A Batch and Real-time Data Analytics Framework for Healthcare Applications (original) (raw)
Related papers
The New American Journal of Medicine, 2021
National Early Warning Score (NEWS) 2 was developed by the Royal College of Physicians to be used as early detection of in-hospital patient deterioration. The score has been shown to improve prognosis and triage efficiency. While the benefit of using a triage system has been established, in the real world, inefficient manual data entry and human error contribute to possible delays in identifying patients requiring intensive care transfers. Our team wanted to create an automated predictive model using informatics to improve the quality of patient care and healthcare provider workflow efficiency to identify high-risk patients who would benefit from early interventions by rapid-response teams.
Early warning score using electronically-held data for patients discharged from intensive care units
2020
Rationale. Intensive care units (ICUs) admit the most severely ill patients. Once these patients are discharged from the ICU to a step-down ward, they continue to have their vital signs monitored by nursing staff, with early warning score (EWS) systems being used to identify those at risk of deterioration. Objectives. We report the development and validation of an enhanced continuous scoring system for predicting adverse events, which combines vital signs measured routinely on acute care wards (as used by most EWSs) with a risk score of a future adverse event calculated on discharge from ICU. Methods. A modified Delphi process identified common, and candidate variables frequently collected and stored in electronic records as the basis for a ‗static' score of the patient's condition immediately after discharge from the ICU. L1-regularised logistic regression was used to estimate the in-hospital risk of future adverse event. We then constructed a model of physiological normality using vital-sign data from the day of hospital discharge, which is combined with the static score and used continuously to quantify and update the patient's risk of deterioration throughout their hospital stay. Data from two NHS Foundation Trusts (UK) were used to develop and (externally) validate the model. Measurements and Main Results. A total of 12,394 vital-sign measurements were acquired from 273 patients after ICU discharge for the development set, and 4,831 from 136 patients in the validation cohort. Outcome validation of our model yielded an area under the receiver operating characteristic curve (AUROC) of 0.724 for predicting ICU re-admission or in-hospital death within 24h. It showed an improved performance with respect to other competitive risk scoring systems, including the National EWS (NEWS, 0.653). Conclusion. We showed that a scoring system incorporating data from a patient's stay in ICU has better performance than commonly-used EWS systems based on vital signs alone.
Integrated monitoring and analysis for early warning of patient deterioration
British Journal of Anaesthesia, 2006
Recently there has been an upsurge of interest in strategies for detecting at-risk patients in order to trigger the timely intervention of a Medical Emergency Team (MET), also known as a Rapid Response Team (RRT). We review a real-time automated system, BioSign, which tracks patient status by combining information from vital signs monitored non-invasively on the general ward. BioSign fuses the vital signs in order to produce a single-parameter representation of patient status, the Patient Status Index. The data fusion method adopted in BioSign is a probabilistic model of normality in five dimensions, previously learnt from the vital sign data acquired from a representative sample of patients. BioSign alerts occur either when a single vital sign deviates by close to ±3 standard deviations from its normal value or when two or more vital signs depart from normality, but by a smaller amount. In a trial with high-risk elective/emergency surgery or medical patients, BioSign alerts were generated, on average, every 8 hours; 95% of these were classified as 'True' by clinical experts. Retrospective analysis has also shown that the data fusion algorithm in BioSign is capable of detecting critical events in advance of single-channel alerts.
Resuscitation
Aims: International early warning scores (EWS) including the additive National Early Warning Score (NEWS) and logistic EWS currently utilise physiological snapshots to predict clinical deterioration. We hypothesised that a dynamic score including vital sign trajectory would improve discriminatory power. Methods: Multicentre retrospective analysis of electronic health record data from postoperative patients admitted to cardiac surgical wards in four UK hospitals. Least absolute shrinkage and selection operator-type regression (LASSO) was used to develop a dynamic model (DyniEWS) to predict a composite adverse event of cardiac arrest, unplanned intensive care re-admission or in-hospital death within 24 h. Results: A total of 13,319 postoperative adult cardiac patients contributed 442,461 observations of which 4234 (0.96%) adverse events in 24 h were recorded. The new dynamic model (AUC = 0.80 [95% CI 0.78À0.83], AUPRC = 0.12 [0.10À0.14]) outperforms both an updated snapshot logistic model (AUC = 0.76 [0.73À0.79], AUPRC = 0.08 [0.60À0.10]) and the additive National Early Warning Score (AUC = 0.73 [0.70À0.76], AUPRC = 0.05 [0.02 À0.08]). Controlling for the false alarm rates to be at current levels using NEWS cutoffs of 5 and 7, DyniEWS delivers a 7% improvement in balanced accuracy and increased sensitivities from 41% to 54% at NEWS 5 and 18%À30% at NEWS 7. Conclusions: Using an advanced statistical approach, we created a model that can detect dynamic changes in risk of unplanned readmission to intensive care, cardiac arrest or in-hospital mortality and can be used in real time to risk-prioritise clinical workload.
Critical Care Medicine, 2011
We sought to develop an intensive care unit research database applying automated techniques to aggregate high-resolution diagnostic and therapeutic data from a large, diverse population of adult intensive care unit patients. This freely available database is intended to support epidemiologic research in critical care medicine and serve as a resource to evaluate new clinical decision support and monitoring algorithms. Design: Data collection and retrospective analysis. Setting: All adult intensive care units (medical intensive care unit, surgical intensive care unit, cardiac care unit, cardiac surgery recovery unit) at a tertiary care hospital. Patients: Adult patients admitted to intensive care units between 2001 and 2007. Interventions: None. Measurements and Main Results: The Multiparameter Intelligent Monitoring in Intensive Care II (MIMIC-II) database consists of 25,328 intensive care unit stays. The investigators collected detailed information about intensive care unit patient stays, including laboratory data, therapeutic intervention profiles such as vasoactive medication drip rates and ventilator settings, nursing progress notes, discharge summaries, radiology reports, provider order entry data, International Classification of Diseases, 9th Revision codes, and, for a subset of patients, high-resolution vital sign trends and waveforms. Data were automatically deidentified to comply with Health Insurance Portabil-ity and Accountability Act standards and integrated with relational database software to create electronic intensive care unit records for each patient stay. The data were made freely available in February 2010 through the Internet along with a detailed user's guide and an assortment of data processing tools. The overall hospital mortality rate was 11.7%, which varied by critical care unit. The median intensive care unit length of stay was 2.2 days (interquartile range, 1.1-4.4 days). According to the primary International Classification of Diseases, 9th Revision codes, the following disease categories each comprised at least 5% of the case records: diseases of the circulatory system (39.1%); trauma (10.2%); diseases of the digestive system (9.7%); pulmonary diseases (9.0%); infectious diseases (7.0%); and neoplasms (6.8%). Conclusions: MIMIC-II documents a diverse and very large population of intensive care unit patient stays and contains comprehensive and detailed clinical data, including physiological waveforms and minute-by-minute trends for a subset of records. It establishes a new public-access resource for critical care research, supporting a diverse range of analytic studies spanning epidemiology, clinical decision-rule development, and electronic tool development.
Toward a two-tier clinical warning system for hospitalized patients
AMIA ... Annual Symposium proceedings. AMIA Symposium, 2011
Clinical study has found early detection and intervention to be essential for preventing clinical deterioration in patients at general hospital units. In this paper, we envision a two-tiered early warning system designed to identify the signs of clinical deterioration and provide early warning of serious clinical events. The first tier of the system automatically identifies patients at risk of clinical deterioration from existing electronic medical record databases. The second tier performs real-time clinical event detection based on real-time vital sign data collected from on-body wireless sensors attached to those high-risk patients. We employ machine-learning techniques to analyze data from both tiers, assigning scores to patients in real time. The assigned scores can then be used to trigger early-intervention alerts. Preliminary study of an early warning system component and a wireless clinical monitoring system component demonstrate the feasibility of this two-tiered approach.
Journal of Multidisciplinary Healthcare, 2021
To evaluate the effect of national early warning scoring system (NEWS) implementation in identifying patients at risk of clinical deterioration at an emergency hospital. Background: Early warning score has been developed to facilitate early detection of deterioration by categorizing a patients' severity of illness and prompting nursing staff to request a medical review at specific trigger points. Patients and Methods: A prospective, control/intervention groups', quasi-experimental design was utilized. A sample of 364 adult patients were admitted to the inpatient unit at an emergency hospital for six months. The patients were divided into a study group (174 patients) and a control group (190 patients). All study patients were followed up to either death or hospital discharge before and after implementing a new observation chart. The patients' outcomes were compared and analyzed between both groups. Results: In the intervention period, compared to the control period, a significant reduction was seen in the number of cardiopulmonary arrest (4.7% vs 1.1%, p = 0.046), unplanned ICU admission (5.3% vs 1.7%, p = 0.049), emergency surgery (6.3% vs 0%, p = 0.001), acute kidney injury (6.8% vs 1.1%, p = 0.006). As well, there was a significant increase in the number of patients receiving medical reviews following clinical deterioration in terms of escalation plan (3.2% vs 26.4%, p = <0.001). Conclusion: The implementation of NEWS was associated with a significant improvement in patients' outcomes in hospital wards, increases in the frequency of vital signs measurements, and an increase in the number of medical reviews following clinical instability.
Critical Care, 2011
The survival of patients admitted to an emergency department is determined by the severity of acute illness and the quality of care provided. The high number and the wide spectrum of severity of illness of admitted patients make an immediate assessment of all patients unrealistic. The aim of this study is to evaluate a scoring system based on readily available physiological parameters immediately after admission to an emergency department (ED) for the purpose of identification of at-risk patients. Methods: This prospective observational cohort study includes 4,388 consecutive adult patients admitted via the ED of a 960-bed tertiary referral hospital over a period of six months. Occurrence of each of seven potential vital sign abnormalities (threat to airway, abnormal respiratory rate, oxygen saturation, systolic blood pressure, heart rate, low Glasgow Coma Scale and seizures) was collected and added up to generate the vital sign score (VSS). VSS initial was defined as the VSS in the first 15 minutes after admission, VSS max as the maximum VSS throughout the stay in ED. Occurrence of single vital sign abnormalities in the first 15 minutes and VSS initial and VSS max were evaluated as potential predictors of hospital mortality. Results: Logistic regression analysis identified all evaluated single vital sign abnormalities except seizures and abnormal respiratory rate to be independent predictors of hospital mortality. Increasing VSS initial and VSS max were significantly correlated to hospital mortality (odds ratio (OR) 2.80, 95% confidence interval (CI) 2.50 to 3.14, P < 0.0001 for VSS initial ; OR 2.36, 95% CI 2.15 to 2.60, P < 0.0001 for VSS max ). The predictive power of VSS was highest if collected in the first 15 minutes after ED admission (log rank Chi-square 468.1, P < 0.0001 for VSS initial ;,log rank Chi square 361.5, P < 0.0001 for VSS max ). Conclusions: Vital sign abnormalities and VSS collected in the first minutes after ED admission can identify patients at risk of an unfavourable outcome.
Monitoring vital signs using early warning scoring systems: a review of the literature
Journal of Nursing Management, 2011
Monitoring vital signs using early warning scoring systems: a review of the literature Aim To evaluate the need for, and the development and utility of, pen-and-paper (Modified) Early Warning Scoring (MEWS/EWS) systems for adult inpatients outside critical care and emergency departments, by reviewing published literature. Background Serious adverse events can be prevented by recognizing and responding to early signs of clinical and physiological deterioration. Evaluation Of 534 papers reporting MEWS/EWS systems for adult inpatients identified, 14 contained useable data on development and utility of MEWS/EWS systems. Systems without aggregate weighted scores were excluded. Key issues MEWS/EWS systems facilitate recognition of abnormal physiological parameters in deteriorating patients, but have limitations. There is no single validated scoring tool across diagnoses. Evidence of prospective validation of MEWS/ EWS systems is limited; neither is implementation based on clinical trials. There is no evidence that implementation of Westernized MEWS/EWS systems is appropriate in resource-poor locations. Conclusions Better monitoring implies better care, but there is a paucity of data on the validation, implementation, evaluation and clinical testing of vital signsÕ monitoring systems in general wards. Implications for nursing management Recording vital signs is not enough. Patient safety continues to depend on nursesÕ clinical judgment of deterioration. Resources are needed to validate and evaluate MEWS/EWS systems in context.