隨著年齡增長，跌倒風險顯著增加，跌倒事件可能引發多處外傷甚至造成生命危險，進一步影響生活品質及增加家庭負擔，因此針對此議題，一套準確的跌倒偵測及預測系統具有開發之必要。本論文將分為三個部份探討多模態資料應用在跌倒偵測與預測上的成果與技術突破。本論文第一部分設計一套鞋型跌倒偵測系統，此系統安裝飛時測距感測器，因此在運作過程可以藉由感測器測距之功能及時檢測步態周期的變化及地形幾何特徵，成果證明此系統可以將在不同地形上執行的 17 項實驗動作進行跌倒風險的分類，並在跌倒偵測的F1分數辨識成果中達到99.07%，證明系統的可行性與準確性。本論文第二部分提出一結合飛時測距感測器和慣性測量單元的跌倒預測穿戴式系統，此系統深度學習之模型設計出一雙任務學習架構，讓系統能同時辨識三種跌倒風險等級和四種地形，其中預測跌倒的準確率達到 97.7%，能於平均329 毫秒之前偵測到跌倒動作，顯示出本系統的準確性。本論文第三部分提出一套用於跌倒風險評估並產出照護建議之案例式推理架構，此架構能搜索出與個案排名前 N 相似的案例，並當作參考輸入至大型語言模型，以進行跌倒風險的評估，結果顯示此架構整合 Gemma-2-2B-It在跌倒風險評估之準確率達到86.1%，且預測跌倒事件的機率在未來三個月至一年內具有統計上之顯著差異，因此此系統可望提升遠距醫療環境下的跌倒風險評估效能，提供醫療人員更準確的決策支持，並進一步減少老年人跌倒相關的健康風險與醫療負擔。

As people age, the risk of falling significantly increases. Fall accidents can lead to injuries or even life-threatening conditions, further impacting the quality of life and creating burdens on families. To prevent and detect falls in real-time, it is crucial to develop an accurate fall prediction system. This dissertation is divided into three parts, focusing on the application of multimodal data in fall prediction presenting the resulting innovations and technological advancements. The first part of this dissertation designs a shoe-integrated fall detection system equipped with seven time-of-flight sensors to identify falls across different terrains. Embedded within the shoes, the time-of-flight sensors measure real-time distances between the sensors and the ground, enabling simultaneous detection of gait cycle changes and terrain geometries. The system achieved F1 scores of 99.07% for fall detection, demonstrating its feasibility. The second part of this dissertation proposes a wearable pre-impact fall detection system combining time-of-flight sensors and inertial measurement units. This system utilizes a dual-task learning architecture based on convolutional neural networks and long short-term memory networks to simultaneously classify fall risk levels and terrain types, improving the accuracy of fall risk detection across various terrains. The system predicted falls with 97.7% accuracy and detected fall motions with an average of 329 milliseconds before fall impact occurred, confirming the proposed system’s robustness. The third part of this dissertation introduces a case-based reasoning architecture for fall risk assessment and care recommendation generation. The framework retrieves the top-N most similar cases to the user and uses them as contextual input for a large language model (LLM) to assess fall risk. Experimental results show that, when integrated with Gemma-2-2B-It, the architecture achieves an accuracy of 86.1% in fall risk assessment. Moreover, the predicted fall probabilities exhibit statistically significant differences between fallers and non-fallers within a 3-month to 1-year follow-up period. The results demonstrate that the proposed architecture enhances the effectiveness of fall risk assessment in remote healthcare settings, provides accurate decision support for clinicians, and ultimately reduces fall-related health risks and medical burdens among the elderly.

[1] C. H. Jones and M. Dolsten, “Healthcare on the brink: navigating the challenges of an aging society in the United States,” npj Aging, vol. 10, no. 1, pp. 1-10, Apr. 2024.
[2] R. Kolade, J. Porat-Dahlerbruch, R. Makhmutov, T. Achterberg and M. E. Ellen, “Strategies for engaging older adults and informal caregivers in health policy development: A scoping review,” Health Research Policy and Systems, vol. 22, no. 26, Feb. 2024.
[3] M. K. Karlsson, T. Vonschewelov, C. Karlsson, M. Cöster, and B. E. Rosengen, “Prevention of falls in the elderly: A review,” Scandin. J. Public Health, vol. 41, no. 5, pp. 442-454, Jan. 2013. J2-1
[4] L. A. Schaap, N. W. Y. Schoor, P. Lips, and M. Visser, “Associations of sarcopenia definitions, and their components, with the incidence of recurrent falling and fractures: The longitudinal aging study amsterdam,” Gerentol. Ser. A, vol. 73, no. 9, pp. 1199-1204, Sep. 2018. J2-2
[5] J. Williams et al., “Prevalence risk factors and disability associated with fall-related injury in older adults in low- and middle-incomecountries: results from the WHO Study on global AGEing and adult health (SAGE),” BMC Med, vol. 13, no. 1, pp. 147, Jun. 2015. J2-3
[6] P. Kannus, H. Sievänen, M. Palvanen, T. Järvinen, and J. Parkkari, “Prevention of falls and consequent injuries in elderly people,” Lancet., vol. 366, no. 9500, pp. 1885-1893, 2005. J2-4
[7] D. Mohan, D. Z. Al-Hamid, P. H. J. Chong, K. L. K. Sudheera, J. Gutierrez, and H. C. B. Chan “Artificial intelligence and IoT in elderly fall prevention: A review,” IEEE Sens. J., vol. 24, no. 4, pp. 4181-4198, Feb. 2024.
[8] L. Ren and Y. Peng, “Research of fall detection and fall prevention technologies: A systematic review,” IEEE Access, vol. 7, pp. 77702-77722, Jun. 2019.
[9] N. T. Newaz and E. Hanada, “The methods of fall detection: A literature review,” Sensors, vol. 23, no. 11, p. 5212, May 2023.
[10] X. Hu and X. Qu, “Pre-impact fall detection,” BioMed. Eng. OnLine, vol. 15, no. 61, Jun. 2016.
[11] J. M. Morse, R. M. Morse, and S. J. Tylko, “Development of a scale to identify the fall-prone patient,” Can. J. Aging, vol. 8, no. 4, pp. 366-377, 1989.
[12] Podsiadlo D and Richardson S. “The timed Up & Go: a test of basic functional mobility for frail elderly persons,” J. Am. Geriatr. Soc., vol. 39, no. 2, pp. 142-148, 1991.
[13] Li, E. Bodanese, S. Poslad, Z. Huang, T. Hou, K. Wu, and F. Luo, ‘‘An integrated sensing and communication system for fall detection and recognition using ultrawideband signals,’’ IEEE Internet Things J., vol. 11, no. 1, pp. 1509-1521, Jan. 2024.
[14] Yuan-Hao Ho, Guan-Hao Hou, Meng-Hsuan Wu, Fu-Hsing Chen, Chieh-Hsu Chen, and Chih-Lung Lin, “High-precision UWB indoor positioning system for customer pathway tracking,” IEEE 8th Global Conference on Consumer Electronics (GCCE), Osaka, Japan, Oct. 2019.
[15] Yuan-Hao Ho, Wen-Yen Shieh, Pi-Shan Sung and Chih-Lung Lin, “A real-time customer tracking system based on ultra-wideband sensors,” IEEE 10th Global Conference on Consumer Electronics (GCCE), Kyoto, Japan, Oct. 2021.
[16] D. De Venuto and G. Mezzina, “Multisensing architecture for the balance losses during gait via physiologic signals recognition,” IEEE Sens. J., vol. 20, no. 23, pp. 13959-13968, Dec. 2020.
[17] X. Chai, B.-G. Lee, M. Pike, R. Wu, D. Chieng, and W.-Y. Chung, “Pre-impact firefighter fall detection using machine learning on the edge,” IEEE Sens. J., vol. 23, no. 13, pp. 14997-15009, Jul. 2023.
[18] H. Shi, Y. Liu, H. Luo, and H. Zhao, “Knowledge transfer for body sensor networks: Characterization and resistance of negative transfer in overconstrained environments,” IEEE Internet Things J., vol. 11, no. 19, pp. 31959-31973, Oct. 2024.
[19] C.-L. Lin, W.-C. Chiu, T.-C. Chu, Y.-H. Ho, F.-H. Chen, C.-C. Hsu, P.-H. Hsieh, C.-H. Chen, C.-C. K. Lin, P.-S. Sung, and P.-T. Chen, “Innovative head-mounted system based on inertial sensors and magnetometer for detecting falling movements,” Sensors, vol. 20, no.20, p. 5774, Oct. 2020.
[20] C.-L. Lin, W.-C. Chiu, F.-H. Chen, Y.-H. Ho, T.-C. Chu, and P.-H. Hsieh, “Fall monitoring for the elderly using wearable inertial measurement sensors on eyeglasses,” IEEE Sensors Lett., vol. 4, no. 6, Jun. 2020.
[21] A. Choi, T. H. Kim, O. Yuhai, S. Jeong, K. Kim, H. Kim, and J. H. Mun, “Deep learning-based near-fall detection algorithm for fall risk monitoring system using a single inertial measurement unit,” IEEE Trans. Neural Syst. Rehabil. Eng., vol. 30, pp. 2385-2394, Aug. 2022.
[22] X. Yu, T. Ma, J. Jang and S. Xiong, “Data augmentation to address various rotation errors of wearable sensors for robust pre-impact fall detection,” IEEE Trans. Inf. Technol. Biomed., vol. 27, no. 5, pp. 2197-2207, May 2023.
[23] A. Benoit, C. Escriba, D. Gauchard, A. Esteve, and C. Rossi, “Analyzing and comparing deep learning models on a ARM 32 bits microcontroller for pre-impact fall detection,” IEEE Sens. J., vol. 24, no. 7, pp. 11829-11842, Feb. 2024.
[24] J. Howcroft, J. Kofman , and E. D. Lemaire, “Prospective fall-risk prediction models for older adults based on wearable sensors,” IEEE Trans. Neural Syst. Rehabil. Eng., vol. 25, no. 10, pp. 1812-1820, Oct. 2017.
[25] M. W. Rivolta, Md. Aktaruzzaman, G. Rizzo, C. L. Lafortunac, M. Ferrarin, G. Bovi, D. R. Bonardi, A. Caspani, and R. Sassi, “Evaluation of the Tinetti score and fall risk assessment via accelerometry based movement analysis,” Artif. Intell. Med., vol. 95, pp. 38-47, Apr. 2019.
[26] K. McManus, B. R. Greene, L. G. M. Ader, and B. Caulfield, “Development of data-driven metrics for balance impairment and fall risk assessment in older adults,” IEEE Trans. Biomed. Eng., vol. 69, no. 7, pp. 2324-2332, July 2022.
[27] K. Zhang, W. Liu, J. Zhang, Z. Li, and J. Liu, “A fall risk assessment model for community-dwelling elderly individuals based on gait parameters,” IEEE Access, vol. 11, pp. 120857-120867, 2023.
[28] X. Wang, L. Yu, H. Wang, K. L. Tsui, and Y. Zhao, “Sensor-based multifaceted feature extraction and ensemble elastic net approach for assessing fall risk in community-dwelling older adults,” IEEE J. Biomed. Health Inform., vol. 28, no. 11, pp. 6661-6673, Nov. 2024.
[29] A. Millet, A. Madrid, J. M. Alonso-Weber, L. Rodríguez-Mañas, and R. Pérez-Rodrá-Guez, “Machine learning techniques applied to the development of a fall risk index for older adults,” IEEE Access, vol. 11, pp. 84795-84809, 2023.
[30] A. J. Thirunavukarasu, D. S. J. Ting, K. Elangovan, L. Gutierrez, T. F. Tan, and D. S. W. Ting, “Large language models in medicine,” Nat. Med., vol 29, pp. 1930-1940, June 2023.
[31] H. M. Alghamdi, and A. Mostafa, “Towards reliable healthcare LLM agents: a case study for pilgrims during Hajj,” Information, vol. 15, no. 7, June 2024.
[32] Chaoyi Wu, Weixiong Lin, Xiaoman Zhang, Ya Zhang, Weidi Xie, and Yanfeng Wang, “PMC-LLaMA: toward building open-source language models for medicine,” J. Am. Med. Inform. Assoc., vol. 31, no. 9 , pp. 1833-1843, April 2024.
[33] Iuliu Alexandru Pap, and S. Oniga, “Ehealth assistant AI chatbot using a large language model to provide personalized answers through secure decentralized communication,” Sensors, vol. 24, no. 18, Sep. 2024.
[34] T. Han, L. C. Adams, J.-M. Papaioannou, P. Grundmann, T. Oberhauser, A. Figueroa, A. Löser, D. Truhn, and K. K. Bressem, “MedAlpaca-An open-source collection of medical conversational AI models and training data,” 2023, arXiv:2304.08247.
[35] Y. Labrak, A. Bazoge, E. Morin, P.-A. Gourraud, M. Rouvier, and R. Dufour, “BioMistral: A collection of open-source pretrained large language models for medical domains,” 2025, arXiv:2402.10373.
[36] Bufang Yang, Siyang Jiang, Lilin Xu, Kaiwei Liu, Hai Li, Guoliang Xing, Hongkai Chen, Xiaofan Jiang, and Zhenyu Yan, “DrHouse: an LLM-empowered diagnostic reasoning system through harnessing outcomes from sensor data and expert knowledge,” Proc. ACM Interact. Mob. Wearable Ubiquitous Technol., vol. 8, no. 4, Dec. 2024.
[37] F. Khan, T. A. Tulon, N. Masrur, M. J. Hasan, T. Badrul, and A. Islam, “Development and evaluation of ShasthoBondhu: mHealth App for guiding emergency remote healthcare with wearable IoT and AI fusion,” Adv. Sci. Eng. Technol. Int. Conf. (ASET), Abu Dhabi, United Arab Emirates, 2024, pp. 1-10.
[38] Elizabeth Healey, and Isaac Kohane, “LLM-CGM: a benchmark for large language model-enabled querying of continuous glucose monitoring data for conversational diabetes management,” Biocomputing 2025, pp.82-93, 2024.
[39] Y. Kim, X. Xu, D. McDuff, C. Breazeal, and H. W. Park, “Health-LLM: Large language models for health prediction via wearable sensor data,” 2024, arXiv:2401.06866.
[40] T. C. Ho, F. Kharrat, A. Abid, F. Karray, and A. Koubaa, “REMONI: an autonomous system integrating wearables and multimodal large language models for enhanced remote health monitoring,” IEEE Int. Symp. Med. Meas. Appl. (MeMeA), Eindhoven, Netherlands, 2024, pp. 1-6.
[41] C.-L. Lin, T.-Y. Liu, H.-C. Wu, M.-H. Lee, T.-S. Kuo, and S.-T. Young, “A portable monitor for fetal heart rate and uterine contraction,” IEEE Eng. Med. Biol. Mag., vol. 16, no. 6, pp. 80-84, Nov. 1997.
[42] T. de Quadros, A. E. Lazzaretti, and F. K. Schneider, “A movement decomposition and machine learning-based fall detection system using wrist wearable device,” IEEE Sens. J., vol. 18, no. 12, pp. 5082-5089, Apr. 2018.
[43] B. Cates, T. Sim, H. Heo, B. Kim, H. Kim, and J. Mun, “A novel detection model and its optimal features to classify falls from low- and high-acceleration activities of daily life using an insole sensor system,” Sensors, vol. 18, no. 4, pp. 1227, Apr. 2018.
[44] J. K. Lee, S. N. Robinovitch, and E. J. Park, “Inertial sensing-based pre-impact detection of falls involving near-fall scenarios,” IEEE Trans. Neural Syst. Rehabil. Eng., vol. 23, no. 2, pp. 258-266, Mar. 2015.
[45] M. A. Brodie, K. wang, K. Delbaere, M. Persiani, N.H. Lovell, S. J. Redmond, M. B. Del Rosario, and S. R. Lord, “New methods to monitor stair ascents using a wearable pendant device reveal how behavior, fear, and frailty influence falls in octogenarians,” IEEE Trans. Biomed. Eng., vol. 62, no. 11, pp. 2595-2601, Nov. 2015.
[46] C.-L. Lin, T.-C. Chu, C.-E. Wu, Y.-M. Chang, T.-C. Lin, J.-F. Chen, C.-Y. Chuang, and W.-C. Chiu, “Tracking touched trajectory on capacitive touch panels using an adjustable weighted prediction covariance matrix,” IEEE Trans. on Ind. Electron., vol. 64, no. 6, pp. 4910-4916, Jun. 2017.
[47] M. Gupta, J. Gao, C. C. Aggarwal, and J. Han, “Outlier detection for temporal data: A survey,” IEEE Trans. Knowl. Data Eng., vol. 26, no. 9, pp. 2250-2267, Sep. 2014.
[48] Y. Zhang, Z. Zhang, Y. Zhang, J. Bao, Y. Zhang, and H. Deng, “Human activity recognition based on motion sensor using U-Net,” IEEE Access, vol. 7, pp. 75213-75226, Jun. 2019.
[49] K. Liu, C. Hsieh, H. Huang, S. J. Hsu, and C. Chan, “An analysis of segmentation approaches and window sizes in wearable-based critical fall detection systems with machine learning models,” IEEE Sens. J., vol. 20, no. 6, pp. 3303-3313, Mar. 2020.
[50] A. Rocha and S. K. Goldenstein, “Multiclass from binary: Expanding one-versus-all, one-versus-one and ECOC-based approaches,” IEEE Trans. Neural Netw. Learn. Syst., vol. 25, no. 2, pp. 289-302, Feb. 2014.
[51] C. Wang, Y. Kim, D. G. Kim, S. H. Lee, and S. D. Min, “Smart helmet and insole sensors for near-fall incidence recognition during descent of stairs,” Applied Sciences, vol. 10, no. 7, pp. 2262, Mar. 2020.
[52] R. Xi, M. Li, M. Hou, M. Fu, H. Qu, D. Liu, and C. R. Haruna, “Deep dilation on multimodality time series for human activity recognition,” IEEE Access, vol. 6, pp. 53381-53396, Sep. 2018.
[53] C.-L. Lin, P.-T. Lee, Y.-H. Ho, Z.-L. Yang, Y.-H. Lu, C.-Y. Chan, and P.-S. Sung, “A highly reliable ultrasonic sensor-based bed-exit detection system for the elderly with early notification,” IEEE Sensors Lett., vol. 8, no. 1, pp. 1-4, Jan. 2024.
[54] X. Qian, H. Chen, H. Jiang, J. Green, H. Cheng, and M.-C. Huang, “Wearable computing with distributed deep learning hierarchy: A study of fall detection,” IEEE Sens. J., vol. 20, no. 16, pp. 9408-9416, Aug. 2020.
[55] C. Mosquera-Lopez, E. Wan, M. Shastry, J. Folsom, J. Leitschuh, J. Condon, U. Rajhbeharrysingh, A. Hildebrand, M. Cameron, and P. G. Jacobs, “Automated detection of real-world falls: Modeled from people with multiple sclerosis,” IEEE J. Biomed. Health Inform, vol. 25, no. 6, pp. 1975-1984, Jun. 2021.
[56] B. Cao, Q. Ping, B. Liu, Y. Nian, and M. He, “Real-Time Fall Detection Using Wideband Radar and a Lightweight Deep Learning Network,” IEEE Sens. J., vol. 24, no. 20, pp. 33682-33693, Oct. 2024.
[57] C. -L. Lin, Y. -H. Ho, W. -C. Chiu, T. -C. Chu and Y. -H. Liu, “Innovative shoe-integrated system based on time-of-flight range sensors for fall detection on various terrains,” IEEE Sensors Lett., vol. 5, no. 10, pp. 1-4, Oct. 2021.
[58] C. -L. Lin, F.-Y. Lin, C.-Y. Huang, Y.-H. Ho, W.-C. Chiu, and P.-S. Sung, “Classification of gaits with a high risk of falling using a head-mounted device with a temporal convolutional network,” IEEE Sensors Lett., vol. 8, no. 5, pp. 1-4, May 2024.
[59] L. Montesinos, R. Castaldo, and L. Pecchia, “Wearable inertial sensors for fall risk assessment and prediction in older adults: a systematic review and meta-analysis,” IEEE Trans. Neural Syst. Rehabil. Eng., vol. 26, no. 3, pp. 573-582, Mar. 2018.
[60] M. Nouredanesh, K. Gordt, M. Schwenk, and J. Tung, “Automated detection of multidirectional compensatory balance reactions: A step towards tracking naturally occurring near falls,” IEEE Trans. Neural Syst. Rehabil. Eng., vol. 28, no. 2, pp. 478-487, Feb. 2020.
[61] C. Tunca, G. Salur, and C. Ersoy, “Deep learning for fall risk assessment with inertial sensors: Utilizing domain knowledge in spatio-temporal gait parameters,” IEEE J. Biomed. Health Inform., vol. 24, no. 7, pp. 1994-2005, Jul. 2020.
[62] K. Wang, K. Delbaere, M. A. D. Brodie, N. H. Lovell, L. Kark, S. R. Lord, and S. J. Redmond, “Differences between gait on stairs and flat surfaces in relation to fall risk and future falls,” IEEE J. Biomed. Health Inform., vol. 21, no. 6, pp. 1479-1486, Mar. 2017.
[63] Y. Diao, N. Lou, S. Liang, Y. Zhang, Y. Ning, G. Li, and G. Zhao, “A novel environment-adaptive timed up and go test system for fall risk assessment with wearable inertial sensors,” IEEE Sens. J., vol. 21, no. 16, pp. 18287-18297, Aug. 2021.
[64] N. Roth, M. Ullrich, A. Küderle, T. Gladow, F. Marxreiter, H. Gassner, F. Kluge, J. Klucken, and B. M. Eskofier, “Real-world stair ambulation characteristics differ between prospective fallers and non-fallers in Parkinson’s disease,” IEEE J. Biomed. Health Inform., vol. 26, no. 9, pp. 4733-4742, Sep. 2022.
[65] G. Shi, C. S. Chan, W. J. Li, K. -S. Leung, Y. Zou, and Y. Jin, “Mobile human airbag system for fall protection using MEMS sensors and embedded SVM Classifier,” IEEE Sens. J., vol. 9, no. 5, pp. 495-503, May 2009.
[66] T. Tamura, T. Yoshimura, M. Sekine, M. Uchida, and O. Tanaka, “A wearable airbag to prevent fall injuries,” IEEE Trans. Inf. Technol. Biomed., vol. 13, no. 6, pp. 910-914, Nov. 2009.
[67] S. Ahn, D. Choi, J. Kim, S. Kim, Y. Jeong, M. Jo, and Y. Kim, ‘‘Optimization of a pre-impact fall detection algorithm and development of hip protection airbag system,’’ Sensors Mater., vol. 30, no. 8, pp. 1743-1752, Aug. 2018.
[68] G. Wu and S. Xue, “Portable preimpact fall detector with inertial sensors,” IEEE Trans. Neural Syst. Rehabil. Eng., vol. 16, no. 2, pp. 178-183, Apr. 2008.
[69] L. Tong, Q. Song, Y. Ge, and M. Liu, “HMM-based human fall detection and prediction method using tri-axial accelerometer,” IEEE Sens. J., vol. 13, no. 5, pp. 1849-1856, May 2013.
[70] F. A. S. Ferreira de Sousa, C. Escriba, E. G. Avina Bravo, V. Brossa, J. -Y. Fourniols, and C. Rossi, “Wearable pre-impact fall detection system based on 3D accelerometer and subject’s height,” IEEE Sens. J., vol. 22, no. 2, pp. 1738-1745, Jan. 2022.
[71] J. Shi, D. Chen, and M. Wang, “Pre-impact fall detection with CNN based class activation mapping method,” Sensors, vol. 20, no. 17, p. 4750, Aug. 2020.
[72] L. Wang, M. Peng, and Q. Zhou, “Pre-impact fall detection based on multi-source CNN ensemble,” IEEE Sens. J., vol. 20, no.10, pp. 5442-5451, Jan. 2020.
[73] W. Saadeh, S. A. Butt, and M. A. B. Altaf, “A patient-specific single sensor IoT-based wearable fall prediction and detection system,” IEEE Trans. Neural Syst. Rehabil. Eng., vol. 27, no. 5, pp. 995-1003, May 2019.
[74] X. Yu, H. Qiu, and S. Xiong, “A novel hybrid deep neural network to predict pre-impact fall for older people based on wearable inertial sensors,” Frontiers Bioeng. Biotechnol., vol. 8, p. 63, Feb. 2020.
[75] R. Jain and V. B. Semwal, “A novel feature extraction method for preimpact fall detection system using deep learning and wearable sensors,” IEEE Sens J., vol. 22, no. 23, pp. 22943-22951, Dec. 2022.
[76] F. Zhang, P. Bohlen, M. D. Lewek, and H. Huang, “Prediction of intrinsically caused tripping events in individuals with stroke,” IEEE Trans. Neural Syst. Rehabil. Eng., vol. 25, no. 8, pp. 1202-1210, Aug. 2017.
[77] A. Pang, Y. Okubo, D. Sturnieks, S. R. Lord, and M. A. Brodie, “Detection of near falls using wearable devices: A systematic review”, J. Geriatric Phys. Therapy, vol. 42, no. 1, pp. 48-56, Jan. 2019.
[78] Y. Zhu, H. Li, Y. Liao, B. Wang, Z. Guan, H. Liu, and D. Cai, “What to do next: Modeling user behaviors by time LSTM,” Proc. 26th Int. Joint Conf. Artif. Intell., pp. 3602-360, 2017.
[79] S. Eyobu, and D. S. Han, “Feature representation and data augmentation for human activity classification based on wearable IMU sensor data using a deep LSTM neural network,” Sensors, vol. 18, no. 9, Aug. 2018.
[80] M. M. Hassan, A. Gumaei, G. Aloi, G. Fortino, and M. Zhou, “A smartphone-enabled fall detection framework for elderly people in connected home healthcare,” IEEE Netw., vol. 33, no. 6, pp. 58-63, Jun. 2019.
[81] G. Li, T. Liu, and J. Yi, “Wearable sensor system for detecting gait parameters of abnormal gaits: A feasibility study,” IEEE Sens J., vol. 18, no. 10, pp. 4234-4241, May 2018.
[82] S. Sahoo, M. Maheshwari, D. K. Pratihar, and S. Mukhopadhyay, “A geometry recognition-based strategy for locomotion transitions early prediction of prosthetic devices,” IEEE Trans. Instrum. Meas., vol. 69, no. 4, pp. 1259-1267, Apr. 2020.
[83] F. I. Mahoney and D. W. Barthel., “Functional evaluation: The Barthel index,” Maryland State Med. J., vol. 14, no. 2, pp. 61-65, 1965.
[84] R. P. Di Fabio, C. Zampieri, and P. Tuite, “Gaze control and foot kinematics during stair climbing: characteristics leading to fall risk in progressive supranuclear palsy,” Phys Ther., vol. 88, no. 2, pp. 240-250, Feb. 2008.
[85] J. V. Jacobs, “A review of stairway falls and stair negotiation: Lessons learned and future needs to reduce injury,” Gait Posture., vol. 49, pp. 159-167, Jun. 2016.
[86] M. J. Pavol, T. M. Owings, K. T. Foley, and M. D. Grabiner, “Mechanisms leading to a fall from an induced trip in healthy older adults,” J. Gerontol A Biol. Sci. Med. Sci., vol. 56, no. 7, pp. M428-M437, Jul. 2001.
[87] S. Wang, T. K. Nguyen, and T. Bhatt, “Trip-related fall risk prediction based on gait pattern in healthy older adults: A machine-learning approach,” Sensors., vol. 23, no. 12, Jun. 2023.
[88] A. Eljubrani, O. Maklouf, and A. A. Mgig, “MEMS inertial measurement unit calibration using low cost hardware,” Int. Conf. Sci. Tech. Autom. Control Comput. Eng. (STA)), Sousse, Tunisia, pp. 315-319, Dec. 2022.
[89] M. Saukoski, L. Aaltonen, and K. A. I. Halonen, “Zero-rate output and quadrature compensation in vibratory mems gyroscopes,” IEEE Sens. J., vol. 7, no. 12, pp. 1639-1652, Dec. 2007.
[90] V. Agostini, G. Balestra, and M. Knaflitz, “Segmentation and classification of gait cycles,” IEEE Trans. Neural Syst. Rehabil. Eng., vol. 22, no. 5, pp. 52-946, Nov. 2014.
[91] A. Rampp, J. Barth, S. Schulein, K.-G. Gaßmann, J. Klucken, and B. M. Eskofier, “Inertial sensor based stride parameter calculation from gait sequences in geriatric patients,” IEEE Trans. Biomed. Eng., vol. 62, no. 4, pp. 1089-1097, Apr. 2015.
[92] M. Pijnappels, K. Delbaere, D. L. Sturnieks, and S. R. Lord, “The association between choice stepping reaction time and falls in older adults—a path analysis model,” Age Ageing, vol. 39, no. 1, pp. 99-104, Jan. 2010.
[93] A.-A. Liu, Y.-T. Su, W.-Z. Nie, and M. Kankanhalli, “Hierarchical clustering multi-task learning for joint human action grouping and recognition,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 39, no. 1, pp. 102-114, Jan. 2017.
[94] Y. Zhang and Q. Yang, “A survey on multi-task learning,” IEEE Trans. Knowl. Data Eng., vol. 34, no. 12, pp. 5586-5609, Dec. 2022.
[95] Y. Fang, S. Cai, Y. Cao, Z. Li, and Z. Zhang, “Adversarial learning guided task relatedness refinement for multi-task deep learning,” IEEE Trans. Multimedia, vol. 25, pp. 6946-6957, Oct. 2022.
[96] N. H. Sarker and M. Sohel Rahman, “Forward diffusion guided reconstruction as a multi-modal multi-task learning scheme,” IEEE Int. Conf. Image Process. (ICIP), Kuala Lumpur, Malaysia, pp. 3180-3184, Oct. 2023.
[97] W. Shao, H. Shi, J. Liu, Y. Zuo, L. Sun, T. Xia, W. Chen, P. Wan, J. Sheng, Q. Zhu, and D. Zhang, “Multi-instance multi-task learning for joint clinical outcome and genomic profile predictions from the histopathological images,” IEEE Trans. Med. Imaging, vol. 43, no. 6, pp. 2266-2278, Jun. 2024.
[98] J. Lin and S. Moothedath, “Fast and sample-efficient relevance-based multi-task representation learning,” IEEE Control Syst. Lett., vol. 8, pp. 1397-1402, Jun. 2024.
[99] T.-Y. Lin, P. Goyal, R. Girshick, K. He, and P. Dollár, “Focal loss for dense object detection,” Proc. IEEE Int. Conf. Comput. Vis., pp. 2980-2988, Oct. 2017.
[100] Y. Cui, M. Jia, T.-Y. Lin, Y. Song, and S. Belongie, “Class-balanced loss based on effective number of samples,” Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pp. 9268-9277, Jun. 2019.
[101] D. L. Woods, J. M. Wyma, E. W. Yund, T. J. Herron, and B. Reed, “Factors influencing the latency of simple reaction time,” Front. Hum. Neurosci., vol. 9, 2015, Art. no. 131.
[102] K. L. Perell, A. Nelson, R. L. Goldman, S. L. Luther, N. Prieto-Lewis, and L. Z. Rubenstein, “Fall risk assessment measures: An analytic review,” J. Gerontol. A Biol. Sci. Med. Sci., vol. 56, no 12, pp. M761-M766 Dec. 2001.
[103] S. R Lord, H. B Menz, and A. Tiedemann, “A physiological profile approach to falls risk assessment and prevention,” Phys. Ther., vol. 83, no. 3, pp. 237-252, Mar. 2003.
[104] S. Bhasin et al., “A randomized trial of a multifactorial strategy to prevent serious fall injuries,” N. Engl. J. Med., vol. 383, no. 2, pp. 129-140, Jul. 2020.
[105] E. Goh et al., “GPT-4 assistance for improvement of physician performance on patient care tasks: a randomized controlled trial,” Nat. Med., 2025.
[106] D. Van Veen et al., “Adapted large language models can outperform medical experts in clinical text summarization,” Nat. Med., 2025.
[107] S. Kresevic et al., “Optimization of hepatological clinical guidelines interpretation by large language models: a retrieval augmented generation-based framework,” npj. Digit. Med., vol. 7, no. 102, Apr. 2024.
[108] S. Gilbert, J. N. Kather, and A. Hogan, “Augmented non-hallucinating large language models as medical information curators,” npj. Digit. Med., vol. 7, no. 100, Apr. 2024.
[109] L. G. Marc, P. J. Raue, and M. L. Bruce, “Screening performance of the 15-item geriatric depression scale in a diverse elderly home care population,” Am. J. Geriatr. Psychiatry, vol. 16, no. 11, pp. 914-921, Nov. 2008.
[110] E. Pfeiffer, “A short portable mental status questionnaire for the assessment of organic brain deficit in elderly patients,” J. Am. Geriatr. Soc., vol. 23, pp. 433-441, Oct. 1975.
[111] E. Sejdi, K. A. Lowry, J. Bellanca, M. S .Redfern, and J. S. Brach, “A comprehensive assessment of gait accelerometry signals in time, frequency and time-frequency domains,” IEEE Trans. Neural Syst. Rehabil. Eng., vol. 22, no. 3, pp. 603-612, May 2014.
[112] M. Goñi, S. B. Eickhoff, M. S. Far, K. R. Patil, and J. Dukart, “Smartphone-based digital biomarkers for Parkinson’s disease in a remotely-administered setting,” IEEE Access, vol. 10, pp. 28361-28384, 2022.
[113] Y. Zhang, W. Yan, Y. Yao, J. B. Ahmed, Y. Tan, and D. Gu, “Prediction of freezing of gait in patients with Parkinson’s disease by identifying impaired gait patterns,” IEEE Trans. Neural Syst. Rehabil. Eng., vol. 28, no. 3, pp. 591-600, Mar. 2020.
[114] A. Agrawal, S. K. Sahay, and S. K. Sahay, “HALO: Hallucination analysis and learning optimization to empower LLMs with retrieval-augmented context for guided clinical decision making,” 2023, arXiv:2305.16264.
[115] A. M. Lehman, A. M. Lehman, and A. M. Lehman, “A framework to assess clinical safety and hallucination rates of LLMs for medical text summarisation,” 2023, arXiv:2306.00969.
[116] J. Miao et al., “Integrating retrieval-augmented generation with large language models in nephrology: advancing practical applications,” Medicina, vol. 60, no. 3, March 2024.
[117] A. Bora, and H. Cuayáhuitl, “Systematic analysis of retrieval-augmented generation-based LLMs for medical chatbot applications,” Mach. Learn. Knowl. Extr., vol. 6, no. 4, pp. 2355-2374, Oct. 2024.
[118] N. Davey, E. Connolly, P. M. Elwaine, and S. P Kennelly, “A systematic review of falls risk of frail patients with dementia in hospital: progress, challenges, and recommendations,” Clin. Interv. Aging, vol. 19, pp. 1127-1139, Jun. 2024.
[119] E. Dove, P. Hewston, R. H. Wang, K. K. Patterson, and A. J. Astell, “Concerns about falling in people with mild cognitive impairment and dementia: a scoping review of exercise interventions,” Front. Dement., vol. 3, Nov. 2024.
[120] C. V. Doorn et al., “Dementia as a risk factor for falls and fall injuries among nursing home residents,” J. Amer. Geriatrics Soc., vol. 51, no. 9, pp. 1213-1218, Sep. 2003.
[121] M. E. Taylor and J. C.T. Close, “Dementia,” Handb. Clin. Neurol., vol. 159, pp. 303-321, Nov. 2018.
[122] J. A. Cohen and J. Verghese, “Gait and dementia,” Handb. Clin. Neurol., vol. 167, pp. 419-427, Nov. 2019.
[123] L. M. Allan, C. G. Ballard, E. N. Rowan, and R. A. Kenny, “Incidence and prediction of falls in dementia: a prospective study in older people,” PLoS One, vol. 4, no. 5, May 2009.
[124] F. MH Lam et al., “Physical exercise improves strength, balance, mobility, and endurance in people with cognitive impairment and dementia: a systematic review,” J. Physiother., vol. 64, no. 1, pp. 4-15, Jan. 2018.
[125] S. M. Okoye, C. D. Fabius, L. Reider, and J. L. Wolff, “Predictors of falls in older adults with and without dementia,” Alzheimers Dement., vol. 19, no. 7, pp. 2888-2897, Jul. 2023.
[126] F. E. Shaw, “Prevention of falls in older people with dementia,” J. Neural Transm., vol. 114, pp. 1259-1264, Jun. 2007.
[127] K. Peek et al., “Reducing falls among people living with dementia: a systematic review,” Dementia, vol. 19, no. 5, pp. 1621-1640, Sep. 2018.
[128] T. Baniasadi, “Risk factors associated with falls in older adults with dementia and Alzheimer’s diseases among older adults in the united states,” medRxiv, Jan. 2023.
[129] A. J. Ordoobadi et al., “Risk of dementia diagnosis after injurious falls in older adults,” JAMA Network Open, vol. 7, no. 9, Sep. 2024.
[130] H. J. Gulka et al., “Efficacy and generalizability of falls prevention interventions in nursing homes: a systematic review and meta-analysis,” J. Am. Med. Dir. Assoc., vol. 21, no. 8, pp. 1024-1035, Aug. 2020.
[131] Q. Xu, X. Ou, and J. Li, “The risk of falls among the aging population: a systematic review and meta-analysis,” Front. Public Health, vol. 10, Oct. 2020.
[132] A. Lígia Silva de Lima, C. Borm, N. M. de Vries, and B. R. Bloem, “Falling among people with Parkinson’s disease: motor, non-motor, or both?,” Arq. Neuro-Psiquiatr., vol. 77, no. 11, pp. 759-760, Nov. 2019.
[133] S. A. Buetow, P.o Martínez-Martín, and B. McCormack, “Falling upward with Parkinson’s disease,” npj Parkinsons Dis., vol. 3, Sep. 2017.
[134] A. Fasano et al., “Falls in Parkinsons disease: A complex and evolving picture,” Movement Disord., vol. 32, no. 11, pp. 1524-1536, Nov. 2017.
[135] P. H. S. Pelicioni, J. C. Menant, M. D. Latt, and S. R. Lord, “Falls in Parkinson’s disease subtypes: risk factors locations and circumstances,” Int. J. Environ. Res. Public Health, vol. 16, no. 12, Jun. 2019.
[136] M. W. Creaby, and M. H. Cole, “Gait characteristics and falls in Parkinson’s disease: A systematic review and meta-analysis,” Parkinsonism Rel. Disorders, vol. 57, pp. 1-8, Dec. 2018.
[137] N. E. Allen et al., “Interventions for preventing falls in Parkinson's disease,” Cochrane Database Syst. Rev., no. 6, June 2022.
[138] S. D. Kim, N. E. Allen, C. G. Canning, and V. S. C. Fung, “Parkinson disease,” Handb. Clin. Neurol., vol. 159, pp. 173-193, Nov. 2018.
[139] R. Camicioli et al., “Prevention of falls in Parkinson's disease: guidelines and gaps,” Mov. Disord. Clin. Pract., vol. 10, no. 10, pp.1459-1469, Oct. 2023.
[140] W. Liu, T. Tung, C. Zhang, and L. Shi, “Systematic review for the prevention and management of falls and fear of falling in patients with Parkinson's disease,” Brain Behav. vol. 12, no. 8, July 2022.
[141] S. Thilarajah et al., “Factors associated with post-stroke physical activity: A systematic review and meta-analysis,” Arch. Phys. Med. Rehabil., vol. 99, no. 9, pp.1876-1889, Sep. 2018.
[142] N. Kerse et al., “Falls after stroke: Results from the auckland regional community stroke (ARCOS) study, 2002 to 2003,” Stroke, vol. 39, no. 6, pp.1890-1893, May 2008.
[143] F. A. Batchelor, S. F. Mackintosh, C. M. Said, and K. D. Hill, “Falls after stroke,” Int. J. Stroke, vol. 7, no. 6, pp. 482-490, Aug. 2012.
[144] Y. Chen et al., “Relationship between fear of falling and fall risk among older patients with stroke: a structural equation modeling,” BMC Geriatrics, vol. 23, no. 1, Oct. 2023.
[145] Q. Xie et al., “Risk factors for fear of falling in stroke patients: a systematic review and meta-analysis,” BMJ Open, vol.12, no.6, May 2022.
[146] O. Djurovic et al., “Risk factors related to falling in patients after stroke,” Iran. J. Public Health, vol. 50, no. 9, pp. 1832-1841, Sep. 2021.
[147] X. Zhao, D. Li, Y. Zhong, B. Hu, Y. Chen, B. Hu, and M. Zhang, “SEER: Self-aligned evidence extraction for retrieval-augmented generation,” 2024, arXiv:2410.11315.
[148] D. F. Navarro et al., “Expert evaluation of large language models for clinical dialogue summarization,” Sci. Rep. vol. 15, no. 1195, Jan. 2025.
[149] T. Brown et al., “Language models are few-shot learners,” Adv. Neural Inf. Process. Syst. 34 th, pp. 1877-1901, 2022.
[150] J. Wei et al., “Chain of thought prompting elicits reasoning in large language models,” Adv. Neural Inf. Process. Syst. 36 th, pp. 24824-24837, 2022.