1
|
Ogasawara T, Mukaino M, Matsunaga K, Wada Y, Suzuki T, Aoshima Y, Furuzawa S, Kono Y, Saitoh E, Yamaguchi M, Otaka Y, Tsukada S. Prediction of stroke patients' bedroom-stay duration: machine-learning approach using wearable sensor data. Front Bioeng Biotechnol 2024; 11:1285945. [PMID: 38234303 PMCID: PMC10791943 DOI: 10.3389/fbioe.2023.1285945] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/30/2023] [Accepted: 12/11/2023] [Indexed: 01/19/2024] Open
Abstract
Background: The importance of being physically active and avoiding staying in bed has been recognized in stroke rehabilitation. However, studies have pointed out that stroke patients admitted to rehabilitation units often spend most of their day immobile and inactive, with limited opportunities for activity outside their bedrooms. To address this issue, it is necessary to record the duration of stroke patients staying in their bedrooms, but it is impractical for medical providers to do this manually during their daily work of providing care. Although an automated approach using wearable devices and access points is more practical, implementing these access points into medical facilities is costly. However, when combined with machine learning, predicting the duration of stroke patients staying in their bedrooms is possible with reduced cost. We assessed using machine learning to estimate bedroom-stay duration using activity data recorded with wearable devices. Method: We recruited 99 stroke hemiparesis inpatients and conducted 343 measurements. Data on electrocardiograms and chest acceleration were measured using a wearable device, and the location name of the access point that detected the signal of the device was recorded. We first investigated the correlation between bedroom-stay duration measured from the access point as the objective variable and activity data measured with a wearable device and demographic information as explanatory variables. To evaluate the duration predictability, we then compared machine-learning models commonly used in medical studies. Results: We conducted 228 measurements that surpassed a 90% data-acquisition rate using Bluetooth Low Energy. Among the explanatory variables, the period spent reclining and sitting/standing were correlated with bedroom-stay duration (Spearman's rank correlation coefficient (R) of 0.56 and -0.52, p < 0.001). Interestingly, the sum of the motor and cognitive categories of the functional independence measure, clinical indicators of the abilities of stroke patients, lacked correlation. The correlation between the actual bedroom-stay duration and predicted one using machine-learning models resulted in an R of 0.72 and p < 0.001, suggesting the possibility of predicting bedroom-stay duration from activity data and demographics. Conclusion: Wearable devices, coupled with machine learning, can predict the duration of patients staying in their bedrooms. Once trained, the machine-learning model can predict without continuously tracking the actual location, enabling more cost-effective and privacy-centric future measurements.
Collapse
Affiliation(s)
- Takayuki Ogasawara
- NTT Basic Research Laboratories and Bio-Medical Informatics Research Center, NTT Corporation, Atsugi, Japan
- Department of Rehabilitation Medicine I, School of Medicine, Fujita Health University, Toyoake, Japan
| | - Masahiko Mukaino
- Department of Rehabilitation Medicine I, School of Medicine, Fujita Health University, Toyoake, Japan
- Department of Rehabilitation Medicine, Hokkaido University Hospital, Sapporo, Japan
| | | | - Yoshitaka Wada
- Department of Rehabilitation Medicine I, School of Medicine, Fujita Health University, Toyoake, Japan
| | - Takuya Suzuki
- Department of Rehabilitation Medicine, Fujita Health University Hospital, Toyoake, Japan
| | - Yasushi Aoshima
- Department of Rehabilitation Medicine, Fujita Health University Hospital, Toyoake, Japan
| | - Shotaro Furuzawa
- Department of Rehabilitation Medicine, Fujita Health University Hospital, Toyoake, Japan
| | - Yuji Kono
- Department of Rehabilitation Medicine I, School of Medicine, Fujita Health University, Toyoake, Japan
- Department of Rehabilitation Medicine, Fujita Health University Hospital, Toyoake, Japan
| | - Eiichi Saitoh
- Department of Rehabilitation Medicine I, School of Medicine, Fujita Health University, Toyoake, Japan
| | - Masumi Yamaguchi
- NTT Basic Research Laboratories and Bio-Medical Informatics Research Center, NTT Corporation, Atsugi, Japan
| | - Yohei Otaka
- Department of Rehabilitation Medicine I, School of Medicine, Fujita Health University, Toyoake, Japan
| | - Shingo Tsukada
- NTT Basic Research Laboratories and Bio-Medical Informatics Research Center, NTT Corporation, Atsugi, Japan
| |
Collapse
|
2
|
Pedrinolla A, Magliozzi R, Colosio AL, Danese E, Gelati M, Rossi S, Pogliaghi S, Calabrese M, Muti E, Cè E, Longo S, Esposito F, Lippi G, Schena F, Venturelli M. Repeated passive mobilization to stimulate vascular function in individuals of advanced age who are chronically bedridden. A randomized controlled trial. J Gerontol A Biol Sci Med Sci 2021; 77:588-596. [PMID: 34036337 DOI: 10.1093/gerona/glab148] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/09/2021] [Indexed: 02/06/2023] Open
Abstract
BACKGROUND Vascular dysfunction and associated disorders are major side effects of chronic bed rest, yet passive mobilization as a potential treatment has only been theorized so far. This study investigated the effects of passive mobilization treatment on vascular function in older, chronically bedridden people. METHODS The study sample was 45 chronically bedridden people of advanced age (mean age 87 years; 56% female; mean bed rest 4 years) randomly assigned to a treatment (n=23) or a control group (CTRL, n=22). The treatment group received passive mobilization twice daily (30 min, 5 times/week) for 4 weeks. A kinesiologist performed passive mobilization by passive knee flexion/extension at 1 Hz in one leg (treated leg, T-leg vs ctrl-leg). The CTRL group received routine treatment. The primary outcome was changes in peak blood flow (∆Peak) as measured with the single passive leg movement test (sPLM) at the common femoral artery. RESULTS ∆Peak was increased in both legs in the Treatment group (+90.9 ml/min, p<0.001, in T-leg and +25.7 ml/min, p=0.039 in ctrl-leg). No difference in peak blood flow after routine treatment was found in the CTRL group. CONCLUSION Improvement in vascular function after 4 weeks of passive mobilization was recorded in the treatment group. Passive mobilization may be advantageously included in standard clinical practice as an effective strategy to treat vascular dysfunction in persons with severely limited mobility.
Collapse
Affiliation(s)
- Anna Pedrinolla
- Department of Neuroscience, Biomedicine, and Movement Science, Section of Movement Science, University of Verona, Verona, Italy
| | - Roberta Magliozzi
- Department of Neuroscience, Biomedicine, and Movement Science, Section of Movement Science, University of Verona, Verona, Italy
| | - Alessandro L Colosio
- Department of Neuroscience, Biomedicine, and Movement Science, Section of Movement Science, University of Verona, Verona, Italy
| | - Elisa Danese
- Department of Life and Reproduction Sciences, Laboratory of Clinical Biochemistry, University of Verona, Verona, Italy
| | - Matteo Gelati
- Department of Life and Reproduction Sciences, Laboratory of Clinical Biochemistry, University of Verona, Verona, Italy
| | - Stefania Rossi
- Department of Neuroscience, Biomedicine, and Movement Science, Section of Movement Science, University of Verona, Verona, Italy
| | - Silvia Pogliaghi
- Department of Neuroscience, Biomedicine, and Movement Science, Section of Movement Science, University of Verona, Verona, Italy
| | - Massimiliano Calabrese
- Department of Neuroscience, Biomedicine, and Movement Science, Section of Movement Science, University of Verona, Verona, Italy
| | | | - Emiliano Cè
- Department of Biomedical Sciences for Health, University of Milan, Milan, Italy.,IRCSS Galeazzi Orthopaedic Institute, Milano, Italy
| | - Stefano Longo
- Department of Biomedical Sciences for Health, University of Milan, Milan, Italy
| | - Fabio Esposito
- Department of Biomedical Sciences for Health, University of Milan, Milan, Italy.,IRCSS Galeazzi Orthopaedic Institute, Milano, Italy
| | - Giuseppe Lippi
- Department of Life and Reproduction Sciences, Laboratory of Clinical Biochemistry, University of Verona, Verona, Italy
| | - Federico Schena
- Department of Neuroscience, Biomedicine, and Movement Science, Section of Movement Science, University of Verona, Verona, Italy
| | - Massimo Venturelli
- Department of Neuroscience, Biomedicine, and Movement Science, Section of Movement Science, University of Verona, Verona, Italy.,Department of Internal Medicine section of Geriatrics, University of Utah, Salt Lake City, UT, USA
| |
Collapse
|
3
|
Inoue T, Maeda K, Nagano A, Shimizu A, Ueshima J, Murotani K, Sato K, Tsubaki A. Undernutrition, Sarcopenia, and Frailty in Fragility Hip Fracture: Advanced Strategies for Improving Clinical Outcomes. Nutrients 2020; 12:nu12123743. [PMID: 33291800 PMCID: PMC7762043 DOI: 10.3390/nu12123743] [Citation(s) in RCA: 59] [Impact Index Per Article: 14.8] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/31/2020] [Revised: 11/30/2020] [Accepted: 12/03/2020] [Indexed: 12/13/2022] Open
Abstract
Geriatric patients with hip fractures often experience overlap in problems related to nutrition, including undernutrition, sarcopenia, and frailty. Such problems are powerful predictors of adverse responses, although few healthcare professionals are aware of them and therefore do not implement effective interventions. This review aimed to summarize the impact of undernutrition, sarcopenia, and frailty on clinical outcomes in elderly individuals with hip fractures and identify successful strategies that integrate nutrition and rehabilitation. We searched PubMed (MEDLINE) and Cochrane Central Register of Controlled Trials (CENTRAL) for relevant literature published over the last 10 years and found that advanced interventions targeting the aforementioned conditions helped to significantly improve postoperative outcomes among these patients. Going forward, protocols from advanced interventions for detecting, diagnosing, and treating nutrition problems in geriatric patients with hip fractures should become standard practice in healthcare settings.
Collapse
Affiliation(s)
- Tatsuro Inoue
- Department of Physical Therapy, Niigata University of Health and Welfare, Shimami-cho 950-3198, Japan; (T.I.); (A.T.)
| | - Keisuke Maeda
- Department of Geriatric Medicine, National Center for Geriatrics and Gerontology, Obu 474-8511, Japan
- Department of Palliative and Supportive Medicine, Graduate School of Medicine, Aichi Medical University, Nagakute 480-1195, Japan
- Correspondence: ; Tel.: +81-561-62-3311; Fax: +81-561-78-6364
| | - Ayano Nagano
- Department of Nursing, Nishinomiya Kyoritsu Neurosurgical Hospital, Nishinomiya 663-8211, Japan;
| | - Akio Shimizu
- Department of Nutrition, Hamamatsu City Rehabilitation Hospital, Hamamatsu 433-8127, Japan;
| | - Junko Ueshima
- Department of Clinical Nutrition and Food Service, NTT Medical Center Tokyo, Tokyo 141-8625, Japan;
| | - Kenta Murotani
- Biostatistics Center, Kurume University, Kurume 830-0011, Japan;
| | - Keisuke Sato
- Okinawa Chuzan Hospital Clinical Research Center, Chuzan Hospital, Matsumoto 904-2151, Japan;
| | - Atsuhiro Tsubaki
- Department of Physical Therapy, Niigata University of Health and Welfare, Shimami-cho 950-3198, Japan; (T.I.); (A.T.)
| |
Collapse
|