scholarly journals Comparing the predictive ability of a commercial artificial intelligence early warning system with physician judgement for clinical deterioration in hospitalised general internal medicine patients: a prospective observational study

BMJ Open ◽  
2019 ◽  
Vol 9 (10) ◽  
pp. e032187
Author(s):  
Jonathan Arnold ◽  
Alex Davis ◽  
Baruch Fischhoff ◽  
Emmanuelle Yecies ◽  
Jon Grace ◽  
...  
Keyword(s):  
Internal Medicine ◽  
Observational Study ◽  
General Internal Medicine ◽  
Early Warning ◽  
Early Warning System ◽  
Prospective Observational Study ◽  
Warning System ◽  
Clinical Deterioration ◽  
Receiver Operating Curve ◽  
General Internal

ObjectiveOur study compares physician judgement with an automated early warning system (EWS) for predicting clinical deterioration of hospitalised general internal medicine patients.DesignProspective observational study of clinical predictions made at the end of the daytime work-shift for an academic general internal medicine floor team compared with the risk assessment from an automated EWS collected at the same time.SettingInternal medicine teaching wards at a single tertiary care academic medical centre in the USA.ParticipantsIntern physicians working on the internal medicine wards and an automated EWS (Rothman Index by PeraHealth).OutcomeClinical deterioration within 24 hours including cardiac or pulmonary arrest, rapid response team activation or unscheduled intensive care unit transfer.ResultsWe collected predictions for 1874 patient days and saw 35 clinical deteriorations (1.9%). The area under the receiver operating curve (AUROC) for the EWS was 0.73 vs 0.70 for physicians (p=0.571). A linear regression model combining physician and EWS predictions had an AUROC of 0.75, outperforming physicians (p=0.016) and the EWS (p=0.05).ConclusionsThere is no significant difference in the performance of the EWS and physicians in predicting clinical deterioration at 24 hours on an inpatient general medicine ward. A combined model outperformed either alone. The EWS and physicians identify partially overlapping sets of at-risk patients suggesting they rely on different cues or decision rules for their predictions.Trial registration numberNCT02648828.

scholarly journals Implementing the Bedside Paediatric Early Warning System in a community hospital: A prospective observational study

2011 ◽  
Vol 16 (3) ◽  
pp. e18-e22 ◽  
Author(s):  
Christopher S Parshuram ◽  
Ann Bayliss ◽  
Janette Reimer ◽  
Kristen Middaugh ◽  
Nadeene Blanchard
Keyword(s):  
Observational Study ◽  
Early Warning ◽  
Early Warning System ◽  
Prospective Observational Study ◽  
Community Hospital ◽  
Warning System

Early Warning System Scores for Clinical Deterioration in Hospitalized Patients: A Systematic Review

2014 ◽  
Vol 11 (9) ◽  
pp. 1454-1465 ◽  
Author(s):  
M. E. Beth Smith ◽  
Joseph C. Chiovaro ◽  
Maya O’Neil ◽  
Devan Kansagara ◽  
Ana R. Quiñones ◽  
...  
Keyword(s):  
Systematic Review ◽  
Early Warning ◽  
Early Warning System ◽  
Warning System ◽  
Hospitalized Patients ◽  
Clinical Deterioration

scholarly journals Deep Interpretable Early Warning System for the Detection of Clinical Deterioration

2020 ◽  
Vol 24 (2) ◽  
pp. 437-446 ◽  
Author(s):  
Farah E. Shamout ◽  
Tingting Zhu ◽  
Pulkit Sharma ◽  
Peter J. Watkinson ◽  
David A. Clifton
Keyword(s):  
Early Warning ◽  
Early Warning System ◽  
Warning System ◽  
Clinical Deterioration

The use of Early Warning System Scores in Pre-Hospital and Emergency Department Settings to Predict Clinical Deterioration: s Systematic Review and Meta-Analysis

2021 ◽  
Author(s):  
Gigi Guan ◽  
Crystal Man Ying Lee ◽  
Stephen Begg ◽  
Angela Crombie ◽  
George Mnatzaganian
Keyword(s):  
Systematic Review ◽  
Emergency Department ◽  
Publication Bias ◽  
Early Warning ◽  
Early Warning System ◽  
Meta Analysis ◽  
Hospital Setting ◽  
Warning System ◽  
Clinical Deterioration ◽  
Early Warning Score

Abstract Background: It is unclear which Early Warning System (EWS) score best predicts in-hospital deterioration when applied in the emergency department (ED) or pre-hospital setting. Methods: This systematic review and meta-analysis assessed the predictive abilities of five commonly used EWS scores: National Early Warning Score (NEWS) and its updated version NEWS2, Modified Early Warning Score (MEWS), Rapid Acute Physiological Score (RAPS) and Cardiac Arrest Risk Triage (CART). Outcomes of interest included admission to ICU, up-to-≥3-day and 30-day mortality. Pooled estimates were calculated using DerSimonian and Laird random-effects models, constructed by type of EWS score, cut-off points, outcomes, and study setting. Risk of bias was assessed using the Newcastle-Ottawa Scale. Meta-regressions investigated between study heterogeneity. Funnel plots tested for publication bias. Results: A total of 11,565 articles was identified, of which 15 were included. Eight and seven articles conducted in the ED and pre-hospital settings, respectively. In the ED, MEWS and NEWS at cut-off points of 3, 4, or 6 had similar pooled diagnostic odds ratios (DOR) to predict 30-day mortality, ranging from 4.05 (Confidence Interval (CI) 2.35–6.99) to 6.48 (95% CI 1.83–22.89), p = 0.757. The ability of MEWS (cut-off point ≥ 3) to predict ICU admission had a similar pooled DOR of 5.54 (95% CI 2.02–15.21). In the pre-hospital setting, EWS scores failed to predict 30-day mortality. Using high cut-off points of 5, 7, or 9, their predictability improved when assessing up-to-≥3-day mortality with DOR ranging from 11.60 (95%, CI 9.75–13.88) to 20.37 (95% CI 13.16–31.52).Publication bias was not detected. Participants’ age explained 92% of between-study variance. Conclusion: EWS scores’ predictability of clinical deterioration improves when applied on patient populations that are already in the ED or hospital. The high thresholds used and the scores’ failure to predict 30-day mortality make them less suited for use in the pre-hospital setting.

scholarly journals Implementation of an Electronic National Early Warning System to Decrease Clinical Deterioration in Hospitalized Patients at a Tertiary Medical Center

2021 ◽  
Vol 18 (9) ◽  
pp. 4550
Author(s):  
Chieh-Liang Wu ◽  
Chen-Tsung Kuo ◽  
Sou-Jen Shih ◽  
Jung-Chen Chen ◽  
Ying-Chih Lo ◽  
...  
Keyword(s):  
Information System ◽  
Early Warning ◽  
Early Warning System ◽  
Medical Center ◽  
Warning System ◽  
Clinical Deterioration ◽  
Early Warning Score ◽  
Control Group ◽  
Number Of Patients ◽  
The Impact

The National Early Warning Score (NEWS) is an early warning system that predicts clinical deterioration. The impact of the NEWS on the outcome of healthcare remains controversial. This study was conducted to evaluate the effectiveness of implementing an electronic version of the NEWS (E-NEWS), to reduce unexpected clinical deterioration. We developed the E-NEWS as a part of the Health Information System (HIS) and Nurse Information System (NIS). All adult patients admitted to general wards were enrolled into the current study. The “adverse event” (AE) group consisted of patients who received cardiopulmonary resuscitation (CPR), were transferred to an intensive care unit (ICU) due to unexpected deterioration, or died. Patients without AE were allocated to the control group. The development of the E-NEWS was separated into a baseline (October 2018 to February 2019), implementation (March to August 2019), and intensive period (September. to December 2019). A total of 39,161 patients with 73,674 hospitalization courses were collected. The percentage of overall AEs was 6.06%. Implementation of E-NEWS was associated with a significant decrease in the percentage of AEs from 6.06% to 5.51% (p = 0.001). CPRs at wards were significantly reduced (0.52% to 0.34%, p = 0.012). The number of patients transferred to the ICU also decreased significantly (3.63% to 3.49%, p = 0.035). Using multivariate analysis, the intensive period was associated with reducing AEs (p = 0.019). In conclusion, we constructed an E-NEWS system, updating the NEWS every hour automatically. Implementing the E-NEWS was associated with a reduction in AEs, especially CPRs at wards and transfers to ICU from ordinary wards.

scholarly journals Acute Pharmacological Effects and Oral Fluid Biomarkers of the Synthetic Cannabinoid UR-144 and THC in Recreational Users

Biology ◽  
2021 ◽  
Vol 10 (4) ◽  
pp. 257
Author(s):  
Nunzia La Maida ◽  
Esther Papaseit ◽  
Lucia Martínez ◽  
Clara Pérez-Mañá ◽  
Lourdes Poyatos ◽  
...  
Keyword(s):  
Blood Pressure ◽  
Heart Rate ◽  
Observational Study ◽  
Early Warning ◽  
Early Warning System ◽  
Oral Fluid ◽  
Subjective Effects ◽  
Warning System ◽  
Pharmacological Effects ◽  
The Eu

Synthetic cannabinoids (SCs) are one of the most frequent classes of new psychoactive substances monitored by the EU Early Warning System and World Health Organization. UR-144 is a SC with a relative low affinity for the CB1 receptor with respect to that for the CB2 receptor. As with other cannabinoid receptor agonists, it has been monitored by the EU Early Warning System since 2012 for severe adverse effects on consumers. Since data for UR-144 human pharmacology are very limited, an observational study was carried out to evaluate its acute pharmacological effects following its administration using a cannabis joint as term of comparison. Disposition of UR-144 and delta-9-tetrahydrocannibinol (THC) was investigated in oral fluid. Sixteen volunteers smoked a joint prepared with tobacco and 1 or 1.5 mg dose of UR-144 (n = 8) or cannabis flowering tops containing 10 or 20 mg THC (n = 8). Physiological variables including systolic and diastolic blood pressure, heart rate and cutaneous temperature were measured. A set of Visual Analog Scales (VAS), the Addiction Research Centre Inventory (ARCI)-49-item short form version and the Evaluation of the Subjective Effects of Substances with Abuse Potential (VESSPA-SSE) were administered to evaluate subjective effects. Oral fluid was collected at baseline, 10, 20, 40 min and 1, 2, 3 and 4 h after smoking, for UR-144 or THC concentration monitoring. Results showed significant statistical increases in both systolic and diastolic blood pressure and heart rate after both UR-144 and cannabis smoking. Both substances produced an increase in VAS related to stimulant-like and high effects, but scores were significantly higher after cannabis administration. No hallucinogenic effects were observed. Maximal oral fluid UR-144 and THC concentrations appeared at 20 and 10 min after smoking, respectively. The presence of UR-144 in oral fluid constitutes a non-invasive biomarker of SC consumption. The results of this observational study provide valuable preliminary data of the pharmacological effects of UR-144, showing a similar profile of cardiovascular effects in comparison with THC but lower intensity of subjective effects. Our results have to be confirmed by research in a larger sample to extensively clarify pharmacological effects and the health risk profile of UR-144.

Sign in / Sign up

Export Citation Format

Share Document