{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"medRxiv"}],"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T20:28:32Z","timestamp":1773865712411,"version":"3.50.1"},"posted":{"date-parts":[[2026,3,16]]},"group-title":"Health Informatics","reference-count":30,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T00:00:00Z","timestamp":1773619200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,3,16]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:p>The digital clock drawing test (dCDT) is a cognitive screening tool employing a digital pen. While many studies rely on summary statistics of dCDT features to predict cognitive outcomes, these approaches often involve subjective decisions such as feature selection and imputation. In this study, we introduce novel dCDT features, expressed as mathematical functions, and compare them to commonly used summary features. We included dCDTs from 3,415 participants from the Framingham Heart Study. Random forest models with five-fold cross-validation were trained to distinguish participants with mild cognitive impairment or dementia from cognitively intact participants. When combined with established time-based features, functional features related to spatial proximity and circularity demonstrated predictive power comparable to commonly used summary features. Our findings highlight the potential of integrating functional features to detect subtle motions and behaviors in digital cognitive assessments, offering new tools that may enhance diagnostic accuracy and support early detection strategies.<\/jats:p>","DOI":"10.64898\/2026.03.14.26348336","type":"posted-content","created":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T23:45:12Z","timestamp":1773704712000},"source":"Crossref","is-referenced-by-count":0,"title":["Predicting cognitive impairment using novel functional features of spatial proximity and circularity in the digital clock drawing test"],"prefix":"10.64898","author":[{"given":"Adlin","family":"Pinheiro","sequence":"first","affiliation":[{"name":"Department of Biostatistics, Boston University School of Public Health, Boston, MA, United States"},{"name":"Framingham Heart Study, Boston University Chobanian & Avedisian School of Medicine, Boston, MA, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cody","family":"Karjadi","sequence":"additional","affiliation":[{"name":"Framingham Heart Study, Boston University Chobanian & Avedisian School of Medicine, Boston, MA, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yorghos","family":"Tripodis","sequence":"additional","affiliation":[{"name":"Department of Biostatistics, Boston University School of Public Health, Boston, MA, United States"},{"name":"Alzheimer\u2019s Disease Research and Chronic Traumatic Encephalopathy Centers, Boston University, Boston, MA, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5312-8644","authenticated-orcid":false,"given":"Vijaya B.","family":"Kolachalama","sequence":"additional","affiliation":[{"name":"Department of Medicine, Boston University Chobanian & Avedisian School of Medicine, Boston, MA, United States"},{"name":"Department of Computer Science, Boston University, Boston, MA, United States"},{"name":"Faculty of Computing & Data Sciences, Boston University, Boston, MA, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kathryn","family":"Lunetta","sequence":"additional","affiliation":[{"name":"Department of Biostatistics, Boston University School of Public Health, Boston, MA, United States"},{"name":"Framingham Heart Study, Boston University Chobanian & Avedisian School of Medicine, Boston, MA, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Serkalem","family":"Demissie","sequence":"additional","affiliation":[{"name":"Department of Biostatistics, Boston University School of Public Health, Boston, MA, United States"},{"name":"Framingham Heart Study, Boston University Chobanian & Avedisian School of Medicine, Boston, MA, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunyu","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Biostatistics, Boston University School of Public Health, Boston, MA, United States"},{"name":"Framingham Heart Study, Boston University Chobanian & Avedisian School of Medicine, Boston, MA, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rhoda","family":"Au","sequence":"additional","affiliation":[{"name":"Framingham Heart Study, Boston University Chobanian & Avedisian School of Medicine, Boston, MA, United States"},{"name":"Alzheimer\u2019s Disease Research and Chronic Traumatic Encephalopathy Centers, Boston University, Boston, MA, United States"},{"name":"Department of Medicine, Boston University Chobanian & Avedisian School of Medicine, Boston, MA, United States"},{"name":"Department of Neurology, Boston University Chobanian & Avedisian School of Medicine, Boston, MA, United States"},{"name":"Department of Anatomy & Neurobiology, Boston University Chobanian & Avedisian School of Medicine, Boston, MA, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3107-2969","authenticated-orcid":false,"given":"Shariq","family":"Mohammed","sequence":"additional","affiliation":[{"name":"Department of Biostatistics, Boston University School of Public Health, Boston, MA, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"54368","reference":[{"key":"2026031806001204000_2026.03.14.26348336v1.1","doi-asserted-by":"publisher","DOI":"10.1002\/1099-1166(200006)15:6<548::AID-GPS242>3.0.CO;2-U"},{"key":"2026031806001204000_2026.03.14.26348336v1.2","doi-asserted-by":"publisher","DOI":"10.1159\/000203344"},{"key":"2026031806001204000_2026.03.14.26348336v1.3","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1099-1166(199706)12:6<619::AID-GPS554>3.0.CO;2-H"},{"key":"2026031806001204000_2026.03.14.26348336v1.4","doi-asserted-by":"publisher","DOI":"10.1212\/WNL.59.6.898"},{"key":"2026031806001204000_2026.03.14.26348336v1.5","doi-asserted-by":"publisher","DOI":"10.1002\/gps.747"},{"key":"2026031806001204000_2026.03.14.26348336v1.6","doi-asserted-by":"publisher","DOI":"10.1176\/appi.neuropsych.22.1.85"},{"key":"2026031806001204000_2026.03.14.26348336v1.7","doi-asserted-by":"crossref","first-page":"1649","DOI":"10.1017\/S1041610215000939","article-title":"Can clock drawing differentiate Alzheimer\u2019s disease from other dementias?","volume":"27","year":"2015","journal-title":"Int. Psychogeriatr"},{"key":"2026031806001204000_2026.03.14.26348336v1.8","doi-asserted-by":"crossref","unstructured":"Souillard-Mandar W et al. DCTclock: Clinically-interpretable and automated artificial intelligence analysis of drawing behavior for capturing cognition. Front. Digit. Health 2021;3:750661.","DOI":"10.3389\/fdgth.2021.750661"},{"key":"2026031806001204000_2026.03.14.26348336v1.9","doi-asserted-by":"crossref","unstructured":"Davis R , Libon DJ , Au R , Pitman D , and Penney DL . THink: Inferring cognitive status from subtle behaviors. Proc. AAAI Conf. Artif. Intell. 2014:2898\u2013905.","DOI":"10.1609\/aaai.v28i2.19017"},{"key":"2026031806001204000_2026.03.14.26348336v1.10","doi-asserted-by":"publisher","DOI":"10.2196\/34513"},{"key":"2026031806001204000_2026.03.14.26348336v1.11","doi-asserted-by":"crossref","unstructured":"M\u00fcller S , Preische O , Heymann P , Elbing U , and Laske C. Increased diagnostic accuracy of digital vs. conventional clock drawing test for discrimination of patients in the early course of Alzheimer\u2019s disease from cognitively healthy individuals. Front. Aging Neurosci. 2017;9:101.","DOI":"10.3389\/fnagi.2017.00101"},{"key":"2026031806001204000_2026.03.14.26348336v1.12","doi-asserted-by":"crossref","first-page":"3543","DOI":"10.1038\/s41598-019-40010-0","article-title":"Diagnostic value of digital clock drawing test in comparison with CERAD neuropsychological battery total score for discrimination of patients in the early course of Alzheimer\u2019s disease from healthy individuals","volume":"9","year":"2019","journal-title":"Scientific Reports"},{"key":"2026031806001204000_2026.03.14.26348336v1.13","doi-asserted-by":"crossref","first-page":"690","DOI":"10.1017\/S1355617720000144","article-title":"Machine learning analysis of digital clock drawing test performance for differential classification of mild cognitive impairment subtypes versus Alzheimer\u2019s disease","volume":"26","year":"2020","journal-title":"J. Int. Neuropsychol. Soc"},{"key":"2026031806001204000_2026.03.14.26348336v1.14","doi-asserted-by":"crossref","first-page":"47","DOI":"10.3233\/JAD-201129","article-title":"Classifying non-dementia and Alzheimer\u2019s disease\/vascular dementia patients using kinematic, time-based, and visuospatial parameters: the digital clock drawing test","volume":"82","year":"2021","journal-title":"J. Alzheimers Dis"},{"key":"2026031806001204000_2026.03.14.26348336v1.15","doi-asserted-by":"crossref","first-page":"581","DOI":"10.3233\/JAD-210299","article-title":"An artificial intelligence-assisted method for dementia detection using images from the clock drawing test","volume":"83","year":"2021","journal-title":"J. Alzheimers Dis"},{"key":"2026031806001204000_2026.03.14.26348336v1.16","doi-asserted-by":"publisher","DOI":"10.1212\/WNL.0000000000011697"},{"key":"2026031806001204000_2026.03.14.26348336v1.17","doi-asserted-by":"crossref","first-page":"7384","DOI":"10.1038\/s41598-023-34518-9","article-title":"Explainable semi-supervised deep learning shows that dementia is associated with small, avocado-shaped clocks with irregularly placed hands","volume":"13","year":"2023","journal-title":"Scientific Reports"},{"key":"2026031806001204000_2026.03.14.26348336v1.18","doi-asserted-by":"crossref","first-page":"73","DOI":"10.3233\/JAD-191089","article-title":"Cognitive correlates of digital clock drawing metrics in older adults with and without mild cognitive impairment","volume":"75","year":"2020","journal-title":"J. Alzheimers Dis"},{"key":"2026031806001204000_2026.03.14.26348336v1.19","first-page":"567","volume-title":"XIII Mediterranean Conference on Medical and Biological Engineering and Computing","volume":"41","year":"2014"},{"key":"2026031806001204000_2026.03.14.26348336v1.20","doi-asserted-by":"publisher","DOI":"10.1198\/016214504000001745"},{"key":"2026031806001204000_2026.03.14.26348336v1.21","doi-asserted-by":"crossref","first-page":"687","DOI":"10.1038\/s41569-019-0202-5","article-title":"70-year legacy of the Framingham Heart Study","volume":"16","year":"2019","journal-title":"Nature Reviews Cardiology"},{"key":"2026031806001204000_2026.03.14.26348336v1.22","unstructured":"American Psychiatric Association. Diagnostic and Statistical Manual of Mental Disorders: DSM-IV. 4th. American Psychiatric Association, Washington, DC, 1994."},{"key":"2026031806001204000_2026.03.14.26348336v1.23","doi-asserted-by":"crossref","first-page":"807","DOI":"10.3233\/JAD-200786","article-title":"Severity distribution of Alzheimer\u2019s disease dementia and mild cognitive impairment in the Framingham Heart Study","volume":"79","year":"2021","journal-title":"J. Alzheimers Dis"},{"key":"2026031806001204000_2026.03.14.26348336v1.24","doi-asserted-by":"crossref","unstructured":"Ramsay JO and Silverman BW. Functional Data Analysis. Springer Series in Statistics. Springer, 2005.","DOI":"10.1007\/b98888"},{"key":"2026031806001204000_2026.03.14.26348336v1.25","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-013-0679-x"},{"key":"2026031806001204000_2026.03.14.26348336v1.26","doi-asserted-by":"crossref","unstructured":"Wickham H. ggplot2: Elegant Graphics for Data Analysis. Springer-Verlag New York, 2016.","DOI":"10.1007\/978-3-319-24277-4_9"},{"key":"2026031806001204000_2026.03.14.26348336v1.27","doi-asserted-by":"crossref","unstructured":"Xu S et al. Use ggbreak to effectively utilize plotting space to deal with large datasets and outliers. Front. Genet. 2021;12:774846.","DOI":"10.3389\/fgene.2021.774846"},{"key":"2026031806001204000_2026.03.14.26348336v1.28","unstructured":"Kassambara A. ggpubr: \u2018ggplot2\u2019 Based Publication Ready Plots. R package version 0.6.0. 2023."},{"key":"2026031806001204000_2026.03.14.26348336v1.29","doi-asserted-by":"crossref","first-page":"e43","DOI":"10.1002\/imt2.43","article-title":"Complex heatmap visualization","volume":"1","year":"2022","journal-title":"Imeta"},{"key":"2026031806001204000_2026.03.14.26348336v1.30","doi-asserted-by":"crossref","first-page":"59","DOI":"10.3233\/JAD-201249","article-title":"Normative references for graphomotor and latency digital clock drawing metrics for adults age 55 and older: operationalizing the production of a normal appearing clock","volume":"82","year":"2021","journal-title":"J. Alzheimers Dis"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.64898\/2026.03.14.26348336","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T13:00:33Z","timestamp":1773838833000},"score":1,"resource":{"primary":{"URL":"http:\/\/medrxiv.org\/lookup\/doi\/10.64898\/2026.03.14.26348336"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,16]]},"references-count":30,"URL":"https:\/\/doi.org\/10.64898\/2026.03.14.26348336","relation":{},"subject":[],"published":{"date-parts":[[2026,3,16]]},"subtype":"preprint"}}