Artificial intelligence (AI) and big data are transforming healthcare with high-throughput analyses of complex diseases. Machine learning and sophisticated computational methods can be used to efficiently interpret human genomes and other biomarkers, providing insights for patient treatment and with major applications in diagnostics and preventive care.
A personalised treatment plan may include preventive care for diseases that are at a higher risk of developing, for example increased screening for cancer if a patient possesses the BRCA 1 or BRCA 2 gene mutation. Additionally, AI can generate insights from genetic information, biomarkers, and other physiological data to predict how a patient will respond to different treatment options, which may help avoid adverse reactions, reduce the use of expensive or unnecessary treatments on patients that are unlikely to respond, and ultimately reduce hospitalisation and outpatient costs. For more information, GlobalData’s latest report, Precision and Personalized Medicine – Thematic Research, provides insight into the most prevalent uses of personalised medicine, new applications, and the healthcare, macroeconomic, and technology themes driving growth.
Big data and bioinformatics can also offer human-centred data to be used for early drug research in lieu of, or in combination with, conventional methods like cell or animal models. This could help streamline the drug discovery process by reducing the time and money spent on inviable drug candidates, especially for conditions that translate poorly between animal models and humans. For example, laboratory mice have historically been utilised in early phase drug trials but are a poor model for genetic diversity and age-related diseases in humans. So, treatments for neurodegenerative and other age-related conditions could greatly benefit from the inclusion of human genetics in research and development (R&D).
The field of oncology has been the most accepting of personalised medicine, though other areas of medicine could greatly benefit from this medical model. Still, major barriers to commercialisation and access are funding and reimbursement. Stockholders want to invest in therapies that have a large patient pool and payers are hesitant to reimburse patients for novel diagnostic tests and treatments that lack the positive clinical data of traditional ‘one-size-fits-all’ approaches. However, we could see interest in the sector resurge as increasing market competition and advances in technology rapidly drive down the cost of genetic sequencing. Physiological data is also more comprehensive and accessible than ever due to the recent growth of remote patient monitoring devices and wearable tech from the Covid-19 pandemic.
Furthermore, companies are collaborating to reduce development costs and share patient data for research. Recently, Valo Health Inc., a medical technology company, and Kahn-Sagol-Maccabi (KSM), a research and innovation center, announced they will perform joint studies utilising KSM’s Tipa Biobank of more than 800,000 samples and Valo’s drug discovery and development platform Opal. The Tipa Biobank stores ‘live’ samples, with plans to continue collecting genetic samples from the same subjects over their respective lifetimes. The collaboration provides an opportunity to utilise the growing patient data sector to capitalise on the race to get AI-designed drugs to market and could give Valo/KSM a competitive edge for developing treatments in oncology and for neurodegenerative diseases. Industry collaborations between big market players may also reassure healthcare payers that personalised technology is worth the investment, improving funding and patient identification for new trials and treatments.
Genetic and physiological data can help paint a clearer picture of overall patient health, and it is expected that the demand for preventive medicine will continue increasing as people live longer and the global elderly population grows. Looking to the future, precision and personalised medicine has the potential to expedite drug discovery, improve disease screening, and predict patient responses to treatment options, leading to improved quality of care and reduced overall healthcare costs.