Size at birth, lifecourse factors, and cognitive function in late life: findings from the MYsore study of Natal effects on Ageing and Health (MYNAH) cohort in South India.

OBJECTIVE: To examine if smaller size at birth, an indicator of growth restriction in utero, is associated with lower cognition in late life, and whether this may be mediated by impaired early life brain development and/or adverse cardiometabolic programming. DESIGN: Longitudinal follow-up of a birth cohort. SETTING: CSI Holdsworth Memorial Hospital (HMH), Mysore South India. PARTICIPANTS: 721 men and women (55-80 years) whose size at birth was recorded at HMH. Approximately 20 years earlier, a subset (n = 522) of them had assessments for cardiometabolic disorders in mid-life. MEASUREMENTS: Standardized measurement of cognitive function, depression, sociodemographic, and lifestyle factors; blood tests and assessments for cardiometabolic disorders. RESULTS: Participants who were heavier at birth had higher composite cognitive scores (0.12 SD per SD birth weight [95% CI 0.05, 0.19] p = 0.001) in late life. Other lifecourse factors independently positively related to cognition were maternal educational level and participants' own educational level, adult leg length, body mass index, and socioeconomic position, and negatively were diabetes in mid-life and current depression and stroke. The association of birth weight with cognition was independent cardiometabolic risk factors and was attenuated after adjustment for all lifecourse factors (0.08 SD per SD birth weight [95% CI -0.01, 0.18] p = 0.07). CONCLUSIONS: The findings are consistent with positive effects of early life environmental factors (better fetal growth, education, and childhood socioeconomic status) on brain development resulting in greater long-term cognitive function. The results do not support a pathway linking poorer fetal development with reduced late life cognitive function through cardiometabolic programming.

Diagnosis of Dementia by Machine learning methods in Epidemiological studies: a pilot exploratory study from south India.

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.