Background: Wearable devices could provide important insights about hospitalized patients that include data collected on variations in heart rate, low activity, and poor sleep. Objective: To determine the accuracy of Fitbit heart rate, sleep, and physical activity in patients hospitalized in general medical ward. Methods: We conducted a prospective study enrolling 50 inpatients, and providing them with a Fitbit Charge. Our main measures were Fitbit heart rate, activity, and sleep as well as nurse-recorded heart rate, nurse assessments of activity, and patient-reported sleep. Results: Comparing of heart rate data, the mean difference was 0.45 beats per minute (Pearson correlation: 0.68, P < 0.001). The correlation between nurses’ recorded activity and Fitbit daily steps was 0.06 (P = 0.52). The association between patient-reported sleep score and Fitbit total sleep duration was 0.19 (P = 0.24). Conclusions: Fitbit heart rate appeared to be correlated well with nurse-recorded heart rate, but Fitbit mea-surements of activity and sleep did not correlate well with corresponding assessments. RésuméContexte: Les appareils intelligents portables peuvent fournir des renseignements importants sur les patients hospitalisés tels que des données sur les variations de la fréquence cardiaque, le manque d’activité physique et le manque de sommeil. Objectif: Déterminer l’exactitude des données sur la fréquence cardiaque, le sommeil et l’activité physique recueillies par la montre Fitbit chez les patients hospitalisés. Méthodologie: Nous avons mené une étude prospective sur 50 patients hospitalisés à qui nous avons fourni une montre Fitbit Charge. Nos principales mesures sont la fréquence cardiaque, le niveau d’activité et la durée du sommeil mesurés par la montre Fitbit, de même que les fréquences cardiaques consignées par les infirmières, les évaluations de l’activité par les infirmières et le sommeil déclaré par les patients. Résultats: En comparant les données sur la fréquence cardiaque, la différence moyenne est de 0.45 bpm (corrélation de Pearson: 0.68, P < 0.001). La corrélation entre l’activité consignée par l’infirmière et le nombre de pas quotidiens enregistrés par la montre Fitbit est de 0.06 (P = 0.52). L’association entre le score de sommeil déclaré par le patient et la durée totale de sommeil enregistrée par la montre Fitbit est de 0.19 (P = 0.24). Conclusions: La fréquence cardiaque mesurée par la montre Fitbitsemble bien corrélée avec celle consignée par l’infirmière, mais les mesures Fitbit concernant l’activité et le sommeil ne sont pas bien corrélées avec les évaluations correspondantes.
BackgroundWearable devices such as Fitbits may provide important insights about hospitalized patients that include data on low activity and poor sleep. Monitoring this information could spur interventions to improve mobility and sleep which may reduce the adverse effects associated with hospitalization. However, there is a lack of studies assessing the accuracy of wearables in hospitalized medical patients. The purpose of our study was to determine the accuracy of Fitbit heart rate, sleep and physical activity in hospitalized medical patients.MethodsWe conducted a prospective cohort feasibility study enrolling 50 medical inpatients at two hospitals providing them with a Fitbit Charge. Our main measures were Fitbit heart rate, sleep and activity data as well as nurse recorded heart rates, patient reported sleep, and nurse assessments of activity.ResultsOf the 50 patients who consented to the study, 47 patients wore the devices. Comparing pairs of heart rate data from Fitbit and nurse recorded vital signs for the same minute, there were 261 pairs available for comparison. The mean difference was 0.45 bpm (SD: 13.0, Pearson correlation: 0.68 P<0.001) and the 95% limits of agreement were -25 to 26 bpm. The association between the patient-reported sleep score and Fitbit total sleep duration was 0.19 (P=0.24) and between the self-reported hours of sleep and Fitbit total sleep duration was 0.21 (P=0.21). The correlation between nurse-recorded activity and Fitbit daily steps was 0.06 (P=0.52). ConclusionsFitbit heart rates correlated well with nurse-recorded heart rate but did not correlate well with nurse assessments of activity nor with patient self-assessment of sleep. This study highlights limitations of the accuracy of current wearable wrist-worn device algorithms in activity and sleep detection in patients in hospital. The findings call into question the validity of Fitbits for assessment of patient activity and sleep in the hospital setting and suggest that they should not be routinely used without further validation.Trial RegistrationClinicalTrials.gov NCT03646435
Introduction: Free flap surgery encompasses reconstruction of diverse tissue defects. Flap failure and complications such as infection and ischemia remain a concern following flap surgery, with the current post-operative standard of care being frequent bedside monitoring. Artificial intelligence such as machine learning models could help support surgeons in postoperative monitoring and predicting complications. The purpose of this systematic review is to provide the framework for a review analyzing the existing literature behind the use of artificial intelligence in assessing flap surgery outcomes and predicting postoperative complications. Methods: A systematic review will be conducted using EMBASE and MEDLINE (1974 to October 2021) to identify relevant literature. This will include studies investigating Artificial Intelligence and machine learning models used in the postoperative setting of flap surgery. Primary outcomes will include evaluating the accuracy of evaluating outcomes following flap surgery based on these models, including: flap success, healing and complications up to 1 month following surgery. Secondary outcomes include the analysis of benefits and drawbacks of using machine learning models for outcomes following flap surgery. Studies will be screened by two independent reviewers; risk of bias will be assessed using the Cochrane risk of bias tool with methodological quality assessed using the QUADAS-2 tool. Discussion: This protocol will provide the framework for a review summarizing the current literature exploring the role of Artificial Intelligence for flap surgery outcomes. Results will help provide surgeons with an overview of current applications and identify areas of potential further research and development. Conclusion: As current clinical practice is regular bedside monitoring, integrating Artificial Intelligence could make the process more efficient, accurate and safer for patients and reduce labour burden or healthcare system costs. This review can help identify areas of potential and improvement which could further aid achieving successful outcomes following flap surgery.
Background: Wearable devices such as Fitbits may provide important insights about hospitalized patients that include data on low activity and poor sleep. Monitoring this information could spur interventions to improve mobility and sleep which may reduce the adverse effects associated with hospitalization. However, there is a lack of studies assessing the accuracy of wearables in hospitalized medical patients. The purpose of our study was to determine the accuracy of Fitbit heart rate, sleep and physical activity in hospitalized medical patients.Methods: We conducted a prospective cohort feasibility study enrolling 50 medical inpatients at two hospitals providing them with a wrist-worn Fitbit Charge. Our main measures were Fitbit heart rate, sleep and activity data as well as nurse recorded heart rates, patient reported sleep, and nurse assessments of activity.Results: Of the 50 patients who consented to the study, 47 patients wore the devices. Comparing pairs of heart rate data from Fitbit and nurse recorded vital signs for the same minute, there were 261 pairs available for comparison. The mean difference was 0.45 bpm (SD: 13.0, Pearson correlation: 0.68 P<0.001) and the 95% limits of agreement were -25 to 26 bpm. The association between the patient-reported sleep score and Fitbit total sleep duration was 0.19 (P=0.24) and between the self-reported hours of sleep and Fitbit total sleep duration was 0.21 (P=0.21). The correlation between nurse-recorded activity and Fitbit daily steps was 0.06 (P=0.52). Conclusions: Fitbit heart rates correlated well with nurse-recorded heart rate but did not correlate well with nurse assessments of activity nor with patient self-assessment of sleep. This study highlights limitations of the accuracy of current wearable wrist-worn device algorithms in activity and sleep detection in patients in hospital. The findings call into question the validity of Fitbits for assessment of patient activity and sleep in the hospital setting and suggest that they should not be routinely used without further validation.Trial Registration: ClinicalTrials.gov NCT03646435
Thank you for providing your input in this study. Please have a look at the printed summary graphs of your patients' data.By completing this survey, you are providing consent to the use of the below responses for research study purposes. You have been informed that your participation in this research study will remain strictly confidential and will have no impact on the status of your employment.Please answer the following on a scale of 1 to 10 where 1 is Strongly disagree and 10 is Strongly agree or 'Do not know':1. The Fitbit heart rate was accurate for your patient.2. The Fitbit sleep assessment was accurate.3. The Fitbit activity assessment was accurate.4. The data provided from the Fitbits could provide important added information on my patients.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
334 Leonard St
Brooklyn, NY 11211
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.