Project
Portfolio

Project Portfolio, 2020-2021 Cohort

SEED – Diagnostic

Within our Diagnostic vertical, we have the SEED (Self-replicating Environmentally-Embedded Diagnostic) team developed a cell-based diagnostic tool that detects specific DNA or RNA sequences and produces a customizable readout. The invention is made possible by genetically modifying and utilizing live bacteria cells of the species Bacillus subtilis which possess the natural ability to take up DNA from their environment in a process known as competence. This technique is useful for a variety of diagnoses, including COVID-19.

SnapDx – Diagnostic/Med Tech

SnapDx is an ultra low-cost, electricity-free saliva-based molecular COVID test. Invented at PrakashLab, Stanford – SnapDx presents a unique and completely instrument-free approach to multi-step molecular diagnostics for home and field settings. As COVID-19 cases increase globally, fast, frequent, and frictionless diagnostics needed to be accessible to everyone, including resource-limited regions. Looking beyond COVID-19, this saliva-based diagnostics test can be programmed for other targets such as seasonal flu, malaria, and new variants of viruses.

TrueImage – Digital Health

The TrueImage team developed a machine learning application that evaluates images taken by patients. The designed algorithm identifies the skin in the photo through segmentation, and not only analyzes the photo quality, but gives patients feedback and how to improve the image quality. The algorithm identifies skin blemishes, regardless of skin pigmentation, and can tell patients if the photo is unsatisfactory due to blurriness, poor lighting, or zoom control. They team has created a diverse database of photos to help address the inequities in differing skin pigmentation photo resources.

Hymecromone – Therapeutic

The ongoing COVID-19 pandemic continues to remind us that therapeutic options to address respiratory inflammation and fibrosis remain limited. With support from Catalyst, the Hymecromone team completed a Phase 1 clinical trial for a new class of medications earlier this year under the leadership of investigators Paul Bollyky MD, D.Phil, Carlos Milla, MD, and Angela Rogers, MD. With positive results from this trial in hand, the Stanford team is now partnering with pulmonary experts and emerging biotech Halo Biosciences to advance clinical development in pulmonary hypertension and other diseases characterized by inflammation and fibrosis.

Over the shoulder shot of a patient talking to a doctor using of a digital tablet

PocketRN – Digital Health

Stanford Medicine Catalyst has partnered with Stanford Health Care Nursing Administration to test and validate an algorithm-based, video-visit platform developed by the Pocket RN innovation team. The telenursing application connects Stanford Health Care patients with specific questions to Stanford Health Care specialty nurses in a matter of minutes. The IRB-approved study is looking to enroll up to 200 patients and will train 20+ nurses to be available on the platform.

Cardinal Robotics – Med Tech

COVID-19 has made disinfecting work environments a high priority across all industries. The Catalyst team is working with Stanford Health Care’s Environmental Health Services specialists to assess the utility of Cardinal Robotics’ low-cost, autonomous UV-C light robotic technology. The Stanford Medicine teams hosted a demo day during which multiple UV-C light robots were evaluated, head-to-head, in a simulated clinical environment. Technology like these achieve the sanitization efficacy of existing UV systems while protecting the user from exposure to UV-C radiation, disinfecting both surfaces and the air.

VIVA – Digital Health

The MVP solution for VIVA (Video Visit triage using AI) will combine the scalability of chatbots with the precision and accuracy of physician video assessment by creating a robust patient triage model. The solution will leverage multi-modal data including patient video and audio with deep learning apps to evaluate appearance. The MVP will also utilize EHR data inputs.