Dataset Information

Automated Fall Detection Algorithm With Global Trigger Tool, Incident Reports, Manual Chart Review, and Patient-Reported Falls: Algorithm Development and Validation With a Retrospective Diagnostic Accuracy Study.

ABSTRACT: BACKGROUND:Falls are common adverse events in hospitals, frequently leading to additional health costs due to prolonged stays and extra care. Therefore, reliable fall detection is vital to develop and test fall prevention strategies. However, conventional methods-voluntary incident reports and manual chart reviews-are error-prone and time consuming, respectively. Using a search algorithm to examine patients' electronic health record data and flag fall indicators offers an inexpensive, sensitive, cost-effective alternative. OBJECTIVE:This study's purpose was to develop a fall detection algorithm for use with electronic health record data, then to evaluate it alongside the Global Trigger Tool, incident reports, a manual chart review, and patient-reported falls. METHODS:Conducted on 2 campuses of a large hospital system in Switzerland, this retrospective diagnostic accuracy study consisted of 2 substudies: the first, targeting 240 patients, for algorithm development and the second, targeting 298 patients, for validation. In the development study, we compared the new algorithm's in-hospital fall rates with those indicated by the Global Trigger Tool and incident reports; in the validation study, we compared the algorithm's in-hospital fall rates with those from patient-reported falls and manual chart review. We compared the various methods by calculating sensitivity, specificity, and predictive values. RESULTS:Twenty in-hospital falls were discovered in the development study sample. Of these, the algorithm detected 19 (sensitivity 95%), the Global Trigger Tool detected 18 (90%), and incident reports detected 14 (67%). Of the 15 falls found in the validation sample, the algorithm identified all 15 (100%), the manual chart review identified 14 (93%), and the patient-reported fall measure identified 5 (33%). Owing to relatively high numbers of false positives based on falls present on admission, the algorithm's positive predictive values were 50% (development sample) and 47% (validation sample). Instead of requiring 10 minutes per case for a full manual review or 20 minutes to apply the Global Trigger Tool, the algorithm requires only a few seconds, after which only the positive results (roughly 11% of the full case number) require review. CONCLUSIONS:The newly developed electronic health record algorithm demonstrated very high sensitivity for fall detection. Applied in near real time, the algorithm can record in-hospital falls events effectively and help to develop and test fall prevention measures.

SUBMITTER: Dolci E

PROVIDER: S-EPMC7536608 | biostudies-literature | 2020 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Automated Fall Detection Algorithm With Global Trigger Tool, Incident Reports, Manual Chart Review, and Patient-Reported Falls: Algorithm Development and Validation With a Retrospective Diagnostic Accuracy Study.

Dolci Elisa E Schärer Barbara B Grossmann Nicole N Musy Sarah Naima SN Zúñiga Franziska F Bachnick Stefanie S Simon Michael M

Journal of medical Internet research 20200921 9

<h4>Background</h4>Falls are common adverse events in hospitals, frequently leading to additional health costs due to prolonged stays and extra care. Therefore, reliable fall detection is vital to develop and test fall prevention strategies. However, conventional methods-voluntary incident reports and manual chart reviews-are error-prone and time consuming, respectively. Using a search algorithm to examine patients' electronic health record data and flag fall indicators offers an inexpensive, se ...[more]

PMID: 32955445

Similar Datasets

Project description:BackgroundExtraction of line-of-therapy (LOT) information from electronic health record and claims data is essential for determining longitudinal changes in systemic anticancer therapy in real-world clinical settings.ObjectiveThe aim of this retrospective cohort analysis is to validate and refine our previously described open-source LOT algorithm by comparing the output of the algorithm with results obtained through blinded manual chart review.MethodsWe used structured electronic health record data and clinical documents to identify 500 adult patients treated for metastatic non-small cell lung cancer with systemic anticancer therapy from 2011 to mid-2018; we assigned patients to training (n=350) and test (n=150) cohorts, randomly divided proportional to the overall ratio of simple:complex cases (n=254:246). Simple cases were patients who received one LOT and no maintenance therapy; complex cases were patients who received more than one LOT and/or maintenance therapy. Algorithmic changes were performed using the training cohort data, after which the refined algorithm was evaluated against the test cohort.ResultsFor simple cases, 16 instances of discordance between the LOT algorithm and chart review prerefinement were reduced to 8 instances postrefinement; in the test cohort, there was no discordance between algorithm and chart review. For complex cases, algorithm refinement reduced the discordance from 68 to 62 instances, with 37 instances in the test cohort. The percentage agreement between LOT algorithm output and chart review for patients who received one LOT was 89% prerefinement, 93% postrefinement, and 93% for the test cohort, whereas the likelihood of precise matching between algorithm output and chart review decreased with an increasing number of unique regimens. Several areas of discordance that arose from differing definitions of LOTs and maintenance therapy could not be objectively resolved because of a lack of precise definitions in the medical literature.ConclusionsOur findings identify common sources of discordance between the LOT algorithm and clinician documentation, providing the possibility of targeted algorithm refinement.

Project description:Intravascular continuous glucose monitoring (CGM) may facilitate glycemic control in the intensive care unit (ICU). We compared the accuracy of a CGM device (OptiScanner®) with a standard reference method.Adult patients who had blood glucose (BG) levels >150 mg/dl and required insertion of an arterial and central venous catheter were included. The OptiScanner® was inserted into a multiple-lumen central venous catheter. Patients were treated using a dynamic-scale insulin algorithm to achieve BG values between 80 and 150 mg/dl. The BG values measured by the OptiScanner® were plotted against BG values measured using a reference analyzer. The correlation between the BG values measured using the two methods and the clinical relevance of any differences were assessed using the coefficient of determination (r 2) and the Clarke error grid, respectively; bias was assessed by the mean absolute relative difference (MARD). Three different standards of glucose monitoring were used to assess accuracy. Glycemic control was assessed using the time in range (TIR). Six indices of glycemic variability were calculated.The analysis included 929 paired samples from 88 patients, monitored for a total of 2584 hours. Reference BG values ranged between 60 and 484 mg/dl. The r 2 value was 0.89. The percentage of BG values within zones A and B of the Clarke error grid was 99.9%; the MARD was 7.7%. Using the ISO 15197 standard and Food and Drug Administration and consensus standards, respectively, 80.4% of measurements were within 15 mg/dl and 88.2% within 15% of reference values, 40% of measurements were within 7 mg/dl and 72.5% within 10% of reference values, and 65.2% of measurements were within 10 mg/dl and 82.7% within 12.5% of reference values. The TIR was slightly lower with the OptiScanner® than with the reference method. The J-index, standard deviation and maximal glucose change were the indices of glycemic variability least affected by the measurement device.Based on the MARD, the performance of the OptiScanner® is adequate for use in ICU patients. Because recent standards for accuracy were not met, the OptiScanner® should not be used as a sole monitor. The assessment of glycemic variability is influenced by the time interval between BG determinations.Clinicaltrials.gov NCT01720381 . Registered 31 October 2012.

Project description:Background and Objectives: Falls account for the highest proportion of preventable injury among older adults. Thus, the United States' Centers for Disease Control and Prevention (CDC) developed the Stopping Elderly Accidents, Deaths, and Injuries (STEADI) algorithm to screen for fall risk. We referred to our STEADI algorithm adaptation as "Quick-STEADI" and compared the predictive abilities of the three-level (low, moderate, and high risk) and two-level (at-risk and not at-risk) Quick-STEADI algorithms. We additionally assessed the qualitative implementation of the Quick-STEADI algorithm in clinical settings. Research Design and Methods: We followed a prospective cohort (N = 200) of adults (65+ years) in the Bassett Healthcare Network (Cooperstown, NY) for 6 months in 2019. We conducted a generalized linear mixed model, adjusting for sociodemographic variables, to determine how baseline fall risk predicted subsequent daily falls. We plotted receiver operating characteristic (ROC) curves and measured the area under the curve (AUC) to determine the predictive ability of the Quick-STEADI algorithm. We identified a participant sample (N = 8) to gauge the experience of the screening process and a screener sample (N = 3) to evaluate the screening implementation. Results: For the three-level Quick-STEADI algorithm, participants at low and moderate risk for falls had a reduced likelihood of daily falls compared to those at high risk (-1.09, p = 0.04; -0.99, p = 0.04). For the two-level Quick-STEADI algorithm, participants not at risk for falls were not associated with a reduced likelihood of daily falls compared to those at risk (-0.89, p = 0.13). The discriminatory ability of the three-level and two-level Quick-STEADI algorithm demonstrated similar predictability of daily falls, based on AUC (0.653; 0.6570). Furthermore, participants and screeners found the Quick-STEADI algorithm to be efficient and viable. Discussion and Implications: The Quick-STEADI is a suitable, alternative fall risk screening algorithm. Qualitative assessments of the Quick-STEADI algorithm demonstrated feasibility in integrating a falls screening program in a clinical setting. Future research should address the validation and the implementation of the Quick-STEADI algorithm in community health settings to determine if falls screening and prevention can be streamlined in these settings. This may increase engagement in fall prevention programs and decrease overall fall risk among older adults.

Project description:ObjectivesWe examined whether providing a quantitative report (QReport) of regional brain volumes improves radiologists' accuracy and confidence in detecting volume loss, and in differentiating Alzheimer's disease (AD) and frontotemporal dementia (FTD), compared with visual assessment alone.MethodsOur forced-choice multi-rater clinical accuracy study used MRI from 16 AD patients, 14 FTD patients, and 15 healthy controls; age range 52-81. Our QReport was presented to raters with regional grey matter volumes plotted as percentiles against data from a normative population (n = 461). Nine raters with varying radiological experience (3 each: consultants, registrars, 'non-clinical image analysts') assessed each case twice (with and without the QReport). Raters were blinded to clinical and demographic information; they classified scans as 'normal' or 'abnormal' and if 'abnormal' as 'AD' or 'FTD'.ResultsThe QReport improved sensitivity for detecting volume loss and AD across all raters combined (p = 0.015* and p = 0.002*, respectively). Only the consultant group's accuracy increased significantly when using the QReport (p = 0.02*). Overall, raters' agreement (Cohen's κ) with the 'gold standard' was not significantly affected by the QReport; only the consultant group improved significantly (κs 0.41➔0.55, p = 0.04*). Cronbach's alpha for interrater agreement improved from 0.886 to 0.925, corresponding to an improvement from 'good' to 'excellent'.ConclusionOur QReport referencing single-subject results to normative data alongside visual assessment improved sensitivity, accuracy, and interrater agreement for detecting volume loss. The QReport was most effective in the consultants, suggesting that experience is needed to fully benefit from the additional information provided by quantitative analyses.Key points• The use of quantitative report alongside routine visual MRI assessment improves sensitivity and accuracy for detecting volume loss and AD vs visual assessment alone. • Consultant neuroradiologists' assessment accuracy and agreement (kappa scores) significantly improved with the use of quantitative atrophy reports. • First multi-rater radiological clinical evaluation of visual quantitative MRI atrophy report for use as a diagnostic aid in dementia.

Project description:ObjectiveThe study sought to evaluate the feasibility of using Unified Medical Language System (UMLS) semantic features for automated identification of reports about patient safety incidents by type and severity.Materials and methodsBinary support vector machine (SVM) classifier ensembles were trained and validated using balanced datasets of critical incident report texts (n_type = 2860, n_severity = 1160) collected from a state-wide reporting system. Generalizability was evaluated on different and independent hospital-level reporting system. Concepts were extracted from report narratives using the UMLS Metathesaurus, and their relevance and frequency were used as semantic features. Performance was evaluated by F-score, Hamming loss, and exact match score and was compared with SVM ensembles using bag-of-words (BOW) features on 3 testing datasets (type/severity: n_benchmark = 286/116, n_original = 444/4837, n_independent =6000/5950).ResultsSVMs using semantic features met or outperformed those based on BOW features to identify 10 different incident types (F-score [semantics/BOW]: benchmark = 82.6%/69.4%; original = 77.9%/68.8%; independent = 78.0%/67.4%) and extreme-risk events (F-score [semantics/BOW]: benchmark = 87.3%/87.3%; original = 25.5%/19.8%; independent = 49.6%/52.7%). For incident type, the exact match score for semantic classifiers was consistently higher than BOW across all test datasets (exact match [semantics/BOW]: benchmark = 48.9%/39.9%; original = 57.9%/44.4%; independent = 59.5%/34.9%).DiscussionBOW representations are not ideal for the automated identification of incident reports because they do not account for text semantics. UMLS semantic representations are likely to better capture information in report narratives, and thus may explain their superior performance.ConclusionsUMLS-based semantic classifiers were effective in identifying incidents by type and extreme-risk events, providing better generalizability than classifiers using BOW.

Project description:Despite extensive preventive efforts, falls continue to be a major source of morbidity and mortality among elderly. Real-time detection of falls and their urgent communication to a telecare center may enable rapid medical assistance, thus increasing the sense of security of the elderly and reducing some of the negative consequences of falls. Many different approaches have been explored to automatically detect a fall using inertial sensors. Although previously published algorithms report high sensitivity (SE) and high specificity (SP), they have usually been tested on simulated falls performed by healthy volunteers. We recently collected acceleration data during a number of real-world falls among a patient population with a high-fall-risk as part of the SensAction-AAL European project. The aim of the present study is to benchmark the performance of thirteen published fall-detection algorithms when they are applied to the database of 29 real-world falls. To the best of our knowledge, this is the first systematic comparison of fall detection algorithms tested on real-world falls. We found that the SP average of the thirteen algorithms, was (mean ± std) 83.0% ± 30.3% (maximum value = 98%). The SE was considerably lower (SE = 57.0% ± 27.3%, maximum value = 82.8%), much lower than the values obtained on simulated falls. The number of false alarms generated by the algorithms during 1-day monitoring of three representative fallers ranged from 3 to 85. The factors that affect the performance of the published algorithms, when they are applied to the real-world falls, are also discussed. These findings indicate the importance of testing fall-detection algorithms in real-life conditions in order to produce more effective automated alarm systems with higher acceptance. Further, the present results support the idea that a large, shared real-world fall database could, potentially, provide an enhanced understanding of the fall process and the information needed to design and evaluate a high-performance fall detector.

Dataset Information

Automated Fall Detection Algorithm With Global Trigger Tool, Incident Reports, Manual Chart Review, and Patient-Reported Falls: Algorithm Development and Validation With a Retrospective Diagnostic Accuracy Study.

Publications

Automated Fall Detection Algorithm With Global Trigger Tool, Incident Reports, Manual Chart Review, and Patient-Reported Falls: Algorithm Development and Validation With a Retrospective Diagnostic Accuracy Study.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets