Machine learning prediction algorithms for 2- , 5- and 10-year risk of Alzheimer's, Parkinson's and dementia at age 65: a study using medical records from France and the UK General Practitioners
Nedelec, T.; Zaidi, K.; Montaud, C.; Guinebretiere, O.; Sipila, P. N.; Wei, D.; Yang, F.; Freydenzon, A.; Belloir, A.; Fournier, N.; hamieh, n.; McRae, A.; Couvy-Duchesne, B.; Hswen, Y.; Fang, F.; Kivimaki, M.; Ansart, M.; Durrleman, S.
Show abstract
Structured abstractO_ST_ABSBackgroundC_ST_ABSLeveraging machine learning on electronic health records offers a promising method for early identification of individuals at risk for dementia and neurodegenerative diseases. Current risk algorithms heavily rely on age, highlighting the need for alternative models with strong predictive power, especially at age 65, a crucial time for early screening and prevention. MethodsThis prospective study analyzed electronic health records (EHR) from 76,427 adults (age 65, 52.1% women) using the THIN database. A general risk algorithm for Alzheimers disease, Parkinsons disease, and dementia was developed using machine learning to select predictors from diagnoses, and medications. ResultsMedications (e.g., laxatives, urological drugs, antidepressants), along with sex, BMI, and comorbidities, were key predictors. The algorithm achieved a 38.4% detection rate at a 5% false-positive rate for 2-year dementia prediction. ConclusionThe validated prediction algorithms, easy to implement in primary care, identify high-risk 65-year-olds using medication records. Further refinement and broader validation are needed.
Matching journals
The top 7 journals account for 50% of the predicted probability mass.
Similar papers in this journal
Similar papers in this journal
- Association between anticholinergic burden and dementia in UK Biobank 97%
- A metabolite-based machine learning approach to diagnose Alzheimer's-type dementia in blood: Results from the European Medical Information Framework for Alzheimer's Disease biomarker discovery cohort 94%
- Reduced dementia incidence following varicella zoster vaccination in Wales 2013–2020 94%
Similar papers in this journal
- Using Machine Learning and Electronic Health Record (EHR) Data for the Early Prediction of Alzheimer’s Disease and Related Dementias 95%
- Potentially Modifiable Dementia Risk Factors in Canada: An Analysis of Canadian Longitudinal Study on Aging with a Multi-Country Comparison 94%
- Real-world datasets for the International Registry for Alzheimer’s Disease and Other Dementias (InRAD) and other registries: an international consensus 94%
Similar papers in this journal
- Self- versus caregiver-reported apathy across neurological disorders 93%
- The PREVENT Dementia programme: Baseline demographic, lifestyle, imaging and cognitive data from a midlife cohort study investigating risk factors for dementia 93%
- Scalable biological-cognitive profiling for Alzheimer's disease in the population 92%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.