scholarly journals Editorial

2012 ◽  
Vol 11 (2) ◽  
pp. 58-58
Author(s):  
Chris Roseveare ◽  
Keyword(s):  
Early Warning ◽  
Clinical Decision Making ◽  
Laboratory Data ◽  
Objective Measure ◽  
Early Warning Score ◽  
Initial Assessment ◽  
Junior Doctors ◽  
Control Mechanisms ◽  
Acute Medicine ◽  
Physiological Variables

The ability to identify and discharge the low-risk patient, and to predict those cases where deterioration is likely is already a key element of the practice of acute medicine . This is an area which has been extensively examined in the past, but two articles in this edition add an interesting dimension to the literature. The use of physiological variables to calculate risk enables fluctuations in a patient’s condition over time can be monitored, allowing appropriate escalation measures to be instituted. The National Early Warning Score has already been implemented in Wales and roll-out across England is expected imminently. Austen and colleagues have highlighted some of the advantages that a standardised system will provide in comparison to their locally-developed Early Warning Score; however the problem of under-scoring due to incomplete or inaccurate recording remains and will continue until electronic solutions are more widespread. Scoring systems utilising laboratory data from admission are less useful for ongoing monitoring but could provide clinicians with an objective measure of risk at the time of initial assessment. As austerity measures bite, the pressure to direct our limited resources to the most appropriate cases will undoubtedly intensify, making this increasingly important. The rigorous quality control mechanisms in laboratories ensure the reliability of biochemical test results; furthermore most hospitals have electronic systems for recording and displaying results which limits the risk of errors from human transcription. O’Sullivan et al have utilised the extensive database from St James’ hospital in Dublin to develop a score based on a number of biochemical and haematological tests. Although this will need to be prospectively validated, retrospective analysis using a huge sample over a number of years, suggests their score may be highly predictive of good and poor outcome. This has great potential to support clinical decision making at the ‘front door’ and improve utilisation of resources. If variety is the ‘spice of life’, then Acute Medicine is certainly the ‘vindaloo’ of the modern hospital. The enormous breadth of clinical problems encountered on the AMU is apparent from the data gathered in York Hospital during the 15 months prior to April 2011. Variety is a key attraction for many junior doctors considering their career choice, at a time when many areas of hospital practice are becoming increasingly specialised. The acute medicine curriculum has ensured that trainees undertake blocks of training in respiratory medicine and cardiology, which is clearly important given that these areas reflected almost 50% of patients. However the authors highlight that the infrequency of certain problems, such as cord compression and diabetic ketoacidosis might also need to be addressed with training outside the AMU in neurology and endocrinology to ensure adequate exposure to these conditions. The rise in alcohol-related admissions is also highlighted in this article, and our trainee section includes a problem based review of the management of these problems. The obesity epidemic, as well as the proliferation of weight-loss surgery and its complications is another area which increasingly challenges our AMU resources. The article by Fiona Maggs provides some practical advice on how to address these issues. I hope you enjoy this edition, and the summer months ahead...

scholarly journals A Machine Learning Prediction Model of Respiratory Failure Within 48 Hours of Patient Admission for COVID-19: Model Development and Validation

10.2196/24246 ◽  
2021 ◽  
Vol 23 (2) ◽  
pp. e24246 ◽  
Author(s):  
Siavash Bolourani ◽  
Max Brenner ◽  
Ping Wang ◽  
Thomas McGinn ◽  
Jamie S Hirsch ◽  
...  
Keyword(s):  
Machine Learning ◽  
Emergency Department ◽  
Respiratory Failure ◽  
Early Warning ◽  
Clinical Decision Making ◽  
Predictive Accuracy ◽  
Invasive Mechanical Ventilation ◽  
Laboratory Data ◽  
Early Warning Score ◽  
Learning Approaches

Background Predicting early respiratory failure due to COVID-19 can help triage patients to higher levels of care, allocate scarce resources, and reduce morbidity and mortality by appropriately monitoring and treating the patients at greatest risk for deterioration. Given the complexity of COVID-19, machine learning approaches may support clinical decision making for patients with this disease. Objective Our objective is to derive a machine learning model that predicts respiratory failure within 48 hours of admission based on data from the emergency department. Methods Data were collected from patients with COVID-19 who were admitted to Northwell Health acute care hospitals and were discharged, died, or spent a minimum of 48 hours in the hospital between March 1 and May 11, 2020. Of 11,525 patients, 933 (8.1%) were placed on invasive mechanical ventilation within 48 hours of admission. Variables used by the models included clinical and laboratory data commonly collected in the emergency department. We trained and validated three predictive models (two based on XGBoost and one that used logistic regression) using cross-hospital validation. We compared model performance among all three models as well as an established early warning score (Modified Early Warning Score) using receiver operating characteristic curves, precision-recall curves, and other metrics. Results The XGBoost model had the highest mean accuracy (0.919; area under the curve=0.77), outperforming the other two models as well as the Modified Early Warning Score. Important predictor variables included the type of oxygen delivery used in the emergency department, patient age, Emergency Severity Index level, respiratory rate, serum lactate, and demographic characteristics. Conclusions The XGBoost model had high predictive accuracy, outperforming other early warning scores. The clinical plausibility and predictive ability of XGBoost suggest that the model could be used to predict 48-hour respiratory failure in admitted patients with COVID-19.

scholarly journals A Machine Learning Prediction Model of Respiratory Failure Within 48 Hours of Patient Admission for COVID-19: Model Development and Validation (Preprint)

2020 ◽  
Author(s):  
Siavash Bolourani ◽  
Max Brenner ◽  
Ping Wang ◽  
Thomas McGinn ◽  
Jamie S Hirsch ◽  
...  
Keyword(s):  
Machine Learning ◽  
Emergency Department ◽  
Respiratory Failure ◽  
Early Warning ◽  
Clinical Decision Making ◽  
Predictive Accuracy ◽  
Invasive Mechanical Ventilation ◽  
Laboratory Data ◽  
Early Warning Score ◽  
Learning Approaches

BACKGROUND Predicting early respiratory failure due to COVID-19 can help triage patients to higher levels of care, allocate scarce resources, and reduce morbidity and mortality by appropriately monitoring and treating the patients at greatest risk for deterioration. Given the complexity of COVID-19, machine learning approaches may support clinical decision making for patients with this disease. OBJECTIVE Our objective is to derive a machine learning model that predicts respiratory failure within 48 hours of admission based on data from the emergency department. METHODS Data were collected from patients with COVID-19 who were admitted to Northwell Health acute care hospitals and were discharged, died, or spent a minimum of 48 hours in the hospital between March 1 and May 11, 2020. Of 11,525 patients, 933 (8.1%) were placed on invasive mechanical ventilation within 48 hours of admission. Variables used by the models included clinical and laboratory data commonly collected in the emergency department. We trained and validated three predictive models (two based on XGBoost and one that used logistic regression) using cross-hospital validation. We compared model performance among all three models as well as an established early warning score (Modified Early Warning Score) using receiver operating characteristic curves, precision-recall curves, and other metrics. RESULTS The XGBoost model had the highest mean accuracy (0.919; area under the curve=0.77), outperforming the other two models as well as the Modified Early Warning Score. Important predictor variables included the type of oxygen delivery used in the emergency department, patient age, Emergency Severity Index level, respiratory rate, serum lactate, and demographic characteristics. CONCLUSIONS The XGBoost model had high predictive accuracy, outperforming other early warning scores. The clinical plausibility and predictive ability of XGBoost suggest that the model could be used to predict 48-hour respiratory failure in admitted patients with COVID-19.

scholarly journals Development, Implementation, and Evaluation of an In-Hospital Optimized Early Warning Score for Patient Deterioration

2020 ◽  
Vol 5 (1) ◽  
pp. 238146831989966 ◽  
Author(s):  
Cara O’Brien ◽  
Benjamin A. Goldstein ◽  
Yueqi Shen ◽  
Matthew Phelan ◽  
Curtis Lambert ◽  
...  
Keyword(s):  
Confidence Interval ◽  
Early Warning ◽  
Clinical Decision Making ◽  
Risk Model ◽  
Clinical Status ◽  
Area Under The Curve ◽  
Clinical Decision ◽  
Early Warning Score ◽  
Support Tool ◽  
National Early Warning Score

Background. Identification of patients at risk of deteriorating during their hospitalization is an important concern. However, many off-shelf scores have poor in-center performance. In this article, we report our experience developing, implementing, and evaluating an in-hospital score for deterioration. Methods. We abstracted 3 years of data (2014–2016) and identified patients on medical wards that died or were transferred to the intensive care unit. We developed a time-varying risk model and then implemented the model over a 10-week period to assess prospective predictive performance. We compared performance to our currently used tool, National Early Warning Score. In order to aid clinical decision making, we transformed the quantitative score into a three-level clinical decision support tool. Results. The developed risk score had an average area under the curve of 0.814 (95% confidence interval = 0.79–0.83) versus 0.740 (95% confidence interval = 0.72–0.76) for the National Early Warning Score. We found the proposed score was able to respond to acute clinical changes in patients’ clinical status. Upon implementing the score, we were able to achieve the desired positive predictive value but needed to retune the thresholds to get the desired sensitivity. Discussion. This work illustrates the potential for academic medical centers to build, refine, and implement risk models that are targeted to their patient population and work flow.

scholarly journals IN-HOSPITAL MORTALITY AND THE PREDICTIVE ABILITY OF THE MODIFIED EARLY WARNING SCORE IN GHANA

2020 ◽  
Author(s):  
Enoch J Abbey ◽  
Jennifer S. Mammen ◽  
Samara E. Soghoian ◽  
Maureen Cadorette ◽  
Promise Ariyo
Keyword(s):  
Early Warning ◽  
Roc Curve ◽  
Predictive Accuracy ◽  
Early Recognition ◽  
Vital Signs ◽  
Objective Measure ◽  
Predictive Ability ◽  
Clinical Deterioration ◽  
Early Warning Score ◽  
African Countries

ABSTRACT BACKGROUND The modified early warning score (MEWS) is an objective measure of illness severity that promotes early recognition of clinical deterioration in critically ill patients. Its primary use is to; facilitate faster intervention or increase the level of care. Despite, its adoption in some African countries, MEWS is not standard of care in Ghana. We assessed the validity of MEWS as a predictor of mortality, among medically ill inpatients at the Korle Bu Teaching Hospital (KBTH), Accra, Ghana. We sought to identify the predictive ability of MEWS in detecting clinical deterioration among medical in-patients and its comparability to the routinely measured vital signs. METHOD This was a retrospective study of medical inpatients, aged >=13 years and admitted at KBTH from January 2017 to March 2019. Vital signs at 48 hours after admission were coded using MEWS criteria, to obtain a limited MEWS score (LMEWS) and the level of consciousness imputed to obtain a full MEWS score (MEWS). A predictive model comparing mortality among patients with significant MEWS (L/MEWS >=4) and non-significant MEWS (L/MEWS <4) scores was designed using multiple logistic regression. Internally validated for predictive accuracy, using the Receiver Operating Characteristic (ROC) curve. RESULTS 112 patients were included in the study. The adjusted odds of death comparing patients with a significant MEWS to patients with non-significant MEWS was 6.33(95% CI 1.96 to 20.48). Similarly, the adjusted odds of death comparing patients with significant versus non-significant LMEWS was 8.22(95% CI 2.45 to 27.56). The ROC curve for each analysis had a C static of 0.83 and 0.84 respectively. CONCLUSION LMEWS is a good predictor of mortality and comparable to MEWS. Adoption of LMEWS can identify medical in-patients at risk of deterioration and death.

scholarly journals Comparative study of scoring systems in ICU and emergency department in predicting mortality of critically ill

2017 ◽  
Vol 5 (4) ◽  
pp. 1352 ◽  
Author(s):  
Sasi Sekhar T. V. D. ◽  
Anjani Kumar C. ◽  
Bhavya Ch. ◽  
Sameera B. ◽  
Rama Devi Ch.
Keyword(s):  
Emergency Department ◽  
Critically Ill ◽  
Critically Ill Patients ◽  
Clinical Decision Making ◽  
Predictive Accuracy ◽  
Laboratory Data ◽  
Scoring Systems ◽  
Apache Ii ◽  
Early Warning Score ◽  
Saps Ii

Background: Scoring systems can be used to define critically ill patients, estimate their prognosis, help in clinical decision making, and guide the allocation of resources and to estimate the quality of care.  It remains unclear whether the additional data needed to compute ICU scores improves mortality prediction for critically ill patients compared to the simpler ED scores.Methods: We have done a prospective observational study of consecutively admitted 400 critically ill patients to ICU directly from Emergency Department in Dr PSIMS and RF over a period of 2 years. Clinical and laboratory data conforming to the modified early warning score (MEWS), rapid emergency medicine score (REMS), acute physiology and chronic health evaluation (APACHE II), and simplified acute physiology score (SAPS II) were recorded for all patients. A comparison was made between ED scoring systems MEWS, REMS and ICU scoring systems APACHE II, SAPSII. The outcome was recorded in two categories: survived and non-survived with a primary end point of 30-day mortality. Discrimination was evaluated using receiver operating characteristic (ROC) curves.Results: The ICU scores outperformed the ED scores with more area under curve values. The predicted mortality percentage of ICU based scoring systems is high compared to emergency scores (predicted mortality % of SAPS II-63%, APACHE II-33.3%, MEWS-18.5%, REMS-14.8%).Conclusions: ICU scores showed more predictive accuracy than ED scores in prognosticating the outcomes in critically ill patients. This difference is seemed more due to complexity of ICU scores.

Editorial

2013 ◽  
Vol 12 (2) ◽  
pp. 67-68
Author(s):  
Chris Roseveare ◽  
Keyword(s):  
Continuity Of Care ◽  
Early Warning Score ◽  
Initial Assessment ◽  
Similar Proportion ◽  
Published Data ◽  
Acute Medicine ◽  
General Internal ◽  
Acute Medical Unit ◽  
Future Hospital ◽  
The Uk

Much has been written in recent months about the challenges at the hospital’s front door; emergency departments and acute medical units have found themselves in the spotlight, while politicians and clinical leaders have debated where the causes for this crisis lie. As summer progresses and we continue to search for solutions, it is likely that some of the focus will shift from the emergency department to the processes of care which take place after a patient has been admitted. The Royal College of Physicians’ long awaited Future Hospital Commission report will be published later in the year; a key theme in this document is going to be the importance of continuity of care for patients in hospitals, ensuring the minimum numbers of patient transfers both within the hospital and between consultants. Inevitably this will open a key debate over the role of the ‘generalist’ in hospitals of the future. The last decade has seen a steady drift away from generalism, with increasing numbers of hospital clinicians retreating into their speciality enclaves, and withdrawing from the acute medical take. For some patients speciality-led care has been shown to be highly effective; however there remain significant numbers of patients whose problems cannot be neatly packaged into a single organ category. Acute physicians have taken on the management of this group of patients within the acute medical unit (AMU), but who should provide ongoing general medical care for patients who are transferred out of the Unit? A recent survey of members of the Society for Acute Medicine (SAM) has confirmed that the overwhelming majority of existing acute medicine consultants are accredited in General Internal Medicine (GIM), while a similar proportion of current acute medicine trainees expect to attain a certificate of completed training in GIM. Provided that hospitals can secure adequate numbers of new consultant appointments, acute physicians will be ideally placed to provide continuity of care for this patient group. The survey, which will soon be published on the SAM website, also indicates that most acute physicians would be happy to provide this service, as long as it was appropriately resourced and supported; furthermore a substantial proportion viewed a combination of GIM and acute medicine as their preferred model for their future job plan. Inevitably, staffing levels will be key to whether acute physicians can branch out of the AMU. There appears to be no lack of enthusiasm amongst hospitals to expand numbers of acute physicians, with vacancies being advertised on a weekly basis across the UK. However a shortage of doctors completing acute medicine training in 2013, due in part to curriculum changes in 2009, means that many of these posts are remaining unfilled. It is clear that much work clearly remains to be done on our acute medical units to ensure that we achieve the high standards which SAM has published. By the time this edition is published, data for the second Society for Acute Medicine Benchmarking Audit (’SAMBA 2013’) will already have been collected. Results of last year’s baseline audit are presented in this edition, and highlight a number of areas in which acute medical units needed to improve. Delays in the initial assessment of patients and consultant review are likely to have reflected the well recognised, and ongoing imbalance between demand and workforce; however it is encouraging to note that almost all patients underwent appropriate observations to enable calculation of an early warning score. Access to investigations for pulmonary embolism and upper gastrointestinal bleeding also appeared to be constrained to a greater degree than CT scan for suspected stroke, which may reflect the relative priorities often afforded to these conditions. It should be noted that the data were collected on a Wednesday – weekend access to investigations remains an even greater challenge in many centres. Those who are regular users of Twitter and other social media will no doubt be aware of their increasing range of medical uses. In the third of a triad of articles which this journal has published on sepsis, Luke McMenemin and colleagues have highlighted how Twitter might be used in future to help disseminate and identify innovative medical solutions to common clinical challenges. Delays in the publication of traditional written media mean that broad implementation sometimes lags behind the innovation; as a consequence, there may be a tendency to ‘reinvent the wheel’ rather than learning from others’ experience. Twitter clearly has its limitations – the 140 character limit is a tough ask for even the most succinct of writers – but with an increasing numbers of users, perhaps the time has come for more acute physicians to take the plunge!

scholarly journals Comparison of early warning scores in patients with COPD exacerbation: DECAF and NEWS score

Thorax ◽  
2019 ◽  
Vol 74 (10) ◽  
pp. 941-946 ◽  
Author(s):  
Carlos Echevarria ◽  
John Steer ◽  
Stephen C Bourke
Keyword(s):  
Early Warning ◽  
Repeated Measures ◽  
Clinical Decision Making ◽  
Prognostic Score ◽  
Mortality Prediction ◽  
Early Warning Score ◽  
Copd Exacerbation ◽  
Prognostic Performance ◽  
Senior Clinician ◽  
The Impact

BackgroundThe National Early Warning Score 2 (NEWS2) includes two oxygen saturation scales; the second adjusts target saturations to 88%–92% for those with hypercapnic respiratory failure. Using this second scale in all patients with COPD exacerbation (‘NEWS2All COPD’) would simplify practice, but the impact on alert frequency and prognostic performance is unknown. Admission NEWS2 score has not been compared with DECAF (dyspnoea, eosinopenia, consolidation, acidaemia, atrial fibrillation) for inpatient mortality prediction.MethodsNEWS, NEWS2 and NEWS2All COPD and DECAF were calculated at admission in 2645 patients with COPD exacerbation attending consecutively to one of six UK hospitals, all of whom met spirometry criteria for COPD. Alert frequency and appropriateness were assessed for all NEWS iterations. Prognostic performance was compared using the area under the receiver operating characteristic (AUROC) curve. Missing data were imputed using multiple imputation.FindingsCompared with NEWS, NEWS2 reclassified 3.1% patients as not requiring review by a senior clinician (score≥5). NEWS2All COPD reduced alerts by 12.6%, or 16.1% if scoring for injudicious use of oxygen was exempted. Mortality was low in reclassified patients, with no patients dying the same day as being identified as low risk. NEWS2All COPD was a better prognostic score than NEWS (AUROC 0.72 vs 0.65, p<0.001), with similar performance to NEWS2 (AUROC 0.72 vs 0.70, p=0.090). DECAF was superior to all scores (validation cohort AUROC 0.82) and offered a more clinically useful range of risk stratification (DECAF=1.2%–25.5%; NEWS2=3.5%–15.4%).ConclusionNEWS2All COPD safely reduces the alert frequency compared with NEWS2. DECAF offers superior prognostic performance to guide clinical decision-making on admission, but does not replace repeated measures of NEWS2 during hospitalisation to detect the deteriorating patient.

CORONET; COVID-19 in Oncology evaluatiON Tool: Use of machine learning to inform management of COVID-19 in patients with cancer.

2021 ◽  
Vol 39 (15_suppl) ◽  
pp. 1505-1505
Author(s):  
Rebecca Lee ◽  
Oskar Wysocki ◽  
Cong Zhou ◽  
Antonio Calles ◽  
Leonie Eastlake ◽  
...  
Keyword(s):  
Clinical Decision Making ◽  
Laboratory Data ◽  
Data Availability ◽  
Early Warning Score ◽  
Recursive Feature Elimination ◽  
Solid Cancer ◽  
Haematological Cancer ◽  
Entire Cohort ◽  
Increased Risk ◽  
Model Derivation

1505 Background: Patients (pts) with cancer are at increased risk of severe COVID-19 infection and death. Due to COVID-19 outcome heterogeneity, accurate assessment of pts is crucial. Early identification of pts who are likely to deteriorate allows timely discussions regarding escalation of care. Likewise, safe home management will reduce risk of nosocomial infection. To aid clinical decision-making, we developed a model to help determine which pts should be admitted vs. managed as an outpatient and which pts are likely to have severe COVID-19. Methods: Pts with active solid or haematological cancer presenting with symptoms/asymptomatic and testing positive for SARS-CoV-2 in Europe and USA were identified following institutional board approval. Clinical and laboratory data were extracted from pt records. Clinical outcome measures were discharge within 24 hours, requirement for oxygen at any stage during admission and death. Random Forest (RF) algorithm was used for model derivation as it compared favourably vs. lasso regression. Relevant clinical features were identified using recursive feature elimination based on SHAP. Internal validation (bootstrapping) with multiple imputations for missing data (maximum ≤2) were used for performance evaluation. Cost function determined cut-offs were defined for admission/death. The final CORONET model was trained on the entire cohort. Results: Model derivation set comprised 672 pts (393 male, 279 female, median age 71). 83% had solid cancers, 17% haematological. Predictive features were selected based on clinical relevance and data availability, supported by recursive feature elimination based on SHAP. RF model using haematological cancer, solid cancer stage, no of comorbidities, National Early Warning Score 2 (NEWS2), neutrophil:lymphocyte ratio, platelets, CRP and albumin achieved AUROC for admission 0.79 (+/-0.03) and death 0.75 (+/-0.02). RF explanation using SHAP revealed NEWS2 and C-reactive protein as the most important features predicting COVID-19 severity. In the entire cohort, CORONET recommended admission of 96% of patients requiring oxygen and 99% of patients who died. We then built a decision support tool using the model, which aids clinical decisions by presenting model predictions and explaining key contributing features. Conclusions: We have developed a model and tool available at https://coronet.manchester.ac.uk/ to predict which pts with cancer and COVID-19 require hospital admission and are likely to have a severe disease course. CORONET is being continuously refined and validated over time.

Sign in / Sign up

Export Citation Format

Share Document