Machine Learning Methods to Extract Documentation of Breast Cancer Symptoms From Electronic Health Records

Forsyth, Alexander W.; Barzilay, Regina; Hughes, Kevin S.; Lui, Dickson; Lorenz, Karl; Enzinger, Andrea C.; Tulsky, James A.; Lindvall, Charlotta

doi:10.1016/j.jpainsymman.2018.02.016

Cited by 72 publications

(46 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Opportunities also exist to incorporate advances in artificial intelligence and machine learning into chart documentation processes [70, 71]. In the future, it may be possible to embed artificial intelligence technologies, including machine learning, into EMR systems to alert physicians to patient information or physician orders that are potentially inaccurate, imprecise, incomplete, or inappropriate [72–79]. In Alberta, Canada efforts are underway to implement an EMR that will allow health information management specialists to conduct automatic documentation checks prior to patient visits, during care, and post discharge [80].…”

Section: Discussionmentioning

confidence: 99%

Strategies for improving physician documentation in the emergency department: a systematic review

et al. 2018

View full text Add to dashboard Cite

BackgroundPhysician chart documentation can facilitate patient care decisions, reduce treatment errors, and inform health system planning and resource allocation activities. Although accurate and complete patient chart data supports quality and continuity of patient care, physician documentation often varies in terms of timeliness, legibility, clarity and completeness. While many educational and other approaches have been implemented in hospital settings, the extent to which these interventions can improve the quality of documentation in emergency departments (EDs) is unknown.MethodsWe conducted a systematic review to assess the effectiveness of approaches to improve ED physician documentation. Peer reviewed electronic databases, grey literature sources, and reference lists of included studies were searched to March 2015. Studies were included if they reported on outcomes associated with interventions designed to enhance the quality of physician documentation.ResultsNineteen studies were identified that report on the effectiveness of interventions to improve physician documentation in EDs. Interventions included audit/feedback, dictation, education, facilitation, reminders, templates, and multi-interventions. While ten studies found that audit/feedback, dictation, pharmacist facilitation, reminders, templates, and multi-pronged approaches did improve the quality of physician documentation across multiple outcome measures, the remaining nine studies reported mixed results.ConclusionsPromising approaches to improving physician documentation in emergency department settings include audit/feedback, reminders, templates, and multi-pronged education interventions. Future research should focus on exploring the impact of implementing these interventions in EDs with and without emergency medical record systems (EMRs), and investigating the potential of emerging technologies, including EMR-based machine-learning, to promote improvements in the quality of ED documentation.Electronic supplementary materialThe online version of this article (10.1186/s12873-018-0188-z) contains supplementary material, which is available to authorized users.

show abstract

Section: Discussionmentioning

confidence: 99%

Strategies for improving physician documentation in the emergency department: a systematic review

et al. 2018

View full text Add to dashboard Cite

show abstract

“…Machine learning has been applied in multiple health care domains, including diabetes [7], cancer [8], cardiology [9], and mental health [10]. Most of the developed machine learning models and tools in research settings have investigated the potential of prognosis [11], diagnosis [12], or differentiation of clinical groups (eg, a group with a pathology and a healthy control group or groups with pathologies) [13], thus demonstrating promise toward the development of computerized decision support tools [14].…”

Section: Introductionmentioning

confidence: 99%

Applications of Machine Learning in Real-Life Digital Health Interventions: Review of the Literature

2019

View full text Add to dashboard Cite

Background Machine learning has attracted considerable research interest toward developing smart digital health interventions. These interventions have the potential to revolutionize health care and lead to substantial outcomes for patients and medical professionals. Objective Our objective was to review the literature on applications of machine learning in real-life digital health interventions, aiming to improve the understanding of researchers, clinicians, engineers, and policy makers in developing robust and impactful data-driven interventions in the health care domain. Methods We searched the PubMed and Scopus bibliographic databases with terms related to machine learning, to identify real-life studies of digital health interventions incorporating machine learning algorithms. We grouped those interventions according to their target (ie, target condition), study design, number of enrolled participants, follow-up duration, primary outcome and whether this had been statistically significant, machine learning algorithms used in the intervention, and outcome of the algorithms (eg, prediction). Results Our literature search identified 8 interventions incorporating machine learning in a real-life research setting, of which 3 (37%) were evaluated in a randomized controlled trial and 5 (63%) in a pilot or experimental single-group study. The interventions targeted depression prediction and management, speech recognition for people with speech disabilities, self-efficacy for weight loss, detection of changes in biopsychosocial condition of patients with multiple morbidity, stress management, treatment of phantom limb pain, smoking cessation, and personalized nutrition based on glycemic response. The average number of enrolled participants in the studies was 71 (range 8-214), and the average follow-up study duration was 69 days (range 3-180). Of the 8 interventions, 6 (75%) showed statistical significance (at the P =.05 level) in health outcomes. Conclusions This review found that digital health interventions incorporating machine learning algorithms in real-life studies can be useful and effective. Given the low number of studies identified in this review and that they did not follow a rigorous machine learning evaluation methodology, we urge the research community to conduct further studies in intervention settings following evaluation principles and demonstrating the potential of machine learning in clinical practice.

show abstract

“…Electronic medical records may be an alternate source of information. A recent study showed that physicians may already use open-text entries in electronic medical notes to document cancer patients’ symptoms [35]. Another limitation is that the inclusion of bigrams may cause concerns on the conditional independence assumption in LDA.…”

Section: Discussionmentioning

confidence: 99%

Leveraging Latent Dirichlet Allocation in processing free-text personal goals among patients undergoing bladder cancer surgery

Rapkin

Atkinson

et al. 2019

Qual Life Res

View full text Add to dashboard Cite

Purpose As we begin to leverage Big Data in health care settings and particularly in assessing patient-reported outcomes, there is a need for novel analytics to address unique challenges. One such challenge is in coding transcribed interview data, typically free-text entries of statements made during a face-to-face interview. Latent Dirichlet Allocation (LDA) offers statistical rigor and consistency in automating the interpretation of patients’ expressed concerns and coping strategies. Methods LDA was applied to interview data collected as part of a prospective, longitudinal study of QOL in N = 211 patients undergoing radical cystectomy and urinary diversion for bladder cancer. LDA analyzed personal goal statements to extract the latent topics and themes, stratified by time, and on things patients wanted to accomplish and prevent. Model comparison metrics determined the number of topics to extract. Results LDA extracted seven latent topics. Prior to surgery, patients’ priorities were primarily in cancer surgery and recovery. Six months after the surgery, they were replaced by goals on regaining a sense of normalcy, to resume work, to enjoy life more fully, and to appreciate friends and family more. LDA model parameters showed changing priorities, e.g., immediate concerns on surgery and resuming employment decreased post-surgery and were replaced by concerns over cancer recurrence and a desire to remain healthy and strong. Conclusions Novel Big Data analytics such as LDA offer the possibility of summarizing personal goals without the need for conventional fixed-length measures and resource-intensive qualitative data coding.

show abstract

Machine Learning Methods to Extract Documentation of Breast Cancer Symptoms From Electronic Health Records

Cited by 72 publications

References 23 publications

Strategies for improving physician documentation in the emergency department: a systematic review

Strategies for improving physician documentation in the emergency department: a systematic review

Applications of Machine Learning in Real-Life Digital Health Interventions: Review of the Literature

Leveraging Latent Dirichlet Allocation in processing free-text personal goals among patients undergoing bladder cancer surgery

Contact Info

Product

Resources

About