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.

Impact of Melanoma Diagnosis on Sun-Awareness and Protection: Efficacy of Education Campaigns in a High-Risk Population

2004 ◽  
Vol 8 (5) ◽  
pp. 303-309 ◽  
Author(s):  
Anatoli Freiman ◽  
John Yu ◽  
Antoine Loutfi ◽  
Beatrice Wang
Keyword(s):  
Risk Factors ◽  
High Risk ◽  
Risk Groups ◽  
High Risk Population ◽  
Awareness Campaigns ◽  
Number Of Patients ◽  
Increased Risk ◽  
Patients At Risk ◽  
And Behavior ◽  
Attitudes And Behavior

Background: Malignant melanoma is a significant cause of morbidity and mortality worldwide. Sun-awareness campaigns increase public knowledge but may not translate into behavioral changes in practice, which is particularly alarming when reported for individuals in high-risk groups. In particular, patients diagnosed with melanoma are at increased risk of developing subsequent primary melanomas compared with the general population. Objectives: The study was undertaken (1) to assess whether patients with known risk factors for developing melanoma had been exposed to preventative campaign messages prior to their diagnosis, (2) to quantify whether the diagnosis of melanoma changed sun-related attitudes and behavior, and (3) to assess the adequacy of sun-related advice given to patients with melanoma, as well as their compliance with the advice. Methods: Using an anonymous questionnaire, 217 patients previously diagnosed with melanoma were interviewed on the source and frequency of received sun-related advice, as well as on their knowledge, attitudes, and behavior toward sun protection before and after the diagnosis. Results: The number of patients who reported receiving sun-related advice after being diagnosed with melanoma increased by 36% (52% pre-vs. 88% postDiagnosis), with advice being given more frequently and more often by a physician (19% pre- vs. 49% postdiagnosis). Furthermore, sun-related attitudes and behavioral practices were positively altered. Yet, patients with known risk factors were not preferentially targeted for advice before their diagnosis. Conclusions: The diagnosis of melanoma leads to increased sunwareness and protection. While dermatologists should continue their efforts to promote and reinforce sun-awareness in patients with melanoma, additional emphasis on preventative targeting of high-risk individuals would be of marked benefit in decreasing the overall incidence of melanoma. Non-dermatologists, such as family physicians, can be key players in this preventative campign, and can be educated to recognize and educate patients at risk, as well as direct them to be followed under dermatology care.

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.

Predicting the risk of VISIT emergency department (ED) in lung cancer patients using machine learning.

2020 ◽  
Vol 38 (15_suppl) ◽  
pp. 2042-2042
Author(s):  
Pablo Rodriguez-Brazzarola ◽  
Nuria Ribelles ◽  
Jose Manuel Jerez ◽  
Jose Trigo ◽  
Manuel Cobo ◽  
...  
Keyword(s):  
Machine Learning ◽  
Lung Cancer ◽  
At Risk ◽  
Cancer Patients ◽  
Machine Learning Algorithms ◽  
Free Text ◽  
Adaptive Boosting ◽  
Cancer Symptoms ◽  
Lung Cancer Patients ◽  
Patients At Risk

2042 Background: Lung cancer patients commonly need unplanned visits to ED. Many of these visits could be potentially avoidable if it were possible to identify patients at risk when the previous scheduled visit takes place. At that moment, it would be possible to perform elective actions to manage patients at risk to consult the ED in the near future. Methods: Unplanned visits of patients in active cancer therapy (i.e. chemo or immunotherapy) are attended in our own ED facilities. Our Electronic Health Record (EHR) includes specific modules for first visit, scheduled visits and unplanned visits. Lung cancer patients with at least two visits were eligible. The event of interest was patient visit to ED within 21 or 28 days (d) from previous visit. Free text data collected in the three modules were obtained from EHR in order to generate a feature vector composed of the word frequencies for each visit. We evaluate five different machine learning algorithms to predict the event of interest. Area under the ROC curve (AUC), F1 (harmonic mean of precision and recall), True Positive Rate (TPR) and True Negative Rate (TNR) were assessed using 10-fold cross validation. Results: 2,682 lung cancer patients treated between March 2009 and October 2019 were included from which 819 patients were attended at ED. There were 2,237 first visits, 47,465 scheduled visits (per patient: range 1-174; median 12) and 2,125 unplanned visits (per patient: range 1-20; median 2). Mean age at diagnosis was 64 years. The majority of patients had late stage disease (34.24 % III, 51.56 % IV). The Adaptive Boosting Model yields the best results for both 21 d or 28 d prediction. Conclusions: Using unstructured data from real-world EHR enables the possibility to build an accurate predictive model of unplanned visit to an ED within the 21 or 28 following d after a scheduled visit. Such utility would be very useful in order to prevent ED visits related with cancer symptoms and to improve patients care. [Table: see text]

scholarly journals Classifying and Predicting Surgical Complications After Laryngectomy: A Novel Approach to Diagnosing and Treating Patients

2021 ◽  
pp. 014556132110297
Author(s):  
Lukas Koenen ◽  
Philipp Arens ◽  
Heidi Olze ◽  
Steffen Dommerich
Keyword(s):  
Machine Learning ◽  
At Risk ◽  
Postoperative Complications ◽  
Total Laryngectomy ◽  
Univariate Analysis ◽  
Multivariate Logistic Regression Analysis ◽  
Machine Learning Algorithms ◽  
Predictive Values ◽  
Adaboost Algorithm ◽  
Patients At Risk

Objectives: The total laryngectomy is one of the most standardized major surgical procedures in otolaryngology. Several studies have proposed the Clavien-Dindo classification (CDC) as a solution to classifying postoperative complications into 5 grades from less severe to severe. Yet more data on classifying larger patient populations undergoing major otolaryngologic surgery according to the CDC are needed. Predicting postoperative complications in clinical practice is often subject to generalized clinical scoring systems with uncertain predictive abilities for otolaryngologic surgery. Machine learning offers methods to predict postoperative complications based on data obtained prior to surgery. Methods: We included all patients (N = 148) who underwent a total laryngectomy after diagnosis of squamous cell carcinoma at our institution. A univariate and multivariate logistic regression analysis of multiple complex risk factors was performed, and patients were grouped into severe postoperative complications (CDC ≥ 4) and less severe complications. Four different commonly used machine learning algorithms were trained on the dataset. The best model was selected to predict postoperative complications on the complete dataset. Results: Univariate analysis showed that the most significant predictors for postoperative complications were the Charlson Comorbidity Index (CCI) and whether reconstruction was performed intraoperatively. A multivariate analysis showed that the CCI and reconstruction remained significant. The commonly used AdaBoost algorithm achieved the highest area under the curve with 0.77 with high positive and negative predictive values in subsequent analysis. Conclusions: This study shows that postoperative complications can be classified according to the CDC with the CCI being a useful screening tool to predict patients at risk for postoperative complications. We provide evidence that could help identify single patients at risk for complications and customize treatment accordingly which could finally lead to a custom approach for every patient. We also suggest that there is no increase in complications with patients of higher age.

scholarly journals Sarcopenia and Malnutrition Screening in Female Osteoporosis Patients—A Cross-Sectional Study

2021 ◽  
Vol 10 (11) ◽  
pp. 2344
Author(s):  
Franca Genest ◽  
Dominik Rak ◽  
Elisa Bätz ◽  
Kerstin Ott ◽  
Lothar Seefried
Keyword(s):  
At Risk ◽  
Risk Groups ◽  
Cross Sectional Study ◽  
Mineral Density ◽  
Cross Sectional ◽  
Functional Deficits ◽  
Complementary Approach ◽  
Study Results ◽  
Patients At Risk ◽  
Not At Risk

Sarcopenia and malnutrition are important determinants of increased fracture risk in osteoporosis. SARC-F and MNA-SF are well-established questionnaires for identifying patients at risk for these conditions. We sought to evaluate the feasibility and potential added benefit of such assessments as well as the actual prevalence of these conditions in osteoporosis patients. We conducted a cross-sectional, single-center study in female osteoporosis patients ≥ 65 years (SaNSiBaR-study). Results of the sarcopenia (SARC-F) and malnutrition (MNA-SF) screening questionnaires were matched with a functional assessment for sarcopenia and data from patients’ medical records. Out of 107 patients included in the analysis, a risk for sarcopenia (SARC-F ≥ 4 points) and a risk for malnutrition (MNA-SF ≤ 11 points) was found in 33 (30.8%) and 38 (35.5%) patients, respectively. Diagnostic overlap with coincident indicative findings in both questionnaires was observed in 17 patients (16%). As compared to the respective not-at-risk groups, the mean short physical performance battery (SPPB) score was significantly reduced in both patients at risk for sarcopenia (7.0 vs. 10.9 points, p < 0.001) and patients at risk for malnutrition (8.7 vs. 10.5 points, p = 0.005). Still, confirmed sarcopenia according to EWGSOP2 criteria was present in only 6 (6%) of all 107 patients, with only 3 of them having an indicative SARC-F score. Bone mineral density was not significantly different in any of the at-risk groups at any site. In summary, applying SARC-F and MNA-SF in osteoporosis patients appears to be a complementary approach to identify individuals with functional deficits.

scholarly journals Using Predictive Modeling and Supervised Machine Learning to Identify Patients at Risk for Venous Thromboembolism Following Posterior Lumbar Fusion

2021 ◽  
pp. 219256822110193
Author(s):  
Kevin Y. Wang ◽  
Ijezie Ikwuezunma ◽  
Varun Puvanesarajah ◽  
Jacob Babu ◽  
Adam Margalit ◽  
...  
Keyword(s):  
Machine Learning ◽  
At Risk ◽  
Venous Thromboembolism ◽  
Risk Stratification ◽  
Predictive Model ◽  
Predictive Modeling ◽  
Lumbar Fusion ◽  
Posterior Lumbar Fusion ◽  
Single Level ◽  
Patients At Risk

Study Design: Retrospective review. Objective: To use predictive modeling and machine learning to identify patients at risk for venous thromboembolism (VTE) following posterior lumbar fusion (PLF) for degenerative spinal pathology. Methods: Patients undergoing single-level PLF in the inpatient setting were identified in the National Surgical Quality Improvement Program database. Our outcome measure of VTE included all patients who experienced a pulmonary embolism and/or deep venous thrombosis within 30-days of surgery. Two different methodologies were used to identify VTE risk: 1) a novel predictive model derived from multivariable logistic regression of significant risk factors, and 2) a tree-based extreme gradient boosting (XGBoost) algorithm using preoperative variables. The methods were compared against legacy risk-stratification measures: ASA and Charlson Comorbidity Index (CCI) using area-under-the-curve (AUC) statistic. Results: 13, 500 patients who underwent single-level PLF met the study criteria. Of these, 0.95% had a VTE within 30-days of surgery. The 5 clinical variables found to be significant in the multivariable predictive model were: age > 65, obesity grade II or above, coronary artery disease, functional status, and prolonged operative time. The predictive model exhibited an AUC of 0.716, which was significantly higher than the AUCs of ASA and CCI (all, P < 0.001), and comparable to that of the XGBoost algorithm ( P > 0.05). Conclusion: Predictive analytics and machine learning can be leveraged to aid in identification of patients at risk of VTE following PLF. Surgeons and perioperative teams may find these tools useful to augment clinical decision making risk stratification tool.

Sign in / Sign up

Export Citation Format

Share Document