Personalized medicine drug discovery has long been a goal for researchers and clinicians alike, but several obstacles have slowed its progress. Although there has been an explosion in genomic data, the corresponding clinical utility for this data has been slow to be validated. Data from tissue images \u2014 a key diagnostic tool \u2014 has been limited to simple scoring, resulting in limited information available to researchers to customize therapies based on patient biology.<\/p>\n
Growth in personalized medicine drug discovery has increased significantly in recent years, however. Here are three ways technology is enabling more targeted and effective drug development.<\/p>\n
Consumers first realized the power of correlation with e commerce. Amazon’s “People Like You Also Bought” feature introduced algorithms that look at online buying profiles and match them to others to surface relevant products. Bioinformaticists are using a similar mindset to create medical algorithms that segment populations for clinical trials.<\/p>\n
As more data \u2014 including genetics, biomarkers, tissue samples, and patient responses \u2014 are gathered, digitized, and optimized for data mining, researchers will be able to identify correlations, better understand a person’s biology, and predict how they will react to a particular therapy. This makes personalized medicine drug discovery more targeted and effective than approaches based on broad population averages.<\/p>\n
The power of correlation will truly come to fruition in approaches that use data mining to identify potential rare side effects and segment populations into those at risk of experiencing them. With this information, researchers can develop more personalized treatments and physicians can match those treatments to the right patients.<\/p>\n
The idea of personalized medicine drug discovery often focuses on the ability to quickly extract data from DNA. However, genomic data alone does not provide a comprehensive patient profile, and diagnoses are increasingly being made based on multiple types of diagnostic data.<\/p>\n
Researchers can now go beyond DNA and mine quantifiable data from tissue images. Tissue provides critical information about the stage and manifestation of disease, enabling more informed decision making in the clinical development process. The ability to combine and correlate quantified tissue image data with genomic information and clinical outcomes is essential to personalized medicine drug discovery and is redefining how new therapies are developed.<\/p>\n
Consumer technologies \u2014 and in particular wearable technologies \u2014 are now poised to make a significant impact on personalized medicine drug discovery by reaching patients directly through their devices. Apple’s ResearchKit, a medical platform that turns the iPhone and HealthKit into diagnostic tools, is changing clinical trials and treatment in two important ways.<\/p>\n
First, this kind of technology can support more effective trial recruitment. Pharmaceutical companies will be able to raise more awareness of open clinical trials among patients directly, and patients will be able to more easily identify and join trials applicable to them.<\/p>\n
Second, since ResearchKit enables researchers to gather new types of health data from patients using mobile apps, consumer technologies will allow doctors to treat patients based on more holistic and personalized information. This data will also make its way back into the research and development loop to support drug development and treatment guidelines.<\/p>\n
Together, these three innovations represent a fundamental shift in how personalized medicine drug discovery is approached \u2014 moving from population level assumptions toward truly individualized care guided by each patient’s unique biological data.<\/p>\n