Self-Service Data Science in Healthcare with Automated Machine Learning

Abstract

(1) Background: This work investigates whether and how researcher-physicians can be supported in their knowledge discovery process by employing Automated Machine Learning (AutoML). (2) Methods: We take a design science research approach and select the Tree-based Pipeline Optimization Tool (TPOT) as the AutoML method based on a benchmark test and requirements from researcher-physicians. We then integrate TPOT into two artefacts: a web application and a notebook. We evaluate these artefacts with researcher-physicians to examine which approach suits researcher-physicians best. Both artefacts have a similar workflow, but different user interfaces because of a conflict in requirements. (3) Results: Artefact A, a web application, was perceived as better for uploading a dataset and comparing results. Artefact B, a Jupyter notebook, was perceived as better regarding the workflow and being in control of model construction. (4) Conclusions: Thus, a hybrid artefact would be best for researcher-physicians. However, both artefacts missed model explainability and an explanation of variable importance for their created models. Hence, deployment of AutoML technologies in healthcare remains currently limited to the exploratory data analysis phase.

Deep learning neural network (DLNN)-based classification and optimization algorithm for organ inflammation disease diagnosis

“…An employment of computerized machine learning scheme supports physicians to extract knowledge from previous data and diagnose patient. In [25] a treebased tool is proposed for providing automated ML to test the patient and that is integrated with notebook and web application. In a multi-tenant environment identifying and detecting anomalies activities is an important measurement because there is more possibility for anomalies from visitors of any family and health care employers and in [26] entropy-based detection is proposed, because it identi es irregularity of many applications.…”

Building an Arabic Dialectal Diagnostic Dataset for Healthcare

“…Islam et al [37] discuss the importance of NLP in the healthcare industry with researchers finding ways to improve diagnostics. Furthermore, automation for initial and informal diagnosis has been envisaged through the use of NLP to provide an on-demand self-service for patients [38]. The communication between a doctor and a patient usually involves personal questions, which reveal intimate information necessary for an accurate diagnosis [19].…”

Technology Management for Accelerated Recovery during COVID-19

“…Lower target value represented better outcomes (or improved recovery rate) arising from the pandemic. As per Ooms & Spruit (2020), there have been many instances where data science has leveraged the use of Machine Learning techniques in the healthcare sector, and considering the same, a set of models were created and evaluated to generate Covid-19 related predictions. Machine Learning offered the ability to program real-world problems, explicitly using computer algorithms and statistical techniques.…”