{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T10:53:44Z","timestamp":1764240824033,"version":"3.41.0"},"reference-count":57,"publisher":"Association for Computing Machinery (ACM)","issue":"2","license":[{"start":{"date-parts":[[2025,4,24]],"date-time":"2025-04-24T00:00:00Z","timestamp":1745452800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"NIA","award":["R01AG066748, R01EB009675, R25AG046114, R01AG065218, and R35AG071451"],"award-info":[{"award-number":["R01AG066748, R01EB009675, R25AG046114, R01AG065218, and R35AG071451"]}]},{"DOI":"10.13039\/100000005","name":"Department of Defense","doi-asserted-by":"crossref","award":["AZ190055"],"award-info":[{"award-number":["AZ190055"]}],"id":[{"id":"10.13039\/100000005","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Comput. Healthcare"],"published-print":{"date-parts":[[2025,4,30]]},"abstract":"<jats:p>\n            Forecasting future health status is beneficial for understanding health patterns and providing anticipatory support for cognitive and physical health difficulties. In recent years, generative Large Language Models (LLMs) have shown promise as forecasters. Though not traditionally considered strong candidates for numeric tasks, LLMs demonstrate emerging abilities to address various forecasting problems. They also provide the ability to incorporate unstructured information and explain their reasoning process. In this article, we explore whether LLMs can effectively forecast future self-reported health state. To do this, we utilized in-the-moment assessments of mental sharpness, fatigue, and stress from multiple studies, utilizing daily responses (\n            <jats:italic>N<\/jats:italic>\n            = 106 participants) and responses that are accompanied by text descriptions of activities (\n            <jats:italic>N<\/jats:italic>\n            = 32 participants). With these data, we constructed prompt\/response pairs to predict a participant\u2019s next answer. We fine-tuned several LLMs and applied chain-of-thought prompting evaluating forecasting accuracy and prediction explainability. Notably, we found that LLMs achieved the lowest Mean Absolute Error (MAE) overall (0.851), while gradient boosting achieved the lowest overall RMSE (1.356). When additional text context was provided, LLM forecasts achieved the lowest MAE for predicting mental sharpness (0.862), fatigue (1.000), and stress (0.414). These multimodal LLMs further outperformed the numeric baselines in terms of RMSE when predicting stress (0.947), although numeric algorithms achieved the best RMSE results for mental sharpness (1.246) and fatigue (1.587). This study offers valuable insights for future applications of LLMs in health-based forecasting. The findings suggest that LLMs, when supplemented with additional text information, can be effective tools for improving health forecasting accuracy.\n          <\/jats:p>","DOI":"10.1145\/3709153","type":"journal-article","created":{"date-parts":[[2024,12,24]],"date-time":"2024-12-24T15:40:07Z","timestamp":1735054807000},"page":"1-25","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["CogProg: Utilizing Large Language Models to Forecast In-the-Moment Health Assessment"],"prefix":"10.1145","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9935-9950","authenticated-orcid":false,"given":"Gina","family":"Sprint","sequence":"first","affiliation":[{"name":"Gonzaga University, Spokane, Washington, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5304-2146","authenticated-orcid":false,"given":"Maureen","family":"Schmitter-Edgecombe","sequence":"additional","affiliation":[{"name":"Washington State University, Pullman, Washington, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7499-8059","authenticated-orcid":false,"given":"Raven","family":"Weaver","sequence":"additional","affiliation":[{"name":"Washington State University, Pullman, Washington, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4830-683X","authenticated-orcid":false,"given":"Lisa","family":"Wiese","sequence":"additional","affiliation":[{"name":"Florida Atlantic University, Boca Raton, Florida, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4441-7508","authenticated-orcid":false,"given":"Diane J.","family":"Cook","sequence":"additional","affiliation":[{"name":"Washington State University, Pullman, Washington, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,4,24]]},"reference":[{"unstructured":"Alzheimer\u2019s Association. 2024. 2024 Alzheimer\u2019s Disease Facts and Figures. Retrieved July 25 2024 from https:\/\/www.alz.org\/media\/Documents\/alzheimers-facts-and-figures.pdf","key":"e_1_3_3_2_2"},{"doi-asserted-by":"publisher","unstructured":"Abhinand Balachandran. 2023. Tamil-Llama: A new Tamil language model based on Llama 2. DOI: 10.48550\/arXiv.2311.05845","key":"e_1_3_3_3_2","DOI":"10.48550\/arXiv.2311.05845"},{"doi-asserted-by":"publisher","unstructured":"Defu Cao Furong Jia Sercan O. Arik Tomas Pfister Yixiang Zheng Wen Ye and Yan Liu. 2023. TEMPO: Prompt-based generative pre-trained transformer for time series forecasting. DOI: 10.48550\/arXiv.2310.04948","key":"e_1_3_3_4_2","DOI":"10.48550\/arXiv.2310.04948"},{"doi-asserted-by":"publisher","key":"e_1_3_3_5_2","DOI":"10.5664\/jcsm.9708"},{"doi-asserted-by":"publisher","key":"e_1_3_3_6_2","DOI":"10.3390\/s23229225"},{"doi-asserted-by":"publisher","key":"e_1_3_3_7_2","DOI":"10.1097\/01.wad.0000213849.51495.d9"},{"key":"e_1_3_3_8_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/JTEHM.2020.3014564","article-title":"Wearable device-independent next day activity and next night sleep prediction for rehabilitation populations","volume":"8","author":"Fellger A.","year":"2020","unstructured":"A. Fellger, D. Weeks, E. Crooks, G. Sprint, and D. Cook. 2020. Wearable device-independent next day activity and next night sleep prediction for rehabilitation populations. IEEE J. Transl. Eng. Health Med. 8 (2020), 1\u20139.","journal-title":"IEEE J. Transl. Eng. Health Med"},{"key":"e_1_3_3_9_2","doi-asserted-by":"crossref","first-page":"642044","DOI":"10.3389\/fpsyg.2021.642044","article-title":"A systematic review of momentary assessment designs for mood and anxiety symptoms","volume":"12","author":"Hall Mila","year":"2021","unstructured":"Mila Hall, Paloma V. Scherner, Yannic Kreidel, and Julian A. Rubel. 2021. A systematic review of momentary assessment designs for mood and anxiety symptoms. Front. Psychol. 12 (2021), 642044. Retrieved December 13, 2023 from https:\/\/www.frontiersin.org\/articles\/10.3389\/fpsyg.2021.642044","journal-title":"Front. Psychol"},{"doi-asserted-by":"publisher","unstructured":"Edward J. Hu Yelong Shen Phillip Wallis Zeyuan Allen-Zhu Yuanzhi Li Shean Wang Lu Wang and Weizhu Chen. 2021. LoRA: Low-rank adaptation of large language models. DOI: 10.48550\/arXiv.2106.09685","key":"e_1_3_3_10_2","DOI":"10.48550\/arXiv.2106.09685"},{"doi-asserted-by":"publisher","key":"e_1_3_3_11_2","DOI":"10.2196\/39425"},{"doi-asserted-by":"publisher","key":"e_1_3_3_12_2","DOI":"10.1038\/s41586-023-06160-y"},{"doi-asserted-by":"publisher","unstructured":"Ming Jin Shiyu Wang Lintao Ma Zhixuan Chu James Y. Zhang Xiaoming Shi Pin-Yu Chen Yuxuan Liang Yuan-Fang Li Shirui Pan et al. 2023. Time-LLM: Time series forecasting by reprogramming large language models. DOI: 10.48550\/arXiv.2310.01728","key":"e_1_3_3_13_2","DOI":"10.48550\/arXiv.2310.01728"},{"doi-asserted-by":"publisher","unstructured":"Ming Jin Qingsong Wen Yuxuan Liang Chaoli Zhang Siqiao Xue Xue Wang James Zhang Yi Wang Haifeng Chen Xiaoli Li et al. 2023. Large models for time series and spatio-temporal data: A survey and outlook. DOI: 10.48550\/arXiv.2310.10196","key":"e_1_3_3_14_2","DOI":"10.48550\/arXiv.2310.10196"},{"unstructured":"Y. Kim X. Xu D. McDuff C. Brezeale and Hae Won Park. 2024. Health-LLM: Large language models for health prediction via wearable sensor data. arXiv:2401.06866. Retrieved from https:\/\/arxiv.org\/abs\/2401.06866","key":"e_1_3_3_15_2"},{"doi-asserted-by":"publisher","unstructured":"Takeshi Kojima Shixiang Shane Gu Machel Reid Yutaka Matsuo and Yusuke Iwasawa. 2023. Large language models are zero-shot reasoners. DOI: 10.48550\/arXiv.2205.11916","key":"e_1_3_3_16_2","DOI":"10.48550\/arXiv.2205.11916"},{"doi-asserted-by":"publisher","key":"e_1_3_3_17_2","DOI":"10.1002\/brb3.2898"},{"doi-asserted-by":"publisher","unstructured":"Mike Lewis Yinhan Liu Naman Goyal Marjan Ghazvininejad Abdelrahman Mohamed Omer Levy Ves Stoyanov and Luke Zettlemoyer. 2019. BART: Denoising sequence-to-sequence pre-training for natural language generation translation and comprehension. DOI: 10.48550\/arXiv.1910.13461","key":"e_1_3_3_18_2","DOI":"10.48550\/arXiv.1910.13461"},{"key":"e_1_3_3_19_2","first-page":"9459","volume-title":"Advances in Neural Information Processing Systems","author":"Lewis Patrick","year":"2020","unstructured":"Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich K\u00fcttler, Mike Lewis, Wen-tau Yih, Tim Rockt\u00e4schel, et al. 2020. Retrieval-augmented generation for knowledge-intensive NLP tasks. In Advances in Neural Information Processing Systems. Curran Associates, Inc., 9459\u20139474. Retrieved December 6, 2023, from https:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/6b493230205f780e1bc26945df7481e5-Abstract.html"},{"key":"e_1_3_3_20_2","article-title":"Artificial intelligence for health message generation: An empirical study using a large language model (LLM) and","volume":"8","author":"Lim Sue","year":"2023","unstructured":"Sue Lim and Ralf Schm\u00e4lzle. 2023. Artificial intelligence for health message generation: An empirical study using a large language model (LLM) and prompt engineering. Front. Commun. 8 (2023). Retrieved December 13, 2023 from https:\/\/www.frontiersin.org\/journals\/communication\/articles\/10.3389\/fcomm.2023.1129082\/full.","journal-title":"Front. Commun"},{"key":"e_1_3_3_21_2","first-page":"1950","article-title":"Few-shot parameter-efficient fine-tuning is better and cheaper than in-context learning","volume":"35","author":"Liu Haokun","year":"2022","unstructured":"Haokun Liu, Derek Tam, Mohammed Muqeeth, Jay Mohta, Tenghao Huang, Mohit Bansal, and Colin A. Raffel. 2022. Few-shot parameter-efficient fine-tuning is better and cheaper than in-context learning. Adv. Neural Inf. Process. Syst. 35 (2022), 1950\u20131965.","journal-title":"Adv. Neural Inf. Process. Syst"},{"doi-asserted-by":"publisher","key":"e_1_3_3_22_2","DOI":"10.18653\/v1\/2022.acl-long.225"},{"doi-asserted-by":"publisher","key":"e_1_3_3_23_2","DOI":"10.1007\/978-3-031-45673-2_46"},{"doi-asserted-by":"publisher","key":"e_1_3_3_24_2","DOI":"10.1038\/s41587-022-01618-2"},{"doi-asserted-by":"publisher","key":"e_1_3_3_25_2","DOI":"10.1109\/ICCTIDE.2016.7725358"},{"doi-asserted-by":"publisher","key":"e_1_3_3_26_2","DOI":"10.2196\/34662"},{"doi-asserted-by":"publisher","key":"e_1_3_3_27_2","DOI":"10.2196\/50638"},{"doi-asserted-by":"publisher","key":"e_1_3_3_28_2","DOI":"10.1016\/j.jpsychores.2008.07.005"},{"doi-asserted-by":"publisher","key":"e_1_3_3_29_2","DOI":"10.1371\/journal.pone.0266552"},{"doi-asserted-by":"publisher","unstructured":"Thanh Thi Nguyen Campbell Wilson and Janis Dalins. 2023. Fine-tuning Llama 2 large language models for detecting online sexual predatory chats and abusive texts. DOI: 10.48550\/arXiv.2308.14683","key":"e_1_3_3_30_2","DOI":"10.48550\/arXiv.2308.14683"},{"doi-asserted-by":"publisher","key":"e_1_3_3_31_2","DOI":"10.1001\/jama.2019.22258"},{"doi-asserted-by":"publisher","unstructured":"Bohdan M. Pavlyshenko. 2023. Financial news analytics using fine-tuned Llama 2 GPT model. DOI: 10.48550\/arXiv.2308.13032","key":"e_1_3_3_32_2","DOI":"10.48550\/arXiv.2308.13032"},{"doi-asserted-by":"publisher","key":"e_1_3_3_33_2","DOI":"10.1111\/add.15687"},{"unstructured":"PUCV. 2023. Use of LLaMA 2 7B for Fine-Tuning of Circuit Theory 1 Course. Retrieved November 21 2023 from https:\/\/openreview.net\/forum?id=RaUJHystW1","key":"e_1_3_3_34_2"},{"doi-asserted-by":"publisher","key":"e_1_3_3_35_2","DOI":"10.1080\/08870446.2020.1781122"},{"doi-asserted-by":"publisher","key":"e_1_3_3_36_2","DOI":"10.1037\/neu0000867"},{"doi-asserted-by":"publisher","key":"e_1_3_3_37_2","DOI":"10.1038\/s41586-023-06291-2"},{"doi-asserted-by":"publisher","unstructured":"Chenxi Sun Yaliang Li Hongyan Li and Shenda Hong. 2023. TEST: Text prototype aligned embedding to activate LLM\u2019s ability for time series. DOI: 10.48550\/arXiv.2308.08241","key":"e_1_3_3_38_2","DOI":"10.48550\/arXiv.2308.08241"},{"doi-asserted-by":"publisher","unstructured":"Jiashuo Sun Yi Luo Yeyun Gong Chen Lin Yelong Shen Jian Guo and Nan Duan. 2023. Enhancing chain-of-thoughts prompting with iterative bootstrapping in large language models. DOI: 10.48550\/arXiv.2304.11657","key":"e_1_3_3_39_2","DOI":"10.48550\/arXiv.2304.11657"},{"doi-asserted-by":"publisher","key":"e_1_3_3_40_2","DOI":"10.1089\/big.2020.0159"},{"doi-asserted-by":"publisher","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale et al. 2023. Llama 2: Open foundation and fine-tuned chat models. DOI: 10.48550\/arXiv.2307.09288","key":"e_1_3_3_41_2","DOI":"10.48550\/arXiv.2307.09288"},{"doi-asserted-by":"publisher","key":"e_1_3_3_42_2","DOI":"10.1097\/YCO.0000000000000267"},{"doi-asserted-by":"publisher","unstructured":"Xuezhi Wang Jason Wei Dale Schuurmans Quoc Le Ed Chi Sharan Narang Aakanksha Chowdhery and Denny Zhou. 2023. Self-consistency improves chain of thought reasoning in language models. DOI: 10.48550\/arXiv.2203.11171","key":"e_1_3_3_43_2","DOI":"10.48550\/arXiv.2203.11171"},{"doi-asserted-by":"publisher","unstructured":"Jason Wei Xuezhi Wang Dale Schuurmans Maarten Bosma Brian Ichter Fei Xia Ed Chi Quoc Le and Denny Zhou. 2023. Chain-of-thought prompting elicits reasoning in large language models. DOI: 10.48550\/arXiv.2201.11903","key":"e_1_3_3_44_2","DOI":"10.48550\/arXiv.2201.11903"},{"doi-asserted-by":"publisher","unstructured":"Qingsong Wen Tian Zhou Chaoli Zhang Weiqi Chen Ziqing Ma Junchi Yan and Liang Sun. 2023. Transformers in time series: A survey. DOI: 10.48550\/arXiv.2202.07125","key":"e_1_3_3_45_2","DOI":"10.48550\/arXiv.2202.07125"},{"doi-asserted-by":"publisher","unstructured":"Haixu Wu Tengge Hu Yong Liu Hang Zhou Jianmin Wang and Mingsheng Long. 2023. TimesNet: Temporal 2D-variation modeling for general time series analysis. DOI: 10.48550\/arXiv.2210.02186","key":"e_1_3_3_46_2","DOI":"10.48550\/arXiv.2210.02186"},{"doi-asserted-by":"publisher","unstructured":"Haixu Wu Jiehui Xu Jianmin Wang and Mingsheng Long. 2022. Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting. DOI: 10.48550\/arXiv.2106.13008","key":"e_1_3_3_47_2","DOI":"10.48550\/arXiv.2106.13008"},{"unstructured":"Hao Xue Flora and D. Salim. 2022. PromptCast: A New Prompt-Based Learning Paradigm for Time Series Forecasting. Retrieved October 30 2023 from https:\/\/arxiv.org\/abs\/2210.08964v4","key":"e_1_3_3_48_2"},{"doi-asserted-by":"publisher","key":"e_1_3_3_49_2","DOI":"10.1145\/3488560.3498387"},{"doi-asserted-by":"publisher","key":"e_1_3_3_50_2","DOI":"10.1016\/j.smhl.2024.100464"},{"doi-asserted-by":"publisher","unstructured":"Shunyu Yao Dian Yu Jeffrey Zhao Izhak Shafran Thomas L. Griffiths Yuan Cao and Karthik Narasimhan. 2023. Tree of thoughts: Deliberate problem solving with large language models. DOI: 10.48550\/arXiv.2305.10601","key":"e_1_3_3_51_2","DOI":"10.48550\/arXiv.2305.10601"},{"doi-asserted-by":"publisher","unstructured":"Zihan Yu Liang He Zhen Wu Xinyu Dai and Jiajun Chen. 2023. Towards better chain-of-thought prompting strategies: A survey. DOI: 10.48550\/arXiv.2310.04959","key":"e_1_3_3_52_2","DOI":"10.48550\/arXiv.2310.04959"},{"key":"e_1_3_3_53_2","first-page":"17283","volume-title":"Advances in Neural Information Processing Systems","author":"Zaheer Manzil","year":"2020","unstructured":"Manzil Zaheer, Guru Guruganesh, Kumar Avinava Dubey, Joshua Ainslie, Chris Alberti, Santiago Ontanon, Philip Pham, Anirudh Ravula, Qifan Wang, Li Yang, et al. 2020. Big bird: Transformers for longer sequences. In Advances in Neural Information Processing Systems. Curran Associates, Inc., 17283\u201317297. Retrieved December 20, 2023 from https:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/c8512d142a2d849725f31a9a7a361ab9-Abstract.html"},{"key":"e_1_3_3_54_2","first-page":"11328","volume-title":"37th International Conference on Machine Learning","author":"Zhang Jingqing","year":"2020","unstructured":"Jingqing Zhang, Yao Zhao, Mohammad Saleh, and Peter Liu. 2020. PEGASUS: Pre-training with extracted gap-sentences for abstractive summarization. In 37th International Conference on Machine Learning. PMLR, 11328\u201311339. Retrieved December 20, 2023 from https:\/\/proceedings.mlr.press\/v119\/zhang20ae.html"},{"doi-asserted-by":"publisher","unstructured":"Denny Zhou Nathanael Sch\u00e4rli Le Hou Jason Wei Nathan Scales Xuezhi Wang Dale Schuurmans Claire Cui Olivier Bousquet Quoc Le et al. 2023. Least-to-most prompting enables complex reasoning in large language models. DOI: 10.48550\/arXiv.2205.10625","key":"e_1_3_3_55_2","DOI":"10.48550\/arXiv.2205.10625"},{"doi-asserted-by":"publisher","unstructured":"Haoyi Zhou Shanghang Zhang Jieqi Peng Shuai Zhang Jianxin Li Hui Xiong and Wancai Zhang. 2021. Informer: Beyond efficient transformer for long sequence time-series forecasting. DOI: 10.48550\/arXiv.2012.07436","key":"e_1_3_3_56_2","DOI":"10.48550\/arXiv.2012.07436"},{"doi-asserted-by":"publisher","unstructured":"Tian Zhou Ziqing Ma Qingsong Wen Xue Wang Liang Sun and Rong Jin. 2022. FEDformer: Frequency enhanced decomposed transformer for long-term series forecasting. DOI: 10.48550\/arXiv.2201.12740","key":"e_1_3_3_57_2","DOI":"10.48550\/arXiv.2201.12740"},{"doi-asserted-by":"publisher","unstructured":"Yuchen Zhuang Yue Yu Kuan Wang Haotian Sun and Chao Zhang. 2023. ToolQA: A dataset for LLM question answering with external tools. DOI: 10.48550\/arXiv.2306.13304","key":"e_1_3_3_58_2","DOI":"10.48550\/arXiv.2306.13304"}],"container-title":["ACM Transactions on Computing for Healthcare"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3709153","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3709153","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:31Z","timestamp":1750295851000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3709153"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,24]]},"references-count":57,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,4,30]]}},"alternative-id":["10.1145\/3709153"],"URL":"https:\/\/doi.org\/10.1145\/3709153","relation":{},"ISSN":["2637-8051"],"issn-type":[{"type":"electronic","value":"2637-8051"}],"subject":[],"published":{"date-parts":[[2025,4,24]]},"assertion":[{"value":"2024-01-16","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-12-09","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-04-24","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}