Sheshadri Iyengar Raghavan Bhagyashree1, Kiran Nagaraj2, Martin Prince3, Caroline H D Fall4, Murali Krishna2. 1. E&C Department, ATME College of Engineering, Mysore, India. srbhagyashree@yahoo.co.in. 2. CSI Holdsworth Memorial Hospital, PO Box 28, Mandimohalla, Mysore, India. 3. Department of Epidemiological Psychiatry, Institute of Psychiatry, Kings College, London, UK. 4. International Paediatric Endocrinology, MRC Lifecourse Epidemiology Unit, University of Southampton, Southampton, UK.
Abstract
BACKGROUND: There are limited data on the use of artificial intelligence methods for the diagnosis of dementia in epidemiological studies in low- and middle-income country (LMIC) settings. A culture and education fair battery of cognitive tests was developed and validated for population based studies in low- and middle-income countries including India by the 10/66 Dementia Research Group. AIMS: We explored the machine learning methods based on the 10/66 battery of cognitive tests for the diagnosis of dementia based in a birth cohort study in South India. METHODS: The data sets for 466 men and women for this study were obtained from the on-going Mysore Studies of Natal effect of Health and Ageing (MYNAH), in south India. The data sets included: demographics, performance on the 10/66 cognitive function tests, the 10/66 diagnosis of mental disorders and population based normative data for the 10/66 battery of cognitive function tests. Diagnosis of dementia from the rule based approach was compared against the 10/66 diagnosis of dementia. We have applied machine learning techniques to identify minimal number of the 10/66 cognitive function tests required for diagnosing dementia and derived an algorithm to improve the accuracy of dementia diagnosis. RESULTS: Of 466 subjects, 27 had 10/66 diagnosis of dementia, 19 of whom were correctly identified as having dementia by Jrip classification with 100% accuracy. CONCLUSIONS: This pilot exploratory study indicates that machine learning methods can help identify community dwelling older adults with 10/66 criterion diagnosis of dementia with good accuracy in a LMIC setting such as India. This should reduce the duration of the diagnostic assessment and make the process easier and quicker for clinicians, patients and will be useful for 'case' ascertainment in population based epidemiological studies.
BACKGROUND: There are limited data on the use of artificial intelligence methods for the diagnosis of dementia in epidemiological studies in low- and middle-income country (LMIC) settings. A culture and education fair battery of cognitive tests was developed and validated for population based studies in low- and middle-income countries including India by the 10/66 Dementia Research Group. AIMS: We explored the machine learning methods based on the 10/66 battery of cognitive tests for the diagnosis of dementia based in a birth cohort study in South India. METHODS: The data sets for 466 men and women for this study were obtained from the on-going Mysore Studies of Natal effect of Health and Ageing (MYNAH), in south India. The data sets included: demographics, performance on the 10/66 cognitive function tests, the 10/66 diagnosis of mental disorders and population based normative data for the 10/66 battery of cognitive function tests. Diagnosis of dementia from the rule based approach was compared against the 10/66 diagnosis of dementia. We have applied machine learning techniques to identify minimal number of the 10/66 cognitive function tests required for diagnosing dementia and derived an algorithm to improve the accuracy of dementia diagnosis. RESULTS: Of 466 subjects, 27 had 10/66 diagnosis of dementia, 19 of whom were correctly identified as having dementia by Jrip classification with 100% accuracy. CONCLUSIONS: This pilot exploratory study indicates that machine learning methods can help identify community dwelling older adults with 10/66 criterion diagnosis of dementia with good accuracy in a LMIC setting such as India. This should reduce the duration of the diagnostic assessment and make the process easier and quicker for clinicians, patients and will be useful for 'case' ascertainment in population based epidemiological studies.
Entities:
Keywords:
Dementia; Diagnosis; Low- and middle-income countries; Machine learning
Authors: F W Unverzagt; O S Morgan; C H Thesiger; D A Eldemire; J Luseko; S Pokuri; S L Hui; K S Hall; H C Hendrie Journal: J Int Neuropsychol Soc Date: 1999-03 Impact factor: 2.892
Authors: M Ganguli; V Chandra; J E Gilby; G Ratcliff; S D Sharma; R Pandav; E C Seaberg; S Belle Journal: Int Psychogeriatr Date: 1996 Impact factor: 3.878
Authors: H C Hendrie; B O Osuntokun; K S Hall; A O Ogunniyi; S L Hui; F W Unverzagt; O Gureje; C A Rodenberg; O Baiyewu; B S Musick Journal: Am J Psychiatry Date: 1995-10 Impact factor: 18.112
Authors: D I Kaufer; J L Cummings; P Ketchel; V Smith; A MacMillan; T Shelley; O L Lopez; S T DeKosky Journal: J Neuropsychiatry Clin Neurosci Date: 2000 Impact factor: 2.198
Authors: H C Hendrie; K S Hall; N Pillay; D Rodgers; C Prince; J Norton; H Brittain; A Nath; A Blue; J Kaufert Journal: Int Psychogeriatr Date: 1993 Impact factor: 3.878
Authors: Murali Krishna; Eunice Beulah; Steven Jones; Rajesh Sundarachari; Saroja A; Kalyanaraman Kumaran; S C Karat; J R M Copeland; Martin Prince; Caroline Fall Journal: Int J Geriatr Psychiatry Date: 2015-12-17 Impact factor: 3.485
Authors: Ana Luisa Sosa; Emiliano Albanese; Martin Prince; Daisy Acosta; Cleusa P Ferri; Mariella Guerra; Yueqin Huang; K S Jacob; Juan Llibre de Rodriguez; Aquiles Salas; Fang Yang; Ciro Gaona; At Joteeshwaran; Guillermina Rodriguez; Gabriela Rojas de la Torre; Joseph D Williams; Robert Stewart Journal: BMC Neurol Date: 2009-08-26 Impact factor: 2.474
Authors: Min Young Chun; Chae Jung Park; Jonghyuk Kim; Jee Hyang Jeong; Hyemin Jang; Kyunga Kim; Sang Won Seo Journal: Front Aging Neurosci Date: 2022-08-05 Impact factor: 5.702