scholarly journals The application of predictive analytics to identify at-risk students in health professions education

2021 ◽  
Author(s):  
Anshul Kumar ◽  
Roger A. Edwards ◽  
Lisa Walker
Keyword(s):  
At Risk ◽  
Predictive Analytics ◽  
Physician Assistant ◽  
Student Assessment ◽  
Health Professions ◽  
Warning Signs ◽  
K Nearest Neighbors ◽  
One Year ◽  
Certifying Examination ◽  
Leave One Out

Introduction: When a learner fails to reach a milestone, educators often wonder if there had been any warning signs that could have allowed them to intervene sooner. Machine learning is used to predict which students are at risk of failing a national certifying exam. Predictions are made well in advance of the exam, such that educators can meaningfully intervene before students take the exam.Methods: Using already-collected, first-year student assessment data from four cohorts in a Master of Physician Assistant Studies program, the authors implement an "adaptive minimum match" version of the k-nearest neighbors algorithm (AMMKNN), using changing numbers of neighbors to predict each student's future exam scores on the Physician Assistant National Certifying Examination (PANCE). Leave-one-out cross validation (LOOCV) was used to evaluate the practical capabilities of this model, before making predictions for new students. Results: The best predictive model has an accuracy of 93%, sensitivity of 69%, and specificity of 94%. It generates a predicted PANCE score for each student, one year before they are scheduled to take the exam. Students can then be prospectively categorized into groups that need extra support, optional extra support, or no extra support. The educator then has one year to provide the appropriate customized support to each type of student. Conclusions: Predictive analytics can help health professions educators allocate scarce time and resources across their students. Interprofessional educators can use the included methods and code to generate predicted test outcomes for students. The authors recommend that educators using this or similar predictive methods act responsibly and transparently.

Parent-Mediated Intervention for One-Year-Olds Screened as At-Risk for Autism Spectrum Disorder: A Randomized Controlled Trial

2017 ◽  
Vol 47 (11) ◽  
pp. 3520-3540 ◽  
Author(s):  
Linda R. Watson ◽  
Elizabeth R. Crais ◽  
Grace T. Baranek ◽  
Lauren Turner-Brown ◽  
John Sideris ◽  
...  
Keyword(s):  
Autism Spectrum Disorder ◽  
At Risk ◽  
Randomized Controlled Trial ◽  
Controlled Trial ◽  
Autism Spectrum ◽  
Spectrum Disorder ◽  
Randomized Controlled ◽  
One Year

scholarly journals Explaining the association between urbanicity and psychotic-like experiences in adolescence: The indirect effect of urban exposures

2021 ◽  
Author(s):  
Abhishek Saxena ◽  
David Dodell-Feder
Keyword(s):  
At Risk ◽  
Indirect Effect ◽  
Public Health Intervention ◽  
The United States ◽  
Urban Environments ◽  
Income Disparity ◽  
Lead Paint ◽  
Increased Risk ◽  
Worldwide Phenomenon ◽  
One Year

Urban living is a growing worldwide phenomenon with more than two-thirds of people expected to live in cities by 2050. Although there are many benefits to living in an urban environment, urbanicity has also been associated with deleterious health outcomes, including increased risk for psychotic outcomes particularly when the urban exposure occurs in adolescence. However, the mechanisms underlying this association is unclear. Here, we utilize one-year follow-up data from a large (N=7,979), nationwide study of adolescence in the United States to clarify why urbanicity might impact psychotic-like experiences (PLE) by looking at the indirect effect of eight candidate urbanicity-related physical (e.g., pollution) and social (e.g., poverty) exposures. Consistent with other work, we find that of the evaluated exposures related to urbanicity, several were also related to increased number of PLE and associated distress: PM2.5, proximity to roads, census-level homes at-risk for exposure to lead paint, census-level poverty, and census-level income-disparity. Mediation analysis revealed that a substantial proportion the urbanicity-PLE association could be explained by PM2.5 (23% of the urbanicity-PLE number association), families in poverty (57-67% of the urbanicity-PLE number and distress association), and income disparity (55-66% of the urbanicity-PLE number and distress association). Together, these findings suggest that specific urban-related exposures might help to explain why those in urban environments are disproportionately at-risk for psychosis and point towards areas for public health intervention.

scholarly journals Area of Interest of Indonesian Researches in Medical and Health Professions Education: Future Direction

2017 ◽  
Vol 6 (2) ◽  
pp. 67
Author(s):  
Mora Claramita ◽  
Gandes Retno Rahayu ◽  
Rahmi Surayya ◽  
Abu Bakar ◽  
Murti Mandawati ◽  
...  
Keyword(s):  
Medical Education ◽  
Student Assessment ◽  
Universal Coverage ◽  
Health Professions ◽  
Health Professions Education ◽  
Team Work ◽  
Area Of Interest ◽  
Study Results ◽  
Asian Context ◽  
Future Direction

Background: Medical education research has been flourished in the past two decades in Indonesia. It is highly important to study results of medical education researches in Indonesia to provide future direction for medical education. Six published literature in medical education from Asian context was used as the basis of this study.Method: We used the narrative review in which quantitative data were interpreted qualitatively. All national and international publication and the unpublished research in medical education from Indonesia between 2000 - 2013 were collected with multiple methods based on 8 criteria of inclusion/ exclusion. We also grouped the articles into quantitative and qualitative groups based on each method in each study.Results: Total articles interpreted was 151 and grouped into 17 areas of interest and level of evidences from ‘very rarely’ to ‘very frequently’ studied. Studies in the area of understanding problem–based learning (PBL) are still dominating the area of interest including the student-assessment within PBL program. Other areas are still rarely done, especially research in health professions education other than medical doctors.Conclusion: Research in medical education in Indonesia should be more stimulated; in terms of numbers and quality, more importantly to strive for future agent of culture, socio-economic and political changes based on the actual community problems in the universal coverage era toward solid interprofessional team work to accomplish patient safety.

Abstract 16588: Using Machine Learning to Improve Survival Prediction After Heart Transplantation

Circulation ◽  
2020 ◽  
Vol 142 (Suppl_3) ◽  
Author(s):  
Brian Ayers ◽  
Toumas Sandhold ◽  
Igor Gosev ◽  
Sunil Prasad ◽  
Arman Kilic
Keyword(s):  
Machine Learning ◽  
Logistic Regression ◽  
Heart Transplantation ◽  
Risk Prediction ◽  
Predictive Analytics ◽  
Predictive Performance ◽  
Orthotopic Heart Transplantation ◽  
Survival Prediction ◽  
One Year ◽  
Testing Set

Introduction: Prior risk models for predicting survival after orthotopic heart transplantation (OHT) have displayed only modest discriminatory capability. With increasing interest in the application of machine learning (ML) to predictive analytics in clinical medicine, this study aimed to evaluate whether modern ML techniques could improve risk prediction in OHT. Methods: Data from the United Network for Organ Sharing registry was collected for all adult patients that underwent OHT from 2000 through 2019. The primary outcome was one-year post-transplant mortality. Dimensionality reduction and data re-sampling were employed during training. The final ensemble model was created from 100 different models of each algorithm: deep neural network, logistic regression, adaboost, and random forest. Discriminatory capability was assessed using area under receiver-operating-characteristic curve (AUROC), net reclassification index (NRI), and decision curve analysis (DCA). Results: Of the 33,657 study patients, 26,926 (80%) were randomly selected for the training set and 6,731 (20%) as a separate testing set. One-year mortality was balanced between cohorts (11.0% vs 11.3%). The optimal model performance was a final ensemble ML model. This model demonstrated an improved AUROC of 0.764 (95% CI, 0.745-0.782) in the testing set as compared to the other models (Figure). Additionally, the final model demonstrated an improvement of 72.9% ±3.8% (p<0.001) in predictive performance as assessed by NRI compared to logistic regression. The DCA showed the final ensemble method improved risk prediction across the entire spectrum of predicted risk as compared to all other models (p<0.001). Conclusions: An ensemble ML model was able to achieve greater predictive performance as compared to individual ML models as well as logistic regression for predicting survival after OHT. This analysis demonstrates the promise of ML techniques in risk prediction in OHT.

Psychiatric Aspects of Sterilization: A Prospective Survey

1979 ◽  
Vol 135 (4) ◽  
pp. 304-309 ◽  
Author(s):  
Anne H. W. Smith
Keyword(s):  
At Risk ◽  
Sexual Relationships ◽  
Psychiatric Disturbance ◽  
Prospective Survey ◽  
One Year

SummaryPatients consecutively referred for sterilization were examined at the time of referral, two months and one year after operation.Twenty-five per cent of the sample were identified as psychiatric cases at the time of referral, and rates of disturbance were even higher in some subgroups of women. The rate of disturbance fell in all these groups by one year after operation.New psychiatric disturbance following sterilization was similar in amount to that found in the community and was not related to any groups of women said in the literature to be at risk apart from those divorced or separated at the time of referral.Many experienced improvement in their marital and sexual relationships and only 3 per cent expressed feelings of regret.

Early Motor Repertoire Assessment and One-year Neurocognitive Outcome in Infants At-risk. (A pilot communication)

2018 ◽  
Vol 131 ◽  
pp. S154
Author(s):  
D. Chegodaev ◽  
A. Palchik ◽  
O. Lvova ◽  
M. Lavrova ◽  
N. Bakushkina ◽  
...  
Keyword(s):  
At Risk ◽  
Neurocognitive Outcome ◽  
One Year

scholarly journals Imperfect physician assistant and physical therapist admissions processes in the United States

2014 ◽  
Vol 11 ◽  
pp. 11 ◽  
Author(s):  
Phillip Eugene Jones ◽  
Susan Simpkins ◽  
Jennie Alicea Hocking
Keyword(s):  
United States ◽  
Physical Therapist ◽  
Physician Assistant ◽  
Reliability And Validity ◽  
Health Professions ◽  
The United States ◽  
Grade Point Averages ◽  
High Stakes ◽  
Student Centered ◽  
Grade Point

We compared and contrasted physician assistant and physical therapy profession admissions processes based on the similar number of accredited programs in the United States and the co-existence of many programs in the same school of health professions, because both professions conduct similar centralized application procedures administered by the same organization. Many studies are critical of the fallibility and inadequate scientific rigor of the high-stakes nature of health professions admissions decisions, yet typical admission processes remain very similar. Cognitive variables, most notably undergraduate grade point averages, have been shown to be the best predictors of academic achievement in the health professions. The variability of non-cognitive attributes assessed and the methods used to measure them have come under increasing scrutiny in the literature. The variance in health professions students’ performance in the classroom and on certifying examinations remains unexplained, and cognitive considerations vary considerably between and among programs that describe them. One uncertainty resulting from this review is whether or not desired candidate attributes highly sought after by individual programs are more student-centered or graduate-centered. Based on the findings from the literature, we suggest that student success in the classroom versus the clinic is based on a different set of variables. Given the range of positions and general lack of reliability and validity in studies of non-cognitive admissions attributes, we think that health professions admissions processes remain imperfect works in progress.

scholarly journals Norwegian children and adolescents in blended families are at risk of larger one‐year BMI increments

2019 ◽  
Vol 109 (3) ◽  
pp. 587-594
Author(s):  
Hege Kristiansen ◽  
Mathieu Roelants ◽  
Robert Bjerknes ◽  
Petur B. Juliusson
Keyword(s):  
At Risk ◽  
Children And Adolescents ◽  
Blended Families ◽  
One Year
Sign in / Sign up

Export Citation Format

Share Document