Predictive Medicine

Issues of Concern

Predictive medicine is a relatively new medical subspecialty, yet the concept is not novel. In the most basic terms, predictive medicine utilizes specific laboratory and genetic tests to determine an individual's probability of developing a disease. Biomarkers have been commonly used in oncology. Still, the aim is to increase the use of similar biomarkers to predict the more common clinical disorders seen in everyday life.

Predictive Medicine 

Ideally, we would calculate a person’s risk for breast cancer or any other disease and intervene appropriately. This is the goal of predictive medicine: obtaining and cataloging characteristics about individual patients, analyzing that data to predict the patient’s risk for an outcome of interest, predicting which treatment might be most effective for which individual, and then intervening before the outcome occurs.Traditionally, predictive medicine was exclusively confined to the realm of genetics. It was once thought that genetics would revolutionize medicine, and genetics and genomics have improved our ability to predict individual risk for some diseases (eg, the BRCA gene and breast cancer) and predict which treatment will be more effective in a given individual (eg, therapy directed at a molecular target in cancer). However, genetics-based risk prediction has proven to be of limited benefit for reasons including (1) whole-genome sequencing is still relatively expensive and not currently covered by insurance, and (2) the majority of diseases afflicting the population today is multifactorial. For example, heart disease is influenced not only by genetics but also by age, diet, exercise, and stress levels. Collecting and organizing this data for analysis is invaluable.

The Big Data Revolution [3]

Though never formally quantified, healthcare data has already been collected on a titanic scale; every vital sign, medical chart, and radiology image from every clinic, pharmacy, and hospital collectively represent only a tiny fraction of data points available for analysis. Social media, billing, census, and more data also include information contributing to healthcare outcomes. The amount of data increases exponentially as data collection, storage, and processing prices decrease. All this data, coupled with newer computer-based analytic techniques, such as machine learning, make up the so-called "Big Data Revolution." With big data, predictive medicine may soon be able to quantify individual risk for various healthcare outcomes and determine optimal, personalized treatment options. Other industries have already taken advantage of this revolution and are continuing to refine their predictive applications: banks can predict a customer’s risk of defaulting on a loan, and social media websites predict the type of advertisement to which a user is most likely to respond, and insurance companies predict how likely an individual is to file a claim. Most importantly, these industries have developed the software and workflow infrastructure needed to deploy these analyses on the front lines of their operations in real-time.

Clinical Significance

To achieve its goals, predictive medicine must provide applicable insights about outcomes that have not yet occurred and deliver these personalized insights to frontline healthcare providers such as physicians, midlevel practitioners, and nurses at the point of patient contact. Otherwise, predictive medicine's potential is reduced to an academic novelty: compelling in theory but impractical in clinical practice. 

Effective adoption and implementation require significant efforts to purchase, develop, and refine the IT infrastructure and advocate for this next generation of data-based medicine. Success requires the alignment of incentives across all stakeholders—from the medical software companies developing these tools to the medical center administration investing in the infrastructure to the healthcare providers ultimately responsible for using these tools appropriately.   Assuming full adoption, predictive medicine faces additional new challenges. With the unprecedented acquisition and utilization of healthcare and healthcare-related data, HIPAA and data security become even more prominent issues. Philosophically, there are likely to be ongoing debates about the use and overuse of these technologies and their effect on clinical acumen and medical practice, just as there is ongoing criticism regarding the overuse of CTs and other imaging modalities.None of these challenges are insurmountable, and the potential benefits at this time appear to be worth the effort. With the Affordable Care Act's shift from quantity-based healthcare payment reimbursement to a value-based reimbursement system, stakeholders should be even more compelled to closely examine the cost savings and quality improvements afforded by predictive medicine and big data. Only time can tell if predictive medicine lives up to its potential.[4][5]

The biggest problem with predictive medicine is the validity of the available tests. No test is 100% sensitive and 100% specific. Hence, false positives and negatives are expected when applying any test to predict disease. Cost and ethics are also major concerns when it comes to genetic testing to predict disease. When applying genetic tests to predict disease, one can never negate the role of the environment or lifestyle. Plus, the reliability of genetic testing is not 100%. With cost containment a priority in healthcare, empirical ordering of predictive tests may not be practical or realistic for the entire population.

While big data results have helped yield valuable clinical variables that are potentially associated with patient clinical outcomes of interest, one must appreciate the limitations of big data. Indeed, several reports have been made regarding potential miscoding and/or incorrect diagnostic coding that can ultimately result in inconclusive or potentially incorrect statistical conclusions.

Several authors have proposed utilizing big data results and their statistically and clinically relevant variables as a "flashlight" to highlight larger groups of relevant variables to be applied at the institutional level as part of more customized statistically relevant analyses to mitigate these limitations.[6][7]

Nursing, Allied Health, and Interprofessional Team Interventions

Since predictive medicine can help identify patients at greatest risk for an adverse outcome, nursing staff must understand predictive medicine and the importance of the data they collect. This includes accurate and appropriate data collection, proper assessment technique, and communicating to clinician staff when a patient presents with "red flags," indicating they are an at-risk individual.