Dataset Information

VitalDB, a high-fidelity multi-parameter vital signs database in surgical patients.

ABSTRACT: In modern anesthesia, multiple medical devices are used simultaneously to comprehensively monitor real-time vital signs to optimize patient care and improve surgical outcomes. However, interpreting the dynamic changes of time-series biosignals and their correlations is a difficult task even for experienced anesthesiologists. Recent advanced machine learning technologies have shown promising results in biosignal analysis, however, research and development in this area is relatively slow due to the lack of biosignal datasets for machine learning. The VitalDB (Vital Signs DataBase) is an open dataset created specifically to facilitate machine learning studies related to monitoring vital signs in surgical patients. This dataset contains high-resolution multi-parameter data from 6,388 cases, including 486,451 waveform and numeric data tracks of 196 intraoperative monitoring parameters, 73 perioperative clinical parameters, and 34 time-series laboratory result parameters. All data is stored in the public cloud after anonymization. The dataset can be freely accessed and analysed using application programming interfaces and Python library. The VitalDB public dataset is expected to be a valuable resource for biosignal research and development.

SUBMITTER: Lee HC

PROVIDER: S-EPMC9178032 | biostudies-literature | 2022 Jun

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

VitalDB, a high-fidelity multi-parameter vital signs database in surgical patients.

Lee Hyung-Chul HC Park Yoonsang Y Yoon Soo Bin SB Yang Seong Mi SM Park Dongnyeok D Jung Chul-Woo CW

Scientific data 20220608 1

In modern anesthesia, multiple medical devices are used simultaneously to comprehensively monitor real-time vital signs to optimize patient care and improve surgical outcomes. However, interpreting the dynamic changes of time-series biosignals and their correlations is a difficult task even for experienced anesthesiologists. Recent advanced machine learning technologies have shown promising results in biosignal analysis, however, research and development in this area is relatively slow due to th ...[more]

PMID: 35676300

Similar Datasets

Project description:BackgroundPatient safety during anesthesia is crucially dependent on the monitoring of vital signs. However, the values obtained must also be perceived and correctly classified by the attending care providers. To facilitate these processes, we developed Visual-Patient-avatar, an animated virtual model of the monitored patient, which innovatively presents numerical and waveform data following user-centered design principles. After a high-fidelity simulation study, we analyzed the participants' perceptions of 3 different monitor modalities, including this newly introduced technique.ObjectiveThe aim of this study was to collect and evaluate participants' opinions and experiences regarding 3 different monitor modalities, which are Visual-Patient-avatar, Split Screen (avatar and Conventional monitor alongside each other), and Conventional monitor after using them during simulated critical anesthetic events.MethodsThis study was a researcher-initiated, single-center, semiquantitative study. We asked 92 care providers right after finishing 3 simulated emergency scenarios about their positive and negative opinions concerning the different monitor modalities. We processed the field notes obtained and derived the main categories and corresponding subthemes following qualitative research methods.ResultsWe gained a total of 307 statements. Through a context-based analysis, we identified the 3 main categories of "Visual-Patient-avatar," "Split Screen," and "Conventional monitor" and divided them into 11 positive and negative subthemes. We achieved substantial interrater reliability in assigning the statements to 1 of the topics. Most of the statements concerned the design and usability features of the avatar or the Split Screen mode.ConclusionsThis study semiquantitatively reviewed the clinical applicability of the Visual-Patient-avatar technique in a high-fidelity simulation study and revealed the strengths and limitations of the avatar only and Split Screen modality. In addition to valuable suggestions for improving the design, the requirement for training prior to clinical implementation was emphasized. The responses to the Split Screen suggest that this symbiotic modality generates better situation awareness in combination with numerical data and accurate curves. As a subsequent development step, a real-life introduction study is planned, where we will test the avatar in Split Screen mode under actual clinical conditions.

Project description:ObjectiveTo determine feasibility, in terms of acceptability and system fidelity, of continuous vital signs monitoring in abdominal surgery patients on a general ward.DesignObservational cohort study.SettingTertiary teaching hospital.ParticipantsPostoperative abdominal surgical patients (n=30) and nurses (n=23).InterventionsPatients were continuously monitored with the SensiumVitals wearable device until discharge in addition to usual care, which is intermittent Modified Early Warning Score measurements. Heart rate, respiratory rate and axillary temperature were monitored every 2 min. Values and trends were visualised and alerts sent to the nurses.OutcomesSystem fidelity was measured by analysis of the monitoring data. Acceptability by patients and nurses was assessed using questionnaires.ResultsThirty patients were monitored for a median duration of 81 hours (IQR 47-143) per patient, resulting in 115 217 measurements per parameter. In total, 19% (n=21 311) of heart rate, 51% (n=59 184) of respiratory rate and 9% of temperature measurements showed artefacts (n=10 269). The system algorithm sent 972 alerts (median alert rate of 4.5 per patient per day), of which 90.3% (n=878) were system alerts and 9.7% (n=94) were vital sign alerts. 35% (n=33) of vital sign alerts were true positives. 93% (n=25) of patients rated the patch as comfortable, 67% (n=18) felt safer and 89% (n=24) would like to wear it next time in the hospital. Nurses were neutral about usefulness, with a median score of 3.5 (IQR 3.1-4) on a 7-point Likert scale, ease of use 3.7 (IQR 3.2-4.8) and satisfaction 3.7 (IQR 3.2-4.8), but agreed on ease of learning at 5.0 (IQR 4.0-5.8). Neutral scores were mostly related to the perceived limited fidelity of the system.ConclusionsContinuous monitoring of vital signs with a wearable device was well accepted by patients. Nurses' ratings were highly variable, resulting in on average neutral attitude towards remote monitoring. Our results suggest it is feasible to monitor vital signs continuously on general wards, although acceptability of the device among nurses needs further improvement.

Project description:BackgroundPatients are at risk of myocardial injury after major non-cardiac surgery and during acute illness. Myocardial injury is associated with mortality, but often asymptomatic and currently detected through intermittent cardiac biomarker screening. This delays diagnosis, where vital signs deviations may serve as a proxy for early signs of myocardial injury. This study aimed to assess the association between continuous monitored vital sign deviations and subsequent myocardial injury following major abdominal cancer surgery and during acute exacerbation of chronic obstructive pulmonary disease.MethodsPatients undergoing major abdominal cancer surgery or admitted with acute exacerbation of chronic obstructive pulmonary disease had daily troponin measurements. Continuous wireless monitoring of several vital signs was performed for up to 96 h after admission or surgery. The primary exposure was cumulative duration of peripheral oxygen saturation (SpO2 ) below 85% in the 24 h before the primary outcome of myocardial injury, defined as a new onset ischaemic troponin elevation assessed daily. If no myocardial injury occurred, the primary exposure was based on the first 24 h of measurement.ResultsA total of 662 patients were continuously monitored and 113 (17%) had a myocardial injury. Cumulative duration of SpO2 < 85% was significantly associated with myocardial injury (mean difference 14.2 min [95% confidence interval -4.7 to 33.1 min]; p = .005). Durations of hypoxaemia (SpO2 < 88% and SpO2 < 80%), tachycardia (HR > 110 bpm and HR > 130 bpm) and tachypnoea (RR > 24 min-1 and RR > 30 min-1 ) were also significantly associated with myocardial injury (p < .04, for all).ConclusionDuration of severely low SpO2 detected by continuous wireless monitoring is significantly associated with myocardial injury in high-risk patients admitted to hospital wards. The effect of early detection and interventions should be assessed next.

Project description:IntroductionChildren often present to the emergency department (ED) with minor conditions such as fever and have persistently abnormal vital signs. We hypothesized that a significant portion of children discharged from the ED would have abnormal vital signs and that those discharged with abnormal vital signs would experience very few adverse events.MethodsWe performed a retrospective chart review encompassing a 44-month period of all pediatric patients (aged two months to 17 years) who were discharged from the ED with an abnormal pulse rate, respiratory rate, temperature, or oxygen saturation. We used a local quality assurance database to identify pre-defined adverse events after discharge in this population. Our primary aim was to determine the proportion of children discharged with abnormal vital signs and the frequency and nature of adverse events. Additionally, we performed a sub-analysis comparing the rate of adverse events in children discharged with normal vs. abnormal vital signs, as well as a standardized review of the nature of each adverse event.ResultsOf 33,185 children discharged during the study period, 5,540 (17%) of these patients had at least one abnormal vital sign. There were 24/5,540 (0.43%) adverse events in the children with at least one abnormal vital sign vs. 47/27,645 (0.17%) adverse events in the children with normal vital signs [relative risk = 2.5 (95% confidence interval, 1.6 to 2.4)].However, upon review of each adverse event we found only one case that was related to the index visit, was potentially preventable by a 23-hour hospital observation, and caused permanent disability.ConclusionIn our study population, 17% of the children were discharged with at least one abnormal vital sign, and there were very few adverse (0.43%) events associated with this practice. Heart rate was the most common abnormal vital sign leading to an adverse event. Severe adverse events that were potentially related to the abnormal vital sign(s) were exceedingly rare. Additional research is needed in broader populations to better determine the rate of adverse events and possible methods of avoiding them.

Dataset Information

VitalDB, a high-fidelity multi-parameter vital signs database in surgical patients.

Publications

VitalDB, a high-fidelity multi-parameter vital signs database in surgical patients.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets