For many patients today, especially those managing chronic conditions, having a consistent understanding of the status of one’s health and wellbeing is a challenge. Without information about activities going on outside the clinical setting, the level of insight into everyday health is limited.
Through the use of patient-generated health data (PGHD), providers gain access to and understanding of a person’s activity levels and biometrics information from wearables, apps, and in-home medical devices that many patients today use on a regular basis. When this information is integrated into the clinical system, it forms a more comprehensive picture of an individual’s health and enables providers to identify behaviors or trends that could result in a negative health event.
Leveraging this information, care teams are able to provide more proactive, preventive care and offer practical guidance to patients in real time to help improve habits and offer the best possible care.
And, with developments in artificial intelligence (AI) and data science solutions for healthcare, providers are being empowered with deeper insights into patient health. More specifically, predictive analytics are offering significant opportunity for providers to intervene before a patient is expected to trend negatively or experience an adverse health event.
To continue advancing the delivery of quality care, Validic’s™ data science team has developed the Validic Statistics Engine. The first of Validic’s data science initiatives to be released, the Statistics Engine enables care teams to easily derive individual or population-level trends and anomalies from PGHD, powering personalized interventions and user analysis. Updates in the Statistics Engine are made in seconds – or near real time – allowing clinicians to take the right actions at the right time to intervene before a decline in health.
Consider Jack, who has type II diabetes and is struggling to keep his blood glucose values in range. The statistics engine can enable clinicians to easily conduct a macronutrient analysis of his diet – correlated with blood glucose, weight, sleep, activity, caloric intake and burn – to serve as the basis for personalized nutrition and meal recommendations. This can help create personalized, realistic targets for his nutrition.
However, one week, Jack has a considerable number of out-of-range readings. His care manager, Maria, receives a notification regarding the outliers and reaches out to engage him. After that conversation and consulting with Jack’s physician, they adjust the insulin dosage and treatment plan accordingly – preventing a hypoglycemic reaction.
By making use of the large amounts of PGHD that live outside the clinical system – and applying data science techniques to more deeply understand the meaning and subsequent impact of behavior and related health data – providers can offer more comprehensive care to help patients improve behavior and prevent negative health events.
Interested in learning more about the Validic Statistics Engine and our other data science initiatives? Email us at email@example.com.