Exploring the Potential Use of Wearable Devices as a Prognostic Tool among Patients in Hospice Care

Abstract

Background—Smartphones and wearable devices have become a part and parcel of the healthcare industry. The use of wearable technology has already proved its potentials in improving healthcare research, clinical work, and patient care. The real time data allow the care providers to monitor the patients’ symptoms remotely, prioritize the patients’ visits, assist in decision-making, and carry out advanced care planning. Objective—The primary objective of our study was to investigate the potential use of wearable devices as prognosis tools among patients in hospice care and palliative care, and secondary objective was to examine the association between wearable devices and clinical data in the context of patient outcomes, such as discharge and deceased, at various time intervals. Methods—We employed an observational research approach to continuously monitor the hand movements of the recruited 68 patients between December 2019 and June 2022 via actigraphy device at hospice or palliative care ward of Taipei Medical University Hospital (TMUH) in Taiwan. Results—The results revealed that the patients with higher scores in the Karnofsky Performance Status (KPS), and Palliative Performance Scale (PPS) tended to live at discharge, while Palliative Prognostic Score (PaP) and Palliative prognostic Index (PPI) also shared the similar trend. In addition, the results also confirmed that all these evaluating tools only suggested rough rather than accurate and definite prediction. The outcomes (MBD or expired) were positively correlated with accumulated angle and spin values, i.e., the patients who survived had higher angle and spin values compared to those who died/expired. Conclusions—Outcomes had higher correlation with angle value compared to spin and ACT. The correlation value increased within the first 48 h and then began to decline. We recommend rigorous observational studies/randomized control trials with many participants for investigation in the future.

Deep Learning Prediction Model for Patient Survival Outcomes in Palliative Care Using Actigraphy Data and Clinical Information

“…The results of our current study are in line with our previous related study results, including two prospective observational studies [ 28 , 29 ] and a scoping review [ 44 ]. One of our previous findings showed that the majority of the included studies in the scoping review, which utilized wrist-worn wearable devices in cancer populations, focused on physical activity, sleep analysis, and heart vital signs and showed a positive correlation between patient-reported and wearable outcomes [ 44 ], while in the other study, automatic survival prediction using an LSTM DL model showed feasibility in clinical settings and possible benefits in end-of-life care settings without healthcare professionals [ 29 ].…”

“…One of our previous findings showed that the majority of the included studies in the scoping review, which utilized wrist-worn wearable devices in cancer populations, focused on physical activity, sleep analysis, and heart vital signs and showed a positive correlation between patient-reported and wearable outcomes [ 44 ], while in the other study, automatic survival prediction using an LSTM DL model showed feasibility in clinical settings and possible benefits in end-of-life care settings without healthcare professionals [ 29 ]. Additionally, in the third study, wearable devices reported greater angle and spin movements as early as within the first 48 h of observation in the cancer patients who were still alive after discharge from the hospice inpatient unit [ 28 ]. Based on our previous research findings that showed the potential of wearable devices and the utility of actigraphy data as a prognostic tool for patients in hospice care, the current study builds on the concept of utilizing wearable data to predict survival outcomes in hospice patients [ 28 ].…”

“…Additionally, in the third study, wearable devices reported greater angle and spin movements as early as within the first 48 h of observation in the cancer patients who were still alive after discharge from the hospice inpatient unit [ 28 ]. Based on our previous research findings that showed the potential of wearable devices and the utility of actigraphy data as a prognostic tool for patients in hospice care, the current study builds on the concept of utilizing wearable data to predict survival outcomes in hospice patients [ 28 ]. In contrast with our previous similar work [ 29 ], wherein we utilized LSTM DL techniques for predictive analysis, the current study employed a transformer model, which yielded more noteworthy results than LSTM.…”

“…Recently, in our previous study, we evaluated the feasibility of using actigraphy-based patient monitoring to predict survival outcomes and found that wearable devices (WDs) can be useful prognostic tools for palliative care patients nearing the end of their lives. These devices reported greater angle and spin movements as early as in the first 48 h of observation in cancer patients who were still alive following discharge from a hospice inpatient unit [ 28 , 29 ]. Applied research has explored the applications of ML techniques for health monitoring, elderly care, and fitness tracking in the last decade and is growing over time [ 30 ].…”

Evaluating the pragmatic characteristics of advance care planning outcome measures in dementia clinical trials: A scoping review

“…The use of proxies to help measure patient‐reported outcome measures also may hold some promise for PLWD if viewed as complementary rather than substitutive 66,67 . Emerging data capture methods such as natural language processing (NLP) to measure ACP documentation, patient portals to measure electronic PCROs along with wearable devices, smartphones, and artificial intelligence to help measure prognosis and patient‐related parameters may also yield future highly pragmatic outcome measures 51,68–72 . In ADRD pragmatic trials conducted in the home or community setting, a multi‐level approach will likely need to be considered for the collection of PCROs in the absence of healthcare records or administrative data collection methods 73 …”