This presentation will cover: 1) treating patients as equal partners when building digital health solutions by engaging them in the development from the start of the process, to ensure the solutions designed fit well into their lives; 2) leveraging the connection between technology and our partnership with patients, to drive innovation in the most meaningful areas to manage their disease; 3) enabling better outcomes for patients and supporting them in having a more positive experience during treatment.

An evolving trend in clinical and translational science has been for CT decentralization. The benefits are clear, the ability to decrease burden(s) to trial participants, improve recruitment and retention to enable interventions to succeed (or fail faster without early termination), and offer more robust, rigorous medical evidence from broader demographics and diverse participants. This talk will discuss challenges and benefits in terms of existing NIH-funded efforts to advance in terms of the enabling DHT tools.

Early detection of disease is crucial for early intervention. Nowhere is this more evident than in the detection of infectious disease. We have built a scalable real-time smartwatch-based alerting system for the early detection of aberrant physiological signals associated with early infection onset and other stressors. We also perform continuous glucose monitoring for detecting glucose dysregulation.

The future of health and wellness lies in remote patient monitoring and digital health. By adapting to remote technology, industry leaders can aid in prevention, prediction and early detection. Throughout my presentation, I’ll discuss how remote patient monitoring can increase accessibility to healthcare, and how it is a critical first step toward tackling heart disease and improving overall vascular health.

Malama enables remote monitoring for high-risk perinatal conditions, beginning with diabetes in pregnancy which affects nearly 1 in 5 women globally. Malama's fully HIPAA compliant platform makes it easy for patients to track glucose data and receive actionable insights, and for providers to reduce likelihood of adverse events.

The Artificial Intelligence (AI) and Machine Learning (ML) for in vitro Diagnostics (IVDs) Working Group was established to address iterative improvements to AI/ML-enabled medical devices, including IVDs. This session will discuss the development of a regulatory framework to incorporate the use of Real-World Data (RWD) with the specific goals to develop a predetermined change control plan (PCCP) with templates for Software Pre-Specifications (SPS) and an Algorithm Change Protocol (ACP).

It’s crucial in this era of digitization to bring innovative devices, emerging products, and effective treatment to patients. Digitization is a required element for scalable and sustainable healthcare. Advancement in digital pathology, computational pathology, and artificial intelligence expand the network of brainpower for diagnostic, prognostic, and predictive pathology in precision medicine.

The first companion diagnostic for oncology precision medicine was HER2 over 20 years ago using IHC and FISH. IHC is semiquantitative and poor at measuring spatial heterogeneity in tumors. We have developed a deep learning computational pathology method that scores HER2 and other IHC markers at low expression levels, quantitates expression of each cancer cell, and allows scoring of spatial heterogeneity of positive and negative cells. Application of this method called Quantitative Continuous Scoring of IHC better predicts response to ADCs.