Machine learning in medicine using JavaScript - building web apps using TensorFlow.js for interpreting biomedical datasets

Aug 4, 2026

Contributions to medicine can emerge from multiple domains, and this work targets the intersection of machine learning and web development. TensorFlow.js, a JavaScript-based library, is used to model biomedical datasets with neural networks trained on Kaggle data. The study presents TensorFlow.js capabilities for building advanced, web-based machine learning models. Three datasets are modeled: diabetes detection, surgery complications, and heart failure, achieving 92%, nearly 100%, and 80% accuracy, respectively.

LanguageEnglish

CategoryTechnology

FormatPDF

Pages18

Reading Time45 min

AccessFree to download

Introduction

Motivation from multiple domains in medicine

Why JavaScript and TensorFlow.js for medical ML

Advantages of browser-based data processing

Using Angular for a single-page application

Revista de Informtica Terica e Aplicada-RITA-ISSN 2175-2745 Vol. 31, Num. 1 (2024) 32-49 RESEARCH ARTICLE Machine learning in medicine using JavaScript: building web apps using TensorFlow.js for interpreting biomedical datasets Aprendizado de mquina na medicina usando JavaScript: construindo aplicativos webusando TensorFlow.js para interpretar dados biomdicos. Jorge Guerra Pires 1 * Abstract: Contributions to medicine may come from different areas, and most of these areas are filled with researchers eager to contribute. In this paper, we aim to contribute through the intersection of machine learning and web development. We employed TensorFlow.js, a JavaScript-based library, to model biomedical datasets using neural networks obtained from Kaggle. The principal aim of this study is to present the capabilities of TensorFlow.js and promote its utility in the development of sophisticated machine learning models customized for web-based applications. We modeled three datasets: diabetes detection, surgery complications, and heart failure. While Python and R currently dominate, JavaScript and its derivatives are rapidly gaining ground, offering comparable performance and additional features associated with JavaScript. Kaggle, the public platform from which we downloaded our datasets, provides an extensive collection of biomedical datasets. Therefore, readers can easily test our discussed methods by using the provided codes with minor adjustments on any case of their interest. The results demonstrate an accuracy of 92% for diabetes detection, almost 100% for surgery complications, and 80% for heart failure. The possibilities are vast, and we believe that this is an excellent option for researchers focusing on web applications, particularly in the field of medicine. Keywords: bioinformatics—TensorFlow—JavaScript—diabetes—medicine—machine learning—Angular Resumo: Contribuic¸es para a medicina podem surgir de diversas reas, e a maioria dessas reas es˜t repleta de pesquisadores ansiosos para contribuir. Neste artigo, buscamos contribuir por meio da intersec¸ao entre aprendizado de mquina e desenvolvimento web. Utilizamos o TensorFlow.js, uma biblioteca baseada em JavaScript, para modelar conjuntos de dados biomd˜icos por meio de redes neurais. ˜Nosso objetivo principal destacar o TensorFlow.js e advogar pela disseminac¸a˜o desta ferramenta para a criac¸ao de modelos avanc¸ad˜os de aprendizado de mq˜uina adaptados para aplicac¸oes web. Modelamos trs conjuntos de dados: detecc¸ao de diabetes, complicac¸oes˜ cirrg˜icas e insuficincia card . Embora Python e R dominem atualmente, o JavaScript e suas derivac¸oes estao rapidamente ganhando terreno, oferecendo desempenho comparvel erecursos adicionais associados ao JavaScript. ˜O Kaggle, a plataforma pblica de onde baixamos nossos conjuntos de dados, fornece uma extensa colec¸ao de conjuntos de dados biomdicos. Portanto, os leitores podem testar facilmente nossos mtodos discutidos, utilizando os cdigos fornecid˜os com pequenos ajuste˜ sem qualquer caso de seu interesse˜. Nossos resultados demonstram uma precisao de 92% para detecc¸a˜ ode diabetes, 100% para complicac¸oes cirrgicas e ˜80% para insuficincia card . As possibilida˜des sao vastas, e acreditamos que esta uma excelente opc¸ao para pesquisadores concentrados em aplicac¸oes web, especialmente no campo da medicina. Palavras-Chave: bioinformtica—TensorFlow—JavaScript—diabetes – medicina – aprendizado de mquina—Angular 1 Founder at [IdeaCoding Lab / JovemPesquisador.com](IdeaCoding Lab / JovemPesquisador.com), Brazil *Corresponding author: [jorgeguerrabrazil@gmail.com](jorgeguerrabrazil@gmail.com) DOI: [http://dx.doi.org/10.22456/2175-2745.133785](http://dx.doi.org/10.22456/2175-2745.133785) • Received: 07/07/2023 • Accepted: 15/01/2024 CC BY-NC-ND 4 .0 - This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4 . 0 International License. 1. Introduction Contributions to m

FAQs

What is the main goal of the study?

To show how TensorFlow.js can be used to build sophisticated machine learning models for medical web applications and make the approach accessible to non-specialists.

Which datasets and tasks were modeled?

Three biomedical tasks were modeled: diabetes detection, surgery complications, and heart failure.

What advantages does the paper claim for using TensorFlow.js in the browser?

The data stays in the browser for sensitive information, computations run client-side to avoid costly server computation, and it reduces infrastructure costs relevant to medical assistance.

Aug 4, 2026

Upload by Theodore