Browsing by Author "Harle, Chris"

Now showing 1 - 4 of 4
  • Thumbnail Image
    Item
    Balancing patient-centered and safe pain care for non-surgical inpatients: clinical and managerial perspectives
    (Elsevier, 2018-12-24) Mazurenko, Olena; Andraka-Christou, Barbara T.; Bair, Matthew J.; Kara, Areeba Y.; Harle, Chris; Health Policy and Management, School of Public Health
    Background: Hospitals and clinicians aim to deliver care that is safe. Simultaneously, they are ensuring that care is patient-centered, meaning that it is respectful of patients’ values, preferences, and experiences. However, little is known about delivering care in cases where these goals may not align. For example, hospitals and clinicians are facing the daunting challenge of balancing safe and patient-centered pain care for nonsurgical patients, due to lack of comprehensive care guidelines and complexity of this patient population. Methods: To gather clinical and managerial perspectives on the importance, feasibility, and strategies used to balance patient-centered care (PCC) and safe pain care for nonsurgical inpatients, we conducted in-depth, semi-structured interviews with hospitalists (n=10), registered nurses (n=10), and health care managers (n=10) from one healthcare system in the Midwestern United States. We systematically examined transcribed interviews and identified major themes using a thematic analysis approach. Results: Participants acknowledged the importance of balancing PCC and safe pain care. They envisioned this balance as a continuum, with certain patients for whom it is easier (e.g., opioid-naïve patient with a fracture), versus more difficult (e.g., patient with opioid use disorder). Participants also reported several strategies they use to balance PCC and safe pain care, including offering alternatives to opioids, setting realistic pain goals and expectations, and using a team approach. Conclusions: Clinicians and health care managers use various strategies to balance PCC and safe pain care for nonsurgical patients. Future studies should examine the effectiveness of these strategies on patient outcomes.
  • Thumbnail Image
    Item
    Classifying early infant feeding status from clinical notes using natural language processing and machine learning
    (Springer Nature, 2024-04-03) Lemas, Dominick J.; Du, Xinsong; Rouhizadeh, Masoud; Lewis, Braeden; Frank, Simon; Wright, Lauren; Spirache, Alex; Gonzalez, Lisa; Cheves, Ryan; Magalhães, Marina; Zapata, Ruben; Reddy, Rahul; Xu, Ke; Parker, Leslie; Harle, Chris; Young, Bridget; Louis‑Jaques, Adetola; Zhang, Bouri; Thompson, Lindsay; Hogan, William R.; Modave, François; Health Policy and Management, Richard M. Fairbanks School of Public Health
    The objective of this study is to develop and evaluate natural language processing (NLP) and machine learning models to predict infant feeding status from clinical notes in the Epic electronic health records system. The primary outcome was the classification of infant feeding status from clinical notes using Medical Subject Headings (MeSH) terms. Annotation of notes was completed using TeamTat to uniquely classify clinical notes according to infant feeding status. We trained 6 machine learning models to classify infant feeding status: logistic regression, random forest, XGBoost gradient descent, k-nearest neighbors, and support-vector classifier. Model comparison was evaluated based on overall accuracy, precision, recall, and F1 score. Our modeling corpus included an even number of clinical notes that was a balanced sample across each class. We manually reviewed 999 notes that represented 746 mother-infant dyads with a mean gestational age of 38.9 weeks and a mean maternal age of 26.6 years. The most frequent feeding status classification present for this study was exclusive breastfeeding [n = 183 (18.3%)], followed by exclusive formula bottle feeding [n = 146 (14.6%)], and exclusive feeding of expressed mother’s milk [n = 102 (10.2%)], with mixed feeding being the least frequent [n = 23 (2.3%)]. Our final analysis evaluated the classification of clinical notes as breast, formula/bottle, and missing. The machine learning models were trained on these three classes after performing balancing and down sampling. The XGBoost model outperformed all others by achieving an accuracy of 90.1%, a macro-averaged precision of 90.3%, a macro-averaged recall of 90.1%, and a macro-averaged F1 score of 90.1%. Our results demonstrate that natural language processing can be applied to clinical notes stored in the electronic health records to classify infant feeding status. Early identification of breastfeeding status using NLP on unstructured electronic health records data can be used to inform precision public health interventions focused on improving lactation support for postpartum patients.
  • Thumbnail Image
    Item
    Living kidney donor follow-up in a statewide health information exchange: health services utilization, health outcomes and policy implications
    (2016-05-24) Henderson, Macey Leigh; Stone, Cynthia L.; Dixon, Brian; Harle, Chris; Menachemi, Nir; Holmes, Ann; Fry-Revere, Sigrid
    Living donors have contributed about 6,000 kidneys per year in the past 10 years, but more than 100,000 individuals are still waiting for a kidney transplant. Living kidney donors undergo a major surgical procedure without direct medical benefit to themselves, but comprehensive follow-up information on living donors’ health is unfortunately limited. Expert recommendations suggest capturing clinical information beyond traditional sources to improve surveillance of co-morbid conditions from living kidney donors. Currently the United Network for Organ Sharing is responsible for collecting and reporting follow-up data for all living donors from U.S. transplant centers. Under policy implemented in February of 2013, transplant centers must submit follow-up date for two years after donation, but current processes often yield to incomplete and untimely reporting. This dissertation uses a statewide Health Information Exchange as a new clinical data source to 1) retrospectively identify a cohort of living kidney donors, 2) understand their follow-up care patterns, and 3) observe selected clinical outcomes including hypertension, diabetes and post-donation renal function.
  • Thumbnail Image
    Item
    Young people in recovery from substance use disorders: an analysis of a recovery high school's impact on student academic performance & recovery success
    (2017-12-18) Knotts, Adam Christopher; Stone, Cynthia; Dixon, Brian; Harle, Chris; Pfeifle, Bill; Rattermann, Mary Jo
    The purpose of this dissertation was to produce knowledge on the academic performance and recovery success of students enrolled in a Recovery High School. The study site was Hope Academy, located in Indianapolis, IN, and at the time of this publication, one of just five schools in the U.S. accredited by the Association of Recovery Schools. Students enrolled between Fall 2010 and Spring 2017 were evaluated using academic test scores (NWEA-MAP), a measure of recovery success (GAIN-SS), as well as key informant interviews with 13 students and five staff members. It was concluded that recovery school students displayed similar levels of academic growth when compared to a nationallyrepresentative matched Virtual Comparison Group, t-stat = +0.849 (p=0.397). This finding provides evidence that even after experiencing a relapse, recovery school students were capable of achieving similar levels of academic growth as their peers not in recovery from substance use disorders. Interview participants provided more context to the quantitative findings with first-hand accounts of the impact the recovery school had on students.