Suggestions
Kirstin Aschbacher
Team Lead | AI/ML Data Scientist | Psychologist
Kirstin Aschbacher is a highly accomplished individual with a diverse educational background. She holds postgraduate degrees in Biomathematics, Bioinformatics, Computational Biology, and Psychology & Medicine from the University of California, San Francisco (UCSF). Additionally, Kirstin has a Ph.D. in Clinical Psychology, specializing in Psychoneuroimmunology & Behavioral Medicine from UC San Diego. Her undergraduate studies include a Bachelor of Arts in Music Theory and Composition from Brown University.
With a wealth of professional experience, Kirstin has held various roles in prestigious organizations. She has served as a Machine Learning Team Lead at SandboxAQ, a Consultant in Stress & Well-Being Science and Data Science at Health and Wellness Consulting LLC, and as a Senior Director of Health Data Science at Meru Health. Kirstin has also contributed her expertise as the Head of Health Data Science at Meru Health, a Health Data Architect at Oura, an Associate Professor & Data Scientist at UCSF, and a Data Scientist & Behavioral Health Specialist at Jawbone. Furthermore, her experience includes roles such as Fellow at Insight Data Science, Assistant Professor at UCSF School of Medicine, Research Fellow at The Institute for Integrative Health, Postdoctoral Fellow at UCSF, and a Psychology Resident in Behavioral Medicine at Harborview Medical Center/University of Washington.
Highlights
Enjoyed collaborating with an excellent group of cardiologists and researchers to publish this special issue on “Current Proceedings in Magnetocardiology—past, present, future” in the scientific journal: Frontiers in Cardiovascular Medicine. We explore the latest advancements and applications of magnetocardiography (MCG) in clinical settings.
In my capacity as the AI/ML Team Lead for SandboxAQ's AQMed team, I helped contribute a portion about the potential of AI/ML to advance MCG-based cardiovascular diagnostics. Lately, AI/ML tools are so well-packaged, many people seem to believe you just throw the data in there, mix, and valuable products emerge. The thing is: Auto-ML doesn't cut it for really hard problems like we find in medicine. Reading the literature and learning from medical experts really allows us to understand which AI models can best extract the underlying pathophysiologic signature of a particular diagnosis.
In AI + Health, the value of interdisciplinary knowledge can't be overstated.
So excited to announce our team's collaboration to further AI-based detection of cardiac disease with the Mayo Clinic! 🚀
I get that AI is everywhere, but let me tell you - this is different. Our device is out there "in the wild" being pressure-tested by some of the best clinical cardiologists in the world.
You might think: novel quantum-sensing device = not much data. Not true. Simultaneously, we have developed novel approaches to build AI/ML models in large datasets to accelerate our hardware and software development.
You'll want to keep an eye on this one! 😉
