AI in Clinical Decision Support: Roadblocks & Opportunities

Original article was published on Artificial Intelligence on Medium

About the speaker

Having earned a PhD in molecular and cellular biology by the University of Edinburgh (UK), I have experience in computational modeling in genomic research, medicine, and population health. Notably, as a fellow in the NIH (US), I prototyped a pipeline that uses genomic and EHR-level information to create personalized models of disease risk.

Alongside being published in international peer-reviewed journals, my work has earned several awards in the UK and US, including the NYC Open Data competition for a Data Science project in 2018. I am currently a data scientist in, working closely with companies in the healthcare industry helping them to expand their capabilities using AI.

About the talk

As data processing and storage is becoming cheaper, the main barrier to entry for AI adoption is often data availability. This couldn’t be better exemplified than in medicine, where advancements in AI-enabled clinical decision support are mirroring innovations of how data are recorded and stored within healthcare systems.

AI-enabled clinical decision support includes diagnosis and prognosis, and involves classification or regression algorithms that can predict the probability of a medical outcome or the risk for a certain disease. Several image classification algorithms using medical images have been approved by the FDA as diagnostic tools in the last two years, and more are certain to follow.

Similarly, FDA approval has already been given to wearable devices that monitor vital signs to capture irregularities. These early examples demonstrate the huge potential of AI applications in medicine, as the volume and variety of medical data that get captured increases.

More than 80–90% of US hospitals and physician offices are implementing some form of an EHR, and similar or even higher adoption rates are seen globally. Despite persistent outstanding issues, the lack of interoperability between EHR systems or patient history continuity, past barriers to adoption relating to data usability and availability are being overcome.

Three examples of clinical decision support AI models built on EHR data will be discussed.

  • (1) Accumulation of medical histories from birth alongside linked maternal EHR information in a healthcare facility, enabled the prediction of high obesity risk children as early as two years after birth, possibly allowing life-altering preventative interventions.
  • (2) The Advanced Alert Monitoring system developed and deployed by Kaiser Permanente uses Intensive Care Unit (ICU) data to predict fatally deteriorating cases and alert staff to the need of life-saving interventions.
  • (3) Last, but not least, clinical decision support systems are often required to provide sufficient explanations of their predictions. Global and local explanations of predictions regarding hospital readmissions demonstrate how interpretability techniques enable such explanations.

As EHR information becomes standardized and enriched with eg. genomic information, medicine is poised to leverage AI breakthroughs to improve health outcomes.

AI in Clinical Decision Support: Roadblocks & Opportunities