Submission Tilte
Leveraging artificial intelligence methods to analyze precision medicine cancer data
Submission Abstract:
Precision medicine is predicated on the ability to diagnose a patient’s condition and prescribe a patient-specific therapeutic regime. The practice of precision medicine has expanded over the past ten years to embrace more therapeutic areas and diagnostic applications. Technologies founded on the original rationale have led to new approaches and applications that had not been thought possible until the concept was proven.
Advances in technology, medicines, and practice were driven in part by the increased capability of data collection and analysis for an increasing number of biomarkers and imaging modalities. In turn, the results have justified continued investment of resources in precision medicine research. As a consequence of these successes, disease conditions that had been a challenge to diagnose and treat have become easier to identify and manage, especially in an aging population with individuals suffering from multiple cancer types and illnesses:
According to a recent report, nearly 80% of Medicare beneficiaries have at least 2 chronic conditions and more than 60% have at least 3 chronic conditions. Experts estimate that 26% of the US population will be living with multiple chronic conditions by 2030. Although multimorbidity is not limited to older adults, its prevalence increases substantially with age.
(Reference: Fabbri E, Zoli M, Gonzalez-Freire M, Salive ME, Studenski SA, Ferrucci L. Aging and Multimorbidity: New Tasks, Priorities, and Frontiers for Integrated Gerontological and Clinical Research. J Am Med Dir Assoc. 2015 Aug 1;16(8):640-7; doi: 10.1016/j.jamda.2015.03.013. Epub 2015 May 7. PMID: 25958334; PMCID: PMC5125299.)
The true power of these techniques is to use the multiple signals gleaned in a panel of tests to read the signal against the background of noise to make a diagnosis and treatment recommendation. As the ability to measure and understand these readings improve, the benefit should accrue to detect at earlier stages or for conditions that start at younger ages but not be obvious until some time has passed - e.g., slow-growing cancers. Earlier diagnoses can lead to earlier treatment with better overall outcomes with concomitant reduced burden on the healthcare system. Hence a premium will be placed on the ability to screen in routine check-ups to assess a patient’s state of health, even when the patient presents with no apparent symptoms or seemingly ambiguous diagnostic results.
In this special issue, we expand on how artificial intelligence algorithms applied to precision medicine data will have a profound impact on identifying major cancer diseases early in their presentation. Research areas in this issue will survey: using multi-modality diagnostic modalities for earlier diagnosis; more definitive characterization of a disease state; new therapies targeted to novel mechanisms of actions; machine and adaptive learning; expert-guided machine learning to prioritize the most effective treatment options (from excision to drug therapies); making the transition to AI in the clinical setting; training healthcare professionals to use machine learning and artificial intelligence tools; and advances in analytics and artificial intelligence to assess clinical data and medical observations made by specialists.
