Predicting Alcohol-Related Memory Problems in Older Adults: A Machine Learning Study with Multi-Domain Features

Chella Kamarajan, Ashwini K. Pandey, David B. Chorlian, Jacquelyn L. Meyers, Sivan Kinreich, Gayathri Pandey, Stacey Subbie-Saenz de Viteri, Jian Zhang, Weipeng Kuang, Peter B. Barr, Fazil Aliev, Andrey P. Anokhin, Martin H. Plawecki, Samuel Kuperman, Laura Almasy, Alison Merikangas, Sarah J. Brislin, Lance Bauer, Victor Hesselbrock, Grace ChanJohn Kramer, Dongbing Lai, Sarah Hartz, Laura J. Bierut, Vivia V. McCutcheon, Kathleen K. Bucholz, Danielle M. Dick, Marc A. Schuckit, Howard J. Edenberg, Bernice Porjesz

Research output: Contribution to journalArticlepeer-review


Memory problems are common among older adults with a history of alcohol use disorder (AUD). Employing a machine learning framework, the current study investigates the use of multi-domain features to classify individuals with and without alcohol-induced memory problems. A group of 94 individuals (ages 50–81 years) with alcohol-induced memory problems (the memory group) were compared with a matched control group who did not have memory problems. The random forests model identified specific features from each domain that contributed to the classification of the memory group vs. the control group (AUC = 88.29%). Specifically, individuals from the memory group manifested a predominant pattern of hyperconnectivity across the default mode network regions except for some connections involving the anterior cingulate cortex, which were predominantly hypoconnected. Other significant contributing features were: (i) polygenic risk scores for AUD, (ii) alcohol consumption and related health consequences during the past five years, such as health problems, past negative experiences, withdrawal symptoms, and the largest number of drinks in a day during the past twelve months, and (iii) elevated neuroticism and increased harm avoidance, and fewer positive “uplift” life events. At the neural systems level, hyperconnectivity across the default mode network regions, including the connections across the hippocampal hub regions, in individuals with memory problems may indicate dysregulation in neural information processing. Overall, the study outlines the importance of utilizing multidomain features, consisting of resting-state brain connectivity data collected ~18 years ago, together with personality, life experiences, polygenic risk, and alcohol consumption and related consequences, to predict the alcohol-related memory problems that arise in later life.

Original languageEnglish
Article number427
JournalBehavioral Sciences
Issue number5
StatePublished - May 2023


  • EEG source functional connectivity
  • alcohol use disorder (AUD)
  • alcohol-related memory problems
  • default mode network
  • random forests


Dive into the research topics of 'Predicting Alcohol-Related Memory Problems in Older Adults: A Machine Learning Study with Multi-Domain Features'. Together they form a unique fingerprint.

Cite this