scholarly journals Clinical thermography at extreme temperatures

2021 ◽  
Vol 20 (3) ◽  
pp. 236-236
Author(s):  
M Brabrand ◽  
◽  
S K Nissen ◽  
S Hanson ◽  
M Fløjstrup
Keyword(s):  
At Risk ◽  
Emergency Departments ◽  
Vital Signs ◽  
Small Study ◽  
Extreme Temperatures ◽  
Thermal Images ◽  
Increased Risk ◽  
The World ◽  
The Face ◽  
Patients At Risk

Every day, emergency departments and acute medical units all over the world receive and assess thousands of patients. Most are stable, but a few require immediate stabilization. To identify these, all patients are routinely triaged and have vital signs measured. Our group has shown that thermographic images of the face can be an alternative method for identifying patients at increased risk of 30-day mortality. In our previous studies, the thermographic images were taken after the patients had been inside for at least 30 minutes. However, to identify patients at risk, the images have to be available as quickly as triage, i.e. at the door when the patient arrives. Therefore, we have performed a small study, with the aim of illustrating the effect of such heat-gradients on thermal images of the face.

scholarly journals Identifying those at risk of reattendance at discharge from emergency departments using explainable machine learning

2020 ◽  
Author(s):  
F. P. Chmiel ◽  
M. Azor ◽  
F. Borca ◽  
M. J. Boniface ◽  
D. K. Burns ◽  
...  
Keyword(s):  
Machine Learning ◽  
At Risk ◽  
Emergency Departments ◽  
Risk Groups ◽  
Machine Learning Algorithms ◽  
Care Indicator ◽  
Number Of Patients ◽  
Increased Risk ◽  
Single Centre Study ◽  
Patients At Risk

ABSTRACTShort-term reattendances to emergency departments are a key quality of care indicator. Identifying patients at increased risk of early reattendance can help reduce the number of patients with missed or undertreated illness or injury, and could support appropriate discharges with focused interventions. In this manuscript we present a retrospective, single-centre study where we create and evaluate a machine-learnt classifier trained to identify patients at risk of reattendance within 72 hours of discharge from an emergency department. On a patient hold-out test set, our highest performing classifier obtained an AUROC of 0.748 and an average precision of 0.250; demonstrating that machine-learning algorithms can be used to classify patients, with moderate performance, into low and high-risk groups for reattendance. In parallel to our predictive model we train an explanation model, capable of explaining predictions at an attendance level, which can be used to help inform the design of interventional strategies.

scholarly journals Using explainable machine learning to identify patients at risk of reattendance at discharge from emergency departments

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
F. P. Chmiel ◽  
D. K. Burns ◽  
M. Azor ◽  
F. Borca ◽  
M. J. Boniface ◽  
...  
Keyword(s):  
Machine Learning ◽  
At Risk ◽  
Emergency Departments ◽  
Gradient Boosting ◽  
Tree Model ◽  
Post Discharge ◽  
Test Set ◽  
Increased Risk ◽  
Extreme Gradient Boosting ◽  
Patients At Risk

AbstractShort-term reattendances to emergency departments are a key quality of care indicator. Identifying patients at increased risk of early reattendance could help reduce the number of missed critical illnesses and could reduce avoidable utilization of emergency departments by enabling targeted post-discharge intervention. In this manuscript, we present a retrospective, single-centre study where we created and evaluated an extreme gradient boosting decision tree model trained to identify patients at risk of reattendance within 72 h of discharge from an emergency department (University Hospitals Southampton Foundation Trust, UK). Our model was trained using 35,447 attendances by 28,945 patients and evaluated on a hold-out test set featuring 8847 attendances by 7237 patients. The set of attendances from a given patient appeared exclusively in either the training or the test set. Our model was trained using both visit level variables (e.g., vital signs, arrival mode, and chief complaint) and a set of variables available in a patients electronic patient record, such as age and any recorded medical conditions. On the hold-out test set, our highest performing model obtained an AUROC of 0.747 (95% CI 0.722–0.773) and an average precision of 0.233 (95% CI 0.194–0.277). These results demonstrate that machine-learning models can be used to classify patients, with moderate performance, into low and high-risk groups for reattendance. We explained our models predictions using SHAP values, a concept developed from coalitional game theory, capable of explaining predictions at an attendance level. We demonstrated how clustering techniques (the UMAP algorithm) can be used to investigate the different sub-groups of explanations present in our patient cohort.

A multiparametric ICD algorithm for heart failure risk stratification and management: an analysis in clinical practice

EP Europace ◽  
2021 ◽  
Vol 23 (Supplement_3) ◽  
Author(s):  
L Calo" ◽  
V Bianchi ◽  
D Ferraioli ◽  
L Santini ◽  
A Dello Russo ◽  
...  
Keyword(s):  
Heart Failure ◽  
At Risk ◽  
Clinical Practice ◽  
Risk Stratification ◽  
Management Strategies ◽  
Cardiac Resynchronization ◽  
Office Visits ◽  
Increased Risk ◽  
Patients At Risk ◽  
Observation Period

Abstract Funding Acknowledgements Type of funding sources: None. Introduction The HeartLogic algorithm combines multiple implantable cardioverter defibrillator (ICD) sensors to identify patients at risk of heart failure (HF) events. Purpose We sought to evaluate the risk stratification ability of this algorithm in clinical practice. We also analyzed the alert management strategies adopted in the study group and their association with the occurrence of HF events. Methods The HeartLogic feature was activated in 366 ICD and cardiac resynchronization therapy ICD patients at 22 centers. The HeartLogic algorithm automatically calculates a daily HF index and identifies periods IN or OUT of an alert state on the basis of a configurable threshold (in this analysis set to 16). Results The HeartLogic index crossed the threshold value 273 times (0.76 alerts/patient-year) in 150 patients over a median follow-up of 11 months [25-75 percentile: 6-16]. Overall, the time IN the alert state was 11% of the total observation period. Patients experienced 36 HF hospitalizations and 8 patients died of HF (rate: 0.12 events/patient-year) during the observation period. Thirty-five events were associated with the IN alert state (0.92 events/patient-year versus 0.03 events/patient-year in the OUT of alert state). The hazard ratio in the IN/OUT of alert state comparison was (HR: 24.53, 95% CI: 8.55-70.38, p < 0.001), after adjustment for baseline clinical confounders. Alerts followed by clinical actions were associated with a lower rate of HF events (HR: 0.37, 95% CI: 0.14-0.99, p = 0.047). No differences in event rates were observed between in-office and remote alert management. By contrast, verification of HF symptoms during post-alert examination was associated with a higher risk of HF events (HR: 5.23, 95% CI: 1.98-13.83, p < 0.001). Conclusions This multiparametric ICD algorithm identifies patients during periods of significantly increased risk of HF events. The rate of HF events seemed lower when clinical actions were undertaken in response to alerts. Extra in-office visits did not seem to be required in order to effectively manage HeartLogic alerts, while post-alert verification of symptoms seemed useful in order to better stratify patients at risk of HF events.

Abstract 15714: Prediction of Sudden Cardiac Death With Automated High-Throughput Analysis of T-Wave Heterogeneity in Standard 12-Lead Electrocardiogram

Circulation ◽  
2014 ◽  
Vol 130 (suppl_2) ◽  
Author(s):  
Tuomas Kenttä ◽  
Bruce D Nearing ◽  
Kimmo Porthan ◽  
Jani T Tikkanen ◽  
Matti Viitasalo ◽  
...  
Keyword(s):  
At Risk ◽  
Relative Risk ◽  
Sudden Cardiac Death ◽  
General Population ◽  
Cardiac Death ◽  
Left Ventricular ◽  
Adjusted Relative Risk ◽  
T Wave ◽  
Increased Risk ◽  
Patients At Risk

Introduction: Noninvasive identification of patients at risk for sudden cardiac death (SCD) remains a major clinical challenge. Abnormal ventricular repolarization is associated with increased risk of lethal ventricular arrhythmias and SCD. Hypothesis: We investigated the hypothesis that spatial repolarization heterogeneity can identify patients at risk for SCD in general population. Methods: Spatial R-, J- and T-wave heterogeneities (RWH, JWH and TWH, respectively) were automatically analyzed with second central moment technique from standard digital 12-lead ECGs in 5618 adults (46% men; age 50.9±12.5 yrs.) who took part in Health 2000 Study, an epidemiological survey representative of the entire Finnish adult population. During average follow-up of 7.7±1.4 years, a total of 72 SCDs occurred. Thresholds of RWH, JWH and TWH were based on optimal cutoff points from ROC curves. Results: Increased RWH, JWH and TWH (Fig.1) in left precordial leads (V4-V6) were univariately associated with SCD (P<0.001, each). When adjusted with clinical risk markers (age, gender, BMI, systolic blood pressure, cholesterol, heart rate, left ventricular hypertrophy, QRS duration, arterial hypertension, diabetes, coronary heart disease and previous myocardial infarction) JWH and TWH remained as independent predictors of SCD. Increased TWH (≥102μV) was associated with a 1.9-fold adjusted relative risk (95% confidence interval [CI]: 1.2 - 3.1; P=0.011) and increased JWH (≥123μV) with a 2.0-fold adjusted relative risk for SCD (95% CI: 1.2 - 3.3; P=0.004). When both TWH and JWH were above threshold, the adjusted relative risk for SCD was 3.2-fold (95% CI: 1.7 - 6.2; P<0.001). When all heterogeneity measures (RWH, JWH and TWH) were above threshold, the risk for SCD was 3.7-fold (95% CI: 1.6 - 8.6; P=0.003). Conclusions: Automated measurement of spatial J- and T-wave heterogeneity enables analysis of high patient volumes and is able to stratify SCD risk in general population.

scholarly journals Effectiveness of technology-based interventions in detection, prevention, monitoring and treatment of patients at risk or diagnosed with mild cognitive impairment: protocol for a systematic review

BMJ Open ◽  
2021 ◽  
Vol 11 (8) ◽  
pp. e045978
Author(s):  
Jordi Martínez-Soldevila ◽  
Roland Pastells-Peiró ◽  
Carolina Climent-Sanz ◽  
Gerard Piñol-Ripoll ◽  
Mariona Rocaspana-García ◽  
...  
Keyword(s):  
Systematic Review ◽  
At Risk ◽  
Cognitive Impairment ◽  
Mild Cognitive Impairment ◽  
Cognitive Decline ◽  
Meta Analysis ◽  
Cognitive Disorders ◽  
Increased Risk ◽  
Patients At Risk ◽  
Review Protocol

IntroductionThe gradual changes over the decades in the longevity and ageing of European society as a whole can be directly related to the prolonged decline in the birth rate and increase in the life expectancy. According to the WHO, there is an increased risk of dementia or other cognitive disorders as the population ages, which have a major impact on public health. Mild cognitive impairment (MCI) is described as a greater than expected cognitive decline for an individual’s age and level of education, but that does not significantly interfere with activities of daily living. Patients with MCI exhibit a higher risk of dementia compared with others in the same age group, but without a cognitive decline, have impaired walking and a 50% greater risk of falling.The urban lifestyle and advent of smartphones, mobility and immediate access to all information via the internet, including health information, has led to a totally disruptive change in most general aspects.This systematic review protocol is aimed at evaluating the effectiveness of technology-based interventions in the detection, prevention, monitoring and treatment of patients at risk or diagnosed with MCI.Methods and analysisThis review protocol follows the recommendations of the Preferred Reporting Items for Systematic Review and Meta-Analysis Protocols reporting guidelines. The search will be performed on MEDLINE (PubMed), CENTRAL, CINAHL Plus, ISI Web of Science and Scopus databases from 2010 to 2020. Studies of interventions either randomised clinical trials or pre–post non-randomised quasi-experimental designs, published in English and Spanish will be included. Articles that provide relevant information on the use of technology and its effectiveness in interventions that assess improvements in early detection, prevention, follow-up and treatment of the patients at risk or diagnosed with MCI will be included.Ethics and disseminationEthics committee approval not required. The results will be disseminated in publications and congresses.

scholarly journals Proteomic mechanistic profile of patients with diabetes at risk of developing heart failure: insights from the HOMAGE trial

2021 ◽  
Vol 20 (1) ◽  
Author(s):  
Job A. J. Verdonschot ◽  
João Pedro Ferreira ◽  
Pierpaolo Pellicori ◽  
Hans-Peter Brunner-La Rocca ◽  
Andrew L. Clark ◽  
...  
Keyword(s):  
Heart Failure ◽  
At Risk ◽  
Plasma Concentrations ◽  
Diabetic Patients ◽  
Proteomic Profile ◽  
Developing Heart ◽  
Diabetes Status ◽  
Increased Risk ◽  
Patients With Diabetes ◽  
Patients At Risk

Abstract Background Patients with diabetes mellitus (DM) are at increased risk of developing heart failure (HF). The “Heart OMics in AGEing” (HOMAGE) trial suggested that spironolactone had beneficial effect on fibrosis and cardiac remodelling in an at risk population, potentially slowing the progression towards HF. We compared the proteomic profile of patients with and without diabetes among patients at risk for HF in the HOMAGE trial. Methods Protein biomarkers (n = 276) from the Olink®Proseek-Multiplex cardiovascular and inflammation panels were measured in plasma collected at baseline and 9 months (or last visit) from HOMAGE trial participants including 217 patients with, and 310 without, diabetes. Results Twenty-one biomarkers were increased and five decreased in patients with diabetes compared to non-diabetics at baseline. The markers clustered mainly within inflammatory and proteolytic pathways, with granulin as the key-hub, as revealed by knowledge-induced network and subsequent gene enrichment analysis. Treatment with spironolactone in diabetic patients did not lead to large changes in biomarkers. The effects of spironolactone on NTproBNP, fibrosis biomarkers and echocardiographic measures of diastolic function were similar in patients with and without diabetes (all interaction analyses p > 0.05). Conclusions Amongst patients at risk for HF, those with diabetes have higher plasma concentrations of proteins involved in inflammation and proteolysis. Diabetes does not influence the effects of spironolactone on the proteomic profile, and spironolactone produced anti-fibrotic, anti-remodelling, blood pressure and natriuretic peptide lowering effects regardless of diabetes status.  Trial registration NCT02556450.

scholarly journals Vascular Surgery Patients at Risk for Malnutrition Are at an Increased Risk of Developing Postoperative Complications

2020 ◽  
Vol 64 ◽  
pp. 213-220 ◽  
Author(s):  
Louise B.D. Banning ◽  
Lies ter Beek ◽  
Mostafa El Moumni ◽  
Linda Visser ◽  
Clark J. Zeebregts ◽  
...  
Keyword(s):  
At Risk ◽  
Postoperative Complications ◽  
Vascular Surgery ◽  
Increased Risk ◽  
Patients At Risk

Postpartum Depression

2020 ◽  
pp. 21-30
Author(s):  
Sophie Grigoriadis
Keyword(s):  
At Risk ◽  
High Risk ◽  
Postpartum Depression ◽  
Psychotropic Medications ◽  
Community Resources ◽  
Entire Family ◽  
Increased Risk ◽  
The World ◽  
Effective Community ◽  
Depressive Episodes

Postpartum depression occurs in about 9% to 16% of women following delivery. It is often missed because the symptoms may overlap with what women commonly experience after having a baby such as fatigue. It occurs all over the world and those who have support may be at an advantage. The causes are thought to be a combination of genetic, hormonal, and psychosocial ones and women who have had a previous depression are at particularly high risk although many psychosocial factors may also place her at risk. Clinicians must rule out medical contributions and ensure the safety of both mother and baby. Treatment is essential as the consequences affect the entire family. Both psychotropic medications, with considerations for breastfeeding, as well as psychotherapy are effective. Community resources can be used to increase support. Although there remains an increased risk for future depressive episodes, the majority of women recover well with treatment.

scholarly journals Examining the utility of the Hamilton early warning scores (HEWS) at triage: Retrospective pilot study in a Canadian emergency department

CJEM ◽  
2017 ◽  
Vol 20 (2) ◽  
pp. 266-274 ◽  
Author(s):  
Steven Skitch ◽  
Benjamin Tam ◽  
Michael Xu ◽  
Laura McInnis ◽  
Anthony Vu ◽  
...  
Keyword(s):  
At Risk ◽  
Emergency Department ◽  
Early Warning ◽  
Vital Signs ◽  
Roc Curves ◽  
Early Warning Score ◽  
Critical Event ◽  
Discriminative Ability ◽  
Early Warning Scores ◽  
Patients At Risk

ABSTRACTObjectivesEarly warning scores use vital signs to identify patients at risk of critical illness. The current study examines the Hamilton Early Warning Score (HEWS) at emergency department (ED) triage among patients who experienced a critical event during their hospitalization. HEWS was also evaluated as a predictor of sepsis.MethodsThe study population included admissions to two hospitals over a 6-month period. Cases experienced a critical event defined by unplanned intensive care unit admission, cardiopulmonary resuscitation, or death. Controls were randomly selected from the database in a 2-to-1 ratio to match cases on the burden of comorbid illness. Receiver operating characteristic (ROC) curves were used to evaluate HEWS as a predictor of the likelihood of critical deterioration and sepsis.ResultsThe sample included 845 patients, of whom 270 experienced a critical event; 89 patients were excluded because of missing vitals. An ROC analysis indicated that HEWS at ED triage had poor discriminative ability for predicting the likelihood of experiencing a critical event 0.62 (95% CI 0.58-0.66). HEWS had a fair discriminative ability for meeting criteria for sepsis 0.77 (95% CI 0.72-0.82) and good discriminative ability for predicting the occurrence of a critical event among septic patients 0.82 (95% CI 0.75-0.90).ConclusionThis study indicates that HEWS at ED triage has limited utility for identifying patients at risk of experiencing a critical event. However, HEWS may allow earlier identification of septic patients. Prospective studies are needed to further delineate the utility of the HEWS to identify septic patients in the ED.

Sign in / Sign up

Export Citation Format

Share Document