Social determinants of health and the prediction of missed breast imaging appointments
Abstract Background Predictive models utilizing social determinants of health (SDH), demographic data, and local weather data were trained to predict missed imaging appointments (MIA) among breast imaging patients at the Boston Medical Center (BMC). Patients were characterized by many different vari...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2022-11-01
|
| Series: | BMC Health Services Research |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12913-022-08784-8 |
| _version_ | 1811207872852262912 |
|---|---|
| author | Shahabeddin Sotudian Aaron Afran Christina A. LeBedis Anna F. Rives Ioannis Ch. Paschalidis Michael D. C. Fishman |
| author_facet | Shahabeddin Sotudian Aaron Afran Christina A. LeBedis Anna F. Rives Ioannis Ch. Paschalidis Michael D. C. Fishman |
| author_sort | Shahabeddin Sotudian |
| collection | DOAJ |
| description | Abstract Background Predictive models utilizing social determinants of health (SDH), demographic data, and local weather data were trained to predict missed imaging appointments (MIA) among breast imaging patients at the Boston Medical Center (BMC). Patients were characterized by many different variables, including social needs, demographics, imaging utilization, appointment features, and weather conditions on the date of the appointment. Methods This HIPAA compliant retrospective cohort study was IRB approved. Informed consent was waived. After data preprocessing steps, the dataset contained 9,970 patients and 36,606 appointments from 1/1/2015 to 12/31/2019. We identified 57 potentially impactful variables used in the initial prediction model and assessed each patient for MIA. We then developed a parsimonious model via recursive feature elimination, which identified the 25 most predictive variables. We utilized linear and non-linear models including support vector machines (SVM), logistic regression (LR), and random forest (RF) to predict MIA and compared their performance. Results The highest-performing full model is the nonlinear RF, achieving the highest Area Under the ROC Curve (AUC) of 76% and average F1 score of 85%. Models limited to the most predictive variables were able to attain AUC and F1 scores comparable to models with all variables included. The variables most predictive of missed appointments included timing, prior appointment history, referral department of origin, and socioeconomic factors such as household income and access to caregiving services. Conclusions Prediction of MIA with the data available is inherently limited by the complex, multifactorial nature of MIA. However, the algorithms presented achieved acceptable performance and demonstrated that socioeconomic factors were useful predictors of MIA. In contrast with non-modifiable demographic factors, we can address SDH to decrease the incidence of MIA. |
| first_indexed | 2024-04-12T04:12:11Z |
| format | Article |
| id | doaj.art-8ed24c16743f469aa5d4cd4349a9332e |
| institution | Directory Open Access Journal |
| issn | 1472-6963 |
| language | English |
| last_indexed | 2024-04-12T04:12:11Z |
| publishDate | 2022-11-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Health Services Research |
| spelling | doaj.art-8ed24c16743f469aa5d4cd4349a9332e2022-12-22T03:48:29ZengBMCBMC Health Services Research1472-69632022-11-0122111110.1186/s12913-022-08784-8Social determinants of health and the prediction of missed breast imaging appointmentsShahabeddin Sotudian0Aaron Afran1Christina A. LeBedis2Anna F. Rives3Ioannis Ch. Paschalidis4Michael D. C. Fishman5Department of Electrical and Computer Engineering, Division of Systems Engineering, Boston UniversityDepartment of Radiology, Boston University School of MedicineDepartment of Radiology, Boston University School of MedicineDepartment of Radiology, Boston University School of MedicineDepartment of Electrical and Computer Engineering, Division of Systems Engineering, Boston UniversityDepartment of Radiology, Boston University School of MedicineAbstract Background Predictive models utilizing social determinants of health (SDH), demographic data, and local weather data were trained to predict missed imaging appointments (MIA) among breast imaging patients at the Boston Medical Center (BMC). Patients were characterized by many different variables, including social needs, demographics, imaging utilization, appointment features, and weather conditions on the date of the appointment. Methods This HIPAA compliant retrospective cohort study was IRB approved. Informed consent was waived. After data preprocessing steps, the dataset contained 9,970 patients and 36,606 appointments from 1/1/2015 to 12/31/2019. We identified 57 potentially impactful variables used in the initial prediction model and assessed each patient for MIA. We then developed a parsimonious model via recursive feature elimination, which identified the 25 most predictive variables. We utilized linear and non-linear models including support vector machines (SVM), logistic regression (LR), and random forest (RF) to predict MIA and compared their performance. Results The highest-performing full model is the nonlinear RF, achieving the highest Area Under the ROC Curve (AUC) of 76% and average F1 score of 85%. Models limited to the most predictive variables were able to attain AUC and F1 scores comparable to models with all variables included. The variables most predictive of missed appointments included timing, prior appointment history, referral department of origin, and socioeconomic factors such as household income and access to caregiving services. Conclusions Prediction of MIA with the data available is inherently limited by the complex, multifactorial nature of MIA. However, the algorithms presented achieved acceptable performance and demonstrated that socioeconomic factors were useful predictors of MIA. In contrast with non-modifiable demographic factors, we can address SDH to decrease the incidence of MIA.https://doi.org/10.1186/s12913-022-08784-8Social determinants of healthMissed appointmentPredictive modelRadiologyBreast imaging |
| spellingShingle | Shahabeddin Sotudian Aaron Afran Christina A. LeBedis Anna F. Rives Ioannis Ch. Paschalidis Michael D. C. Fishman Social determinants of health and the prediction of missed breast imaging appointments BMC Health Services Research Social determinants of health Missed appointment Predictive model Radiology Breast imaging |
| title | Social determinants of health and the prediction of missed breast imaging appointments |
| title_full | Social determinants of health and the prediction of missed breast imaging appointments |
| title_fullStr | Social determinants of health and the prediction of missed breast imaging appointments |
| title_full_unstemmed | Social determinants of health and the prediction of missed breast imaging appointments |
| title_short | Social determinants of health and the prediction of missed breast imaging appointments |
| title_sort | social determinants of health and the prediction of missed breast imaging appointments |
| topic | Social determinants of health Missed appointment Predictive model Radiology Breast imaging |
| url | https://doi.org/10.1186/s12913-022-08784-8 |
| work_keys_str_mv | AT shahabeddinsotudian socialdeterminantsofhealthandthepredictionofmissedbreastimagingappointments AT aaronafran socialdeterminantsofhealthandthepredictionofmissedbreastimagingappointments AT christinaalebedis socialdeterminantsofhealthandthepredictionofmissedbreastimagingappointments AT annafrives socialdeterminantsofhealthandthepredictionofmissedbreastimagingappointments AT ioannischpaschalidis socialdeterminantsofhealthandthepredictionofmissedbreastimagingappointments AT michaeldcfishman socialdeterminantsofhealthandthepredictionofmissedbreastimagingappointments |