Premium
[TD‐P‐005]: COMPARING CLINICALLY BASED VERSUS ALGORITHM‐GENERATED INTERVENTIONS IN THE CONTEXT OF ALZHEIMER's DISEASE (AD) PREVENTION
Author(s) -
Caesar Emily E.,
Hristov Hollie,
Hackett Katherine,
Walker John Q.,
Isaacson Richard
Publication year - 2017
Publication title -
alzheimer's and dementia
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 6.713
H-Index - 118
eISSN - 1552-5279
pISSN - 1552-5260
DOI - 10.1016/j.jalz.2017.06.2601
Subject(s) - medicine , psychological intervention , context (archaeology) , disease , personalized medicine , family medicine , bioinformatics , psychiatry , paleontology , biology
factors associated with AD simultaneously. Data inputs comprise genomics, bio-specimen measurements, imaging results, medical histories, medications, allergies, immunizations, comorbidities, and results of cognitive evaluations. Algorithms compare the status of multiple physiological and lifestyle states known to be contributors to cognitive decline against desired normative states. We observe that AD disease drivers are interlocked, comprising modifiable feedback loops. Software algorithms implement the protocol, and generated recommendations are delivered to physicians. Health coaches motivate individuals’ adherence and ongoing data collection. Results: One to five iterations of protocols were generated for self-selected individuals (n1⁄4183, 52% pre-MCI, 58.5% female, mean age 66.7 years, mean 17.6 years of education, mean BMI 24.6). Genome data files were obtained with patient consent (65.4% ApoE4 carriers). 100+ serum blood tests were collected in each iteration. Approximately 60% of individuals on the protocol for 6 months have improved memory function, as measured on standardized cognitive evaluations. Conclusions: An informaticsbased platform enables an actionable combination therapy for AD. This allows the testing of the hypothesis that recommended intervention protocols for physician usage can consistently modulate a large number of factors. From an IT perspective, well-established, big-data analytics techniques are utilized, including prioritizing, weightings, probabilities, and partial differential equations. Diagnosis, treatment recommendations and ongoing tracking is extensible. Health coaches are essential to adherence, providing guidance and influencing individuals’ compliance. Individuals comply with the recommendations and can achieve the shortterm goals leading to measurable cognitive improvements. Longer-term studies are needed to show that addressing multiple disease drivers simultaneously can be an effective path to improve cognitive function, and to delay or prevent AD.