Precision medicine and high-performance computing (HPC) are helping to make that last mile of diagnosis and treatment more tailored and effective. Example of using precision medicine to bring better predictability to treatment include:
- Nicklaus Children’s Hospital, which is collaborating with Rady Children’s Institute for Genomic Medicine and Sanford Health to develop precision care plans for each child based on their underlying genetics.[i]
- Since 2013 the Swedish Cancer Institute has also been a leader in precision medicine. They offer gene sequencing for their cancer patients, allowing their specialists to personalize patients’ treatment plans down to the cellular level.[ii]
- Vanderbilt University Medical Center is working with the NIH to launch the All of Us Research Program, which is collecting patient-reported lifestyle data, EHR data, blood and urine samples, and simple biometric data.[iii] This shared data will incorporate lifestyle, socioeconomics, environment and biologic aspects of health to provide more individually appropriate therapies.
Precision medicine is not without issues. Calculating a cost-benefit ratio is complex,[iv] and it increases the burden on clinicians to understand and incorporate a wealth of treatment into their decision-making process. That makes having partnerships between providers and technology vendors to create effective clinical decision support tools more critical. Dana-Farber Cancer Institute, for example, is working with Philips to bring enhanced cancer care pathways to the oncology community.[v]
High performance computing (HPC) isn’t new, but it’s increasingly being combined with high performance data analytics to make the burgeoning complexity of data more manageable.[vi] One example is its use in the rapid processing of genomic workflows to speed more tailored care to patients with chronic or life-threatening diseases. HPC can more readily combine disparate sources and types of data into a single longitudinal perspective of patients and their care – including genomic data, EHR data, claims and clinical trials data – to foster precision medicine.
However, AI and machine learning are still largely confined to specific use cases, and until there is clearer financial gain, their adoption may be slowed by health systems’ increasingly slim margins.
Read our upcoming blog, “Embracing Competitive Disruption,” to learn how your health system can prepare for the wave of new and different competitors.