Background: As the society ages, the number of patients with early cognitive impairment that can progress to Alzheimer’s disease also increases. Early diagnosis and risk as-sessment allows effectively initiate the necessary lifestyle changes and monitoring. The use of artificial intelligence (AI), when analyzing medical histories, enables more pro-ductive evaluation of large datasets and identify patterns that may go unnoticed in clinical practice. This kind of approach can improve early screening, reduce physicians’ workload and develop bigger support for personalized treatment. The aim of the study: To compare the performance of machine learning (ML) algorithm with a physician (neurologist) in assessing patient’s subjective cognitive decline and Alz-heimer’s disease risk in early stages. Research methods: The research was designed as a retrospective, comparative cohort study that used two data sources. Firstly, the National Alzheimer’s Coordination Center (NACC) longitudinal dataset to train the ML model. Secondly, medical records gathered from Pauls Stradins Clinical University Hospital dating from 2020 till May 2025 to evaluate the al-gorithm’s precision. Results: The research included 154 patients, predominantly women (68.8%), with a mean age of 80.3 years. Class distribution consisted of dementia (n=139); mild cognitive im-pairment (MCI) (n=13); subjective cognitive decline (SCD) (n=2). Dementia was identified the best – 128/139 (accuracy – 92.1%) with errors tending towards MCI. MCI was correct in 9/13 cases (accuracy – 69.2%) All SCD cases were classified as dementia. Overall model’s accuracy was 91.6% (141/154). Conclusions: ML algorithm can match to neurologist made diagnoses with high precision but is struggles to separate adjacent early-stage diagnoses. At this moment, ML models are great decision supporters, but no yet alone diagnosticians. Nevertheless, this technology has high potential to being integrated in the future to aid triage and early screening, especially when advanced diagnostics are limited.

Background and Objectives: As society ages, the number of patients with cognitive impairment is increasing. Machine learning methods that use structured clinical and cognitive-assessment data during routine diagnostic work-up may support and monitor structured classifications of cognitive status. This kind of approach can improve early screening, reduce physicians’ workload and develop greater support for personalized treatment. To develop an XGBoost-based machine learning model using the National Alzheimer’s Coordinating Center (NACC) dataset and to evaluate the model’s precision with clinician-assigned diagnosis in a Latvian retrospective cohort study. Materials and Methods: The research was designed as a retrospective external validation cohort study that used two data sources. Firstly, the National Alzheimer’s Coordination Center (NACC) longitudinal dataset was used to train the ML model. Secondly, medical records gathered from Pauls Stradins Clinical University Hospital dating from 2020 to May 2025 were used to evaluate the algorithm’s precision. Results: In the NACC study, the weighted four-class model achieved an overall accuracy of 84.0% and a balanced accuracy of 70.9%, but the SCD class remained poorly classified. After reframing the model to a three-class model the performance grew stronger for normal cognition, mild cognitive impairment (MCI) and dementia. Class distribution in the Latvian cohort consisted of dementia (n = 138); MCI (n = 13); and subjective cognitive decline (SCD) (n = 2). Dementia was identified most strongly—124/138 (sensitivity—89.9%). MCI was correct in 9/13 cases (sensitivity—69.2%). SCD cases were excluded. Overall, the model agreed with the neurologist-assigned diagnoses in 88.1% of the cases (133/151). Conclusions: The ML classification model has high precision when comparing with neurologist-assigned diagnoses, but it struggles to separate adjacent early-stage diagnoses, meaning that it did not reliably identify SCD. These findings support further methodological development and the implementation of prospective research. Nevertheless, this technology has high potential for being integrated in the future to aid triage and early screening, especially when advanced diagnostics are limited.