possible side-effects of various drug combinations administered for TB. Additionally, the application also outputs the side-effects of combination of drugs for TB and for any AMC that the patient is suffering with. PTTRS can be accessed at https://pttrs-bblserver.streamlit.app/. Our polypharmacy side effect predictor can be used for any other disease as well. It can be accessed at https://psep-bblserver.streamlit.app/.
Matching journals
The top 10 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Combining Multi-Dimensional Molecular Fingerprints to Predict hERG Cardiotoxicity of Compounds 95%
- MACI: A machine learning-based approach to identify drug classes of antibiotic resistance genes from metagenomic data 95%
- Predicting the physiological effects of multiple drugs using electronic health record 95%
Similar papers in this journal
- Evaluating Knowledge Fusion Models on Detecting Adverse Drug Events in Text 92%
- Inferring Gender from First Names: Comparing the Accuracy of Genderize, Gender API, and the gender R Package on Authors of Diverse Nationality 91%
- Identification of predictive patient characteristics for assessing the probability of COVID-19 in-hospital mortality 91%
Similar papers in this journal
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.