Premium
P3‐015: CIRCADIAN RHYTHM CHARACTERISTICS MEASURED WITH ACTIGRAPHY IN PATIENTS WITH IRREGULAR SLEEP‐WAKE RHYTHM DISORDER AND ALZHEIMER'S DISEASE
Author(s) -
Murphy Patricia,
Bsharat Mohammad,
Kemethofer Manuel,
Filippov Gleb,
Kubota Naoki,
Moline Margaret
Publication year - 2018
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.2018.06.1370
Subject(s) - actigraphy , circadian rhythm , rhythm , audiology , psychology , medicine , physical medicine and rehabilitation
accuracy. Prior work by this team applied a well-established approach for text categorization popularly known as ‘Bag of Words’ to AE data and tested a wide range of classifiers (Ravindranath et. al, AAIC 2017). We showed that K-Nearest Neighbors (KNN) is simple and accurate with smaller training sets and the resource intensive logistic regression and neural network displayed similar performance after balancing categories in smaller training set. Here, we show that a DNN demonstrates consistency in prediction as well as improvement in accuracy over the previously reported KNN classifier. Results: DNN obtained an accuracy of approximately 75% in its top prediction with a promise of improving the accuracy as the AE dataset continue to grow. We expect this method reduce the workload on the medical coders and allow them to focus on evaluating the predicted results. Conclusions:Future work will focus on deploying the DNNmodel to seamlessly collect, predict and code data with an emphasis on improving model training methods. We plan to construct a framework that will simplify the use of Deep Learning in medical coding and analysis.