Neuropsychological and Clinical Variables Associated with Cognitive Trajectories in Patients with Alzheimer's Disease

Marianna Riello¹Monica Moroni^2*Stefano Bovo²Flavio Ragni²Manuela Buganza¹Raffaella Di Giacopo¹Marco Chierici²Lorenzo Gios³Matteo Pardini^4,5FEDERICO MASSA^4,5Monica Dallabona⁶Elisa Vanzetta⁶Cristina Campi^4,5Michele Piana^4,5Sara Garbarino⁴Manuela Marenco⁴Venet Osmani²Giuseppe Jurman²Antonio Uccelli^4,5Bruno Giometto^1,7

• ¹Neurology Unit, Provincial Health Services of Trento, Trento, Italy, Trento, Italy
• ²Data Science for Health Unit, Fondazione Bruno Kessler, Trento, Italy, Trento, Italy
• ³TrentinoSalute4.0, Trento, Italy, Trento, Italy
• ⁴IRCCS Ospedale Policlinico San Martino, Genoa, Italy, Genova, Italy
• ⁵Department of Neuroscience, Rehabilitation, Ophthalmology, Genetics, Maternal and Child Health (DINOGMI) Universitá di Genova, Genoa, Italy, Genova, Italy
• ⁶Department of Mental Health, Division of Psychology, Provincial Health Services of Trento, Trento, Italy, Trento, Italy
• ⁷University of Trento, Trento, Italy, Trento, Italy

Background: The NeuroArtP3 (NET-2018-12366666) is a multicenter study funded by the Italian Ministry of Health. The aim of the project is to identify the prognostic trajectories of Alzheimer's disease (AD) through the application of artificial intelligence (AI). Only a few AI studies investigated the clinical variables associated with cognitive worsening in AD. We used Mini Mental State Examination (MMSE) scores as outcome to identify factors associated with cognitive decline at follow up. Methods: A sample of 126 patients diagnosed with AD (MMSE >19) were followed during 3 years in 4 time-points: T0 for the baseline and T1, T2 and T3 for the years of follow-ups. Variables of interest included demographics, measures of functional ability, clinical variables, behavioral symptoms, and the equivalent scores (ES) of cognitive tests. Logistic regression, random forest and gradient boosting were applied on baseline data to estimate MMSE scores (decline of at least 3 points) measured at T3. Patients were divided into multiple splits using different model derivation (training) and validation (test) proportions, and the optimization of the models was carried out through cross validation on the derivation subset only. The models' predictive capabilities (balanced accuracy, AUC, AUPCR, F1 score and MCC) were computed on the validation set only. To ensure the robustness of the results, the optimization was repeated 10 times. A SHAP-type analysis was carried out to identify the predictive power of individual variables. The model predicted MMSE outcome at T3 with mean AUC 0.643. Model interpretability analysis revealed that the global cognitive state progression in AD patients is associated with: low spatial memory (Corsi block-tapping), verbal episodic long-term memory (Babcock's story recall) and working memory (Stroop Color) performances, the presence of hypertension, the absence of hypercholesterolemia, and functional skills inabilities at the IADL scores at baseline. This is the first AI study to predict cognitive trajectories of AD patients using routinely collected clinical data, while at the same time providing explainability of factors contributing to these trajectories. The outcomes of this work can aid prognostic interpretation of the clinical and cognitive variables associated with the initial phase of the disease towards personalized therapies.