|Chapter title||An ensemble approach for evaluating the cognitive performance of human population at high altitude|
|Authors||Sengupta, D., Sharma, V.K., Hota, S.K., Srivastava, R.B. and Naik, P.K.|
|Editors||Kumar, P., Kumar, Y. and Tawhid, M.A.|
Hypoxic stress at high altitude can lead to cognitive disorders. One of the key tests developed in recent years for analyzing the onset of such cognitive impairment is the Multidomain Cognitive Screening Test (MDCST). In this study, we identify the key MDCST and clinical features among the Lowlander (≤ 350 m) and Highlander (≥ 1500 but < 4300 m) populations, staying at an altitude ≥ 4300 m for a prolonged duration. Analyzing these measures ensembled with the Beck Depression Inventory (BDI) and sleep factors gives an opportunity to analyze cognitive performance, which can be associated with the early discovery of undetected depression.
A goodness-of-fit test was applied to the two population cohorts for identifying independent significant measures. This was followed by rule-based mining to discover associative rules between the clinical, behavioral, and cognitive screening parameters. The most significant MDCST parameters identified (P-value ≤.05) for analyzing the cognitive performance among the Lowlander population are Visuospatial Executive, Attention, Coordination & Learning, Object recognition, and Orientation, while for the Highlander population, Procedural Memory and Recall are identified in addition to Visuospatial Executive, Coordination, and Learning. Conclusively, a unique set of association rules have been identified with at least 30% support and more than 60% confidence in behavioral and clinical features associated with the cognitive parameters.
|Book title||Machine Learning, Big Data, and IoT for Medical Informatics|
|Digital Object Identifier (DOI)||https://doi.org/10.1016/b978-0-12-821777-1.00021-5|
|Web address (URL)||http://dx.doi.org/10.1016/b978-0-12-821777-1.00021-5|
|Journal||Machine Learning, Big Data, and IoT for Medical Informatics|