Precision Medicine: From Population Averages to Individual Insight

In today’s rapidly evolving health care landscape, clinicians are increasingly asked to move beyond treating disease as it appears to anticipating how it will emerge. Advances in data, technology, and biomedical science are enabling a shift away from one-size-fits-all approaches toward care that reflects the unique biology, risk profile, and lived experience of each patient. This shift, known as precision medicine, is redefining how clinicians diagnose disease, predict outcomes, and intervene earlier and more effectively.

Saman Doroodgar Jorshery, MD, MPH—a researcher at Massachusetts General Hospital, Postdoctoral Scholar, Broad Institute of MIT and Harvard University, and the curriculum lead for AI in Medicine at Harvard Medical School’s HMX Online Learning—has been working at the intersection of clinical care, omics data, imaging, and artificial intelligence. He sees precision medicine not as a distant future, but as a transformation already underway.

“Precision medicine is the application of knowledge regarding patterns in disease and health toward care of an individual person,” Jorshery explains. “This means using genetic, molecular, imaging, and clinical data to deliver prevention and treatment strategies personalized to each patient.”

A Transformative Shift in Care

Historically, medicine has relied on population averages, or what works best for most patients most of the time. “Nowadays, there are multiple sources of information regarding an individual available for personalized risk prediction,” Jorshery says. “Precision medicine involves integrating such information toward understanding individualized health status.”

This shift transforms health care by enabling more accurate diagnoses, predictions of disease risk, prognostic models, targeted therapies, fewer adverse effects, and ultimately better outcome.

Precision Medicine in Practice

Precision medicine’s impact is already evident across clinical specialties, particularly in oncology. The identification of tumor-specific mutations has fundamentally changed how cancer is treated.

“Identifying specific mutations, such as EGFR (epidermal growth factor receptor) in lung cancer, allows patients to receive therapies that directly target their tumor biology,” Jorshery says, “improving both survival and quality of life compared to traditional chemotherapy.”

Cardiology has also embraced precision approaches by combining genomic and clinical data to guide prevention. Using statins in individuals with increased genetic risk and PCSK9 inhibitors for patients with familial hypercholesterolemia has reduced future cardiovascular events. Meanwhile, rheumatology and transplantation medicine are adopting precision strategies to better manage autoimmune disease and prevent organ rejection. “These examples highlight how tailoring treatments to individual biology can transform patient outcomes,” he says.

Omics, AI, and the Power of Integration

The future of precision medicine depends on the ability to analyze complex biological data at scale. Omics technologies, genomics, transcriptomics, proteomics, and metabolomics offer insight into disease mechanisms, particularly when integrated rather than examined in isolation.

“Transcriptomics can identify key RNA transcripts affected by disease-linked genetic loci, while metabolomics helps explain how genetic and environmental factors interact to shape metabolic profiles,” Jorshery explains. Studying these data at both bulk and single-cell levels provides visibility across biological scales.

Because omics datasets are vast and complex, artificial intelligence is essential. “By using raw omics data as input, AI models can uncover hidden patterns, predict disease risk, and identify novel biomarkers and therapeutic targets,” he says. For patients, this convergence enables earlier detection and more precise, personalized care.

Barriers to Adoption and the Role of Education

Despite its promise, precision medicine faces challenges. Many datasets lack representation across age groups, diseases, and ethnic backgrounds, while concerns about privacy, consent, and algorithmic bias remain central.

“The main barriers to wider adoption of precision medicine are data integration, equitable access, and trust,” Jorshery says. Addressing these problems will require robust data infrastructure, clear regulatory frameworks, and clinician education.

“Clinicians need a strong understanding of data science, AI, and modern biomedical technologies to interpret and apply precision medicine insights,” he explains. Equally important is learning how to integrate these insights into shared decision-making, ensuring that technology strengthens, rather than replaces, the human connection in care.

Looking Ahead: Detecting Disease Earlier

What excites Jorshery most about the next decade is the ability to identify disease at subclinical stages, when intervention may be most effective.

“The growing ability to detect disease at a subclinical stage using machine learning-based biomarkers derived from omics and imaging data represents a major shift,” he says. Recent work has shown how AI-based retinal imaging can be linked to both ocular and systemic disease risk.

“The integration of multi-omics, imaging, and AI is enabling the discovery of subclinical biomarkers that reveal early, reversible stages of disease,” he explains. Over time, this shift could move health care beyond predicting risk toward precisely intervening when health begins to change, redefining prevention and extending longevity.

As precision medicine continues to evolve, ongoing research and education will remain essential in helping clinicians to interpret emerging science and apply it thoughtfully in patient care.