Using machine learning to identify predictors of imminent drinking and create tailored messages for at-risk drinkers experiencing homelessness

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.

Download Full-text

Novel Machine Learning Methods for ERP Analysis: A Validation From Research on Infants at Risk for Autism

Developmental Neuropsychology ◽

10.1080/87565641.2011.650808 ◽

2012 ◽

Vol 37 (3) ◽

pp. 274-298 ◽

Cited By ~ 32

Author(s):

Daniel Stahl ◽

Andrew Pickles ◽

Mayada Elsabbagh ◽

Mark H. Johnson ◽

The BASIS Team

Keyword(s):

Machine Learning ◽

At Risk ◽

Learning Methods ◽

Machine Learning Methods

Download Full-text

Vertebral body insufficiency fractures: detection of vertebrae at risk on standard CT images using texture analysis and machine learning

European Radiology ◽

10.1007/s00330-018-5846-8 ◽

2018 ◽

Vol 29 (5) ◽

pp. 2207-2217 ◽

Cited By ~ 11

Author(s):

Urs J. Muehlematter ◽

Manoj Mannil ◽

Anton S. Becker ◽

Kerstin N. Vokinger ◽

Tim Finkenstaedt ◽

...

Keyword(s):

Machine Learning ◽

At Risk ◽

Texture Analysis ◽

Vertebral Body ◽

Ct Images ◽

Insufficiency Fractures

Download Full-text

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

10.1101/2020.12.02.20239194 ◽

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.

Download Full-text

Predicting Obstetric Disease With Machine Learning Applied to Patient-Reported Data (Preprint)

10.2196/preprints.11766 ◽

2018 ◽

Cited By ~ 1

Author(s):

Danielle Bradley ◽

Erin Landau ◽

Adam Wolfberg ◽

Alex Baron

Keyword(s):

Machine Learning ◽

At Risk ◽

Mobile Apps ◽

Learning Algorithms ◽

Machine Learning Algorithms ◽

Supervised Machine Learning ◽

Obstetric Outcomes ◽

Patient Reported ◽

Data Points ◽

Reported Data

BACKGROUND The rise of highly engaging digital health mobile apps over the past few years has created repositories containing billions of patient-reported data points that have the potential to inform clinical research and advance medicine. OBJECTIVE To determine if self-reported data could be leveraged to create machine learning algorithms to predict the presence of, or risk for, obstetric outcomes and related conditions. METHODS More than 10 million women have downloaded Ovia Health’s three mobile apps (Ovia Fertility, Ovia Pregnancy, and Ovia Parenting). Data points logged by app users can include information about menstrual cycle, health history, current health status, nutrition habits, exercise activity, symptoms, or moods. Machine learning algorithms were developed using supervised machine learning methodologies, specifically, Gradient Boosting Decision Tree algorithms. Each algorithm was developed and trained using anywhere from 385 to 5770 features and data from 77,621 to 121,740 app users. RESULTS Algorithms were created to detect the risk of developing preeclampsia, gestational diabetes, and preterm delivery, as well as to identify the presence of existing preeclampsia. The positive predictive value (PPV) was set to 0.75 for all of the models, as this was the threshold where the researchers felt a clinical response—additional screening or testing—would be reasonable, due to the likelihood of a positive outcome. Sensitivity ranged from 24% to 75% across all models. When PPV was adjusted from 0.75 to 0.52, the sensitivity of the preeclampsia prediction algorithm rose from 24% to 85%. When PPV was adjusted from 0.75 to 0.65, the sensitivity of the preeclampsia detection or diagnostic algorithm increased from 37% to 79%. CONCLUSIONS Algorithms based on patient-reported data can predict serious obstetric conditions with accuracy levels sufficient to guide clinical screening by health care providers and health plans. Further research is needed to determine whether such an approach can improve outcomes for at-risk patients and reduce the cost of screening those not at risk. Presenting the results of these models to patients themselves could also provide important insight into otherwise unknown health risks.

Download Full-text

Can population registry data predict which children with ADHD are at risk of later substance use disorders?

10.13056/acamh.12430 ◽

2020 ◽

Keyword(s):

Machine Learning ◽

At Risk ◽

Substance Use ◽

Substance Use Disorders ◽

Child Psychiatry ◽

Registry Data ◽

Early Prediction ◽

Children With Adhd ◽

Youth With Adhd

The first study to examine the potential of machine learning in early prediction of later substance use disorders (SUDs) in youth with ADHD has been published in the Journal of Child Psychiatry and Psychology.

Download Full-text

SCREENING OF PATIENTS AT RISK FOR WILD TYPE ATTR-CM USING A COMPUTATIONAL MACHINE LEARNING ALGORITHM

Canadian Journal of Cardiology ◽

10.1016/j.cjca.2021.07.134 ◽

2021 ◽

Vol 37 (10) ◽

pp. S65

Author(s):

C Willis ◽

K Kawamoto ◽

A Watanabe ◽

J Biskupiak ◽

K Nolen ◽

...

Keyword(s):

Machine Learning ◽

At Risk ◽

Learning Algorithm ◽

Machine Learning Algorithm ◽

Wild Type ◽

Patients At Risk

Download Full-text

MEWS++: Enhancing the Prediction of Clinical Deterioration in Admitted Patients through a Machine Learning Model

Journal of Clinical Medicine ◽

10.3390/jcm9020343 ◽

2020 ◽

Vol 9 (2) ◽

pp. 343 ◽

Cited By ~ 4

Author(s):

Arash Kia ◽

Prem Timsina ◽

Himanshu N. Joshi ◽

Eyal Klang ◽

Rohit R. Gupta ◽

...

Keyword(s):

Machine Learning ◽

At Risk ◽

Area Under The Curve ◽

Learning Model ◽

Clinical Deterioration ◽

Early Warning Score ◽

Support Vector ◽

Adult Age ◽

Machine Learning Model ◽

Patients At Risk

Early detection of patients at risk for clinical deterioration is crucial for timely intervention. Traditional detection systems rely on a limited set of variables and are unable to predict the time of decline. We describe a machine learning model called MEWS++ that enables the identification of patients at risk of escalation of care or death six hours prior to the event. A retrospective single-center cohort study was conducted from July 2011 to July 2017 of adult (age > 18) inpatients excluding psychiatric, parturient, and hospice patients. Three machine learning models were trained and tested: random forest (RF), linear support vector machine, and logistic regression. We compared the models’ performance to the traditional Modified Early Warning Score (MEWS) using sensitivity, specificity, and Area Under the Curve for Receiver Operating Characteristic (AUC-ROC) and Precision-Recall curves (AUC-PR). The primary outcome was escalation of care from a floor bed to an intensive care or step-down unit, or death, within 6 h. A total of 96,645 patients with 157,984 hospital encounters and 244,343 bed movements were included. Overall rate of escalation or death was 3.4%. The RF model had the best performance with sensitivity 81.6%, specificity 75.5%, AUC-ROC of 0.85, and AUC-PR of 0.37. Compared to traditional MEWS, sensitivity increased 37%, specificity increased 11%, and AUC-ROC increased 14%. This study found that using machine learning and readily available clinical data, clinical deterioration or death can be predicted 6 h prior to the event. The model we developed can warn of patient deterioration hours before the event, thus helping make timely clinical decisions.

Download Full-text

Development and Evaluation of a Machine Learning Model for the Early Identification of Patients at Risk for Sepsis

Annals of Emergency Medicine ◽

10.1016/j.annemergmed.2018.11.036 ◽

2019 ◽

Vol 73 (4) ◽

pp. 334-344 ◽

Cited By ~ 31

Author(s):

Ryan J. Delahanty ◽

JoAnn Alvarez ◽

Lisa M. Flynn ◽

Robert L. Sherwin ◽

Spencer S. Jones

Keyword(s):

Machine Learning ◽

At Risk ◽

Early Identification ◽

Learning Model ◽

Machine Learning Model ◽

Patients At Risk

Download Full-text

Learning to Identify At-Risk Students in Distance Education Using Interaction Counts

Revista de Informática Teórica e Aplicada ◽

10.22456/2175-2745.62211 ◽

2016 ◽

Vol 23 (2) ◽

pp. 124 ◽

Cited By ~ 2

Author(s):

Douglas Detoni ◽

Cristian Cechinel ◽

Ricardo Araujo Matsumura ◽

Daniela Francisco Brauner

Keyword(s):

Machine Learning ◽

At Risk ◽

At Risk Students ◽

Drop Out ◽

Support Vector ◽

Learning Models ◽

Data Set ◽

Student Dropout ◽

Vector Machines ◽

Machine Learning Models

Student dropout is one of the main problems faced by distance learning courses. One of the major challenges for researchers is to develop methods to predict the behavior of students so that teachers and tutors are able to identify at-risk students as early as possible and provide assistance before they drop out or fail in their courses. Machine Learning models have been used to predict or classify students in these settings. However, while these models have shown promising results in several settings, they usually attain these results using attributes that are not immediately transferable to other courses or platforms. In this paper, we provide a methodology to classify students using only interaction counts from each student. We evaluate this methodology on a data set from two majors based on the Moodle platform. We run experiments consisting of training and evaluating three machine learning models (Support Vector Machines, Naive Bayes and Adaboost decision trees) under different scenarios. We provide evidences that patterns from interaction counts can provide useful information for classifying at-risk students. This classification allows the customization of the activities presented to at-risk students (automatically or through tutors) as an attempt to avoid students drop out.

Download Full-text