Identifying, Analyzing, and Visualizing Diagnostic Paths for Patients with Nonspecific Abdominal Pain

Patient-Clinician Diagnostic Concordance upon Hospital Admission

OBJECTIVES

 This study aimed to pilot an application-based patient diagnostic questionnaire (PDQ) and assess the concordance of the admission diagnosis reported by the patient and entered by the clinician.

METHODS

 Eligible patients completed the PDQ assessing patients' understanding of and confidence in the diagnosis 24 hours into hospitalization either independently or with assistance. Demographic data, the hospital principal problem upon admission, and International Classification of Diseases 10th Revision (ICD-10) codes were retrieved from the electronic health record (EHR). Two physicians independently rated concordance between patient-reported diagnosis and clinician-entered principal problem as full, partial, or no. Discrepancies were resolved by consensus. Descriptive statistics were used to report demographics for concordant (full) and nonconcordant (partial or no) outcome groups. Multivariable logistic regressions of PDQ questions and a priori selected EHR data as independent variables were conducted to predict nonconcordance.

RESULTS

 A total of 157 (77.7%) questionnaires were completed by 202 participants; 77 (49.0%), 46 (29.3%), and 34 (21.7%) were rated fully concordant, partially concordant, and not concordant, respectively. Cohen's kappa for agreement on preconsensus ratings by independent reviewers was 0.81 (0.74, 0.88). In multivariable analyses, patient-reported lack of confidence and undifferentiated symptoms (ICD-10 "R-code") for the principal problem were significantly associated with nonconcordance (partial or no concordance ratings) after adjusting for other PDQ questions (3.43 [1.30, 10.39], p = 0.02) and in a model using selected variables (4.02 [1.80, 9.55], p < 0.01), respectively.

CONCLUSION

 About one-half of patient-reported diagnoses were concordant with the clinician-entered diagnosis on admission. An ICD-10 "R-code" entered as the principal problem and patient-reported lack of confidence may predict patient-clinician nonconcordance early during hospitalization via this approach.

Analytical methods for identifying sequences of utilization in health data: a scoping review

BACKGROUND

Healthcare, as with other sectors, has undergone progressive digitalization, generating an ever-increasing wealth of data that enables research and the analysis of patient movement. This can help to evaluate treatment processes and outcomes, and in turn improve the quality of care. This scoping review provides an overview of the algorithms and methods that have been used to identify care pathways from healthcare utilization data.

METHOD

This review was conducted according to the methodology of the Joanna Briggs Institute and the Preferred Reporting Items for Systematic Reviews Extension for Scoping Reviews (PRISMA-ScR) Checklist. The PubMed, Web of Science, Scopus, and EconLit databases were searched and studies published in English between 2000 and 2021 considered. The search strategy used keywords divided into three categories: the method of data analysis, the requirement profile for the data, and the intended presentation of results. Criteria for inclusion were that health data were analyzed, the methodology used was described and that the chronology of care events was considered. In a two-stage review process, records were reviewed by two researchers independently for inclusion. Results were synthesized narratively.

RESULTS

The literature search yielded 2,865 entries; 51 studies met the inclusion criteria. Health data from different countries ([Formula: see text]) and of different types of disease ([Formula: see text]) were analyzed with respect to different care events. Applied methods can be divided into those identifying subsequences of care and those describing full care trajectories. Variants of pattern mining or Markov models were mostly used to extract subsequences, with clustering often applied to find care trajectories. Statistical algorithms such as rule mining, probability-based machine learning algorithms or a combination of methods were also applied. Clustering methods were sometimes used for data preparation or result compression. Further characteristics of the included studies are presented.

CONCLUSION

Various data mining methods are already being applied to gain insight from health data. The great heterogeneity of the methods used shows the need for a scoping review. We performed a narrative review and found that clustering methods currently dominate the literature for identifying complete care trajectories, while variants of pattern mining dominate for identifying subsequences of limited length.

Natural history of abdominal pain in family practice: Longitudinal study of electronic medical record data in southwestern Ontario

OBJECTIVE

To examine the frequency, natural history, and outcomes of 3 subtypes of abdominal pain (general abdominal pain, epigastric pain, localized abdominal pain) among patients visiting Canadian family practices.

DESIGN

Retrospective cohort study with a 4-year longitudinal analysis.

SETTING

Southwestern Ontario.

PARTICIPANTS

A total of 1790 eligible patients with International Classification of Primary Care codes for abdominal pain from 18 family physicians in 8 group practices.

MAIN OUTCOME MEASURES

The symptom pathways, the length of an episode, and the number of visits.

RESULTS

Abdominal pain accounted for 2.4% of the 15,149 patient visits and involved 14.0% of the 1790 eligible patients. The frequencies of each of the 3 subtypes were as follows: localized abdominal pain, 89 patients, 1.0% of visits, and 5.0% of patients; general abdominal pain, 79 patients, 0.8% of visits, and 4.4% of patients; and epigastric pain, 65 patients, 0.7% of visits, and 3.6% of patients. Those with epigastric pain received more medications, and patients with localized abdominal pain underwent more investigations. Three longitudinal outcome pathways were identified. Pathway 1, in which the symptom remains at the end of the visit with no diagnosis, was the most common among patients with all subtypes of abdominal symptoms at 52.8%, 54.4%, and 50.8% for localized, general, and epigastric pain, respectively, and the symptom episodes were relatively short. Less than 15% of patients followed pathway 2, in which a diagnosis is made and the symptom persists, and yet the episodes were long with 8.75 to 16.80 months' mean duration and 2.70 to 4.00 mean number of visits. Pathway 3, in which a diagnosis is made and there are no further visits for that symptom, occurred approximately one-third of the time, with about 1 visit over about 2 months. Prior chronic conditions were common across all 3 subtypes of abdominal pain ranging from 72.2% to 80.0%. Psychological symptoms consistently occurred at a rate of approximately one-third.

CONCLUSION

The 3 subtypes of abdominal pain differed in clinically important ways. The most frequent pathway was that the symptom remained with no diagnosis, suggesting a need for clinical approaches and education programs for care of symptoms themselves, not merely in the service of coming to a diagnosis. The importance of prior chronic conditions and psychological conditions was highlighted by the results.

Characterization of Laboratory Flow and Performance for Process Improvements via Application of Process Mining

BACKGROUND

The rising level of laboratory automation provides an increasing number of logged events that can be used for the characterization of laboratory performance and process improvements. This abundance of data is often underutilized for improving laboratory efficiency.

OBJECTIVES

The first aim of this descriptive study is to provide a structured approach for transforming raw laboratory data to data that is suitable for process mining. The second aim is to describe a process mining approach for mapping and characterizing the sample flow in a clinical chemistry laboratory to identify areas for improvement in the testing process.

METHODS

Data were extracted from instrument log files and the middleware between laboratory instruments and information technology infrastructure. Process mining was used for automated process discovery and analysis. Laboratory performance was quantified in terms of relevant key performance indicators (KPIs): turnaround time, timeliness, workload, work-in-process, and machine downtime.

RESULTS

The method was applied to two Dutch university hospital clinical chemistry laboratories. We identified areas where alternative routes might increase laboratory efficiency and observed the negative effects of machine downtime on laboratory performance. This encourages the laboratory to review sample routes in its analyzer lines, the routes of high priority samples during instrument downtime, as well as the preventive maintenance policy.

CONCLUSION

This article provides the first application of process mining to event data from a medical diagnostic laboratory for automated process model discovery. Our study shows that process mining, with the use of relevant KPIs, provides valuable insights for laboratories that motivates the disclosure and increased utilization of laboratory event data, which in turn drive the analytical staff to intervene in the process to achieve the set performance goals. Our approach is vendor independent and widely applicable for all medical diagnostic laboratories.

A flexible framework for visualizing and exploring patient misdiagnosis over time

Diagnosis is a complex and ambiguous process and yet, it is the critical hinge point for all subsequent clinical reasoning and decision-making. Tracking the quality of the patient diagnostic process has the potential to provide valuable insights in improving the diagnostic accuracy and to reduce downstream errors but needs to be informative, timely, and efficient at scale. However, due to the rate at which healthcare data are captured on a daily basis, manually reviewing the diagnostic history of each patient would be a severely taxing process without efficient data reduction and representation. Application of data visualization and visual analytics to healthcare data is one promising approach for addressing these challenges. This paper presents a novel flexible visualization and analysis framework for exploring the patient diagnostic process over time (i.e., patient diagnosis paths). Our framework allows users to select a specific set of patients, events and/or conditions, filter data based on different attributes, and view further details on the selected patient cohort while providing an interactive view of the resulting patient diagnosis paths. A practical demonstration of our system is presented with a case study exploring infection-based patient diagnosis paths.

Development of a Web-Based Nonoperative Small Bowel Obstruction Treatment Pathway App

OBJECTIVE

An electronic pathway for the management of adhesive small bowel obstruction (SBO) was built and implemented on top of the electronic health record. The aims of this study are to describe the development of the electronic pathway and to report early outcomes.

METHODS

The electronic SBO pathway was designed and implemented at a single institution. All patients admitted to a surgical service with a diagnosis of adhesive SBO were enrolled. Outcomes were compared across three time periods: (1) patients not placed on either pathway from September 2013 through December 2014, (2) patients enrolled in the paper pathway from January 2017 through January 2018, and (3) patients enrolled in the electronic pathway from March through October 2018. The electronic SBO pathway pulls real-time data from the electronic health record to prepopulate the evidence-based algorithm. Outcomes measured included length of stay (LOS), time to surgery, readmission, surgery, and need for bowel resection. Comparative analyses were completed with Pearson's chi-squared, analysis of variance, and Kruskal-Wallis tests.

RESULTS

There were 46 patients enrolled in the electronic pathway compared with 93 patients on the paper pathway, and 101 nonpathway patients. Median LOS was lower in both pathway cohorts compared with those not on either pathway (3 days [range 1-11] vs. 3 days [range 1-27] vs. 4 days [range 1-13], p = 0.04). Rates of readmission, surgery, time to surgery, and bowel resection were not significantly different across the three groups.

CONCLUSION

It is feasible to implement and utilize an electronic, evidence-based clinical pathway for adhesive SBOs. Use of the electronic and paper pathways was associated with decreased hospital LOS for patients with adhesive SBOs.

Review of Clinical Research Informatics

OBJECTIVES

Clinical Research Informatics (CRI) declares its scope in its name, but its content, both in terms of the clinical research it supports-and sometimes initiates-and the methods it has developed over time, reach much further than the name suggests. The goal of this review is to celebrate the extraordinary diversity of activity and of results, not as a prize-giving pageant, but in recognition of the field, the community that both serves and is sustained by it, and of its interdisciplinarity and its international dimension.

METHODS

Beyond personal awareness of a range of work commensurate with the author's own research, it is clear that, even with a thorough literature search, a comprehensive review is impossible. Moreover, the field has grown and subdivided to an extent that makes it very hard for one individual to be familiar with every branch or with more than a few branches in any depth. A literature survey was conducted that focused on informatics-related terms in the general biomedical and healthcare literature, and specific concerns ("artificial intelligence", "data models", "analytics", etc.) in the biomedical informatics (BMI) literature. In addition to a selection from the results from these searches, suggestive references within them were also considered.

RESULTS

The substantive sections of the paper-Artificial Intelligence, Machine Learning, and "Big Data" Analytics; Common Data Models, Data Quality, and Standards; Phenotyping and Cohort Discovery; Privacy: Deidentification, Distributed Computation, Blockchain; Causal Inference and Real-World Evidence-provide broad coverage of these active research areas, with, no doubt, a bias towards this reviewer's interests and preferences, landing on a number of papers that stood out in one way or another, or, alternatively, exemplified a particular line of work.

CONCLUSIONS

CRI is thriving, not only in the familiar major centers of research, but more widely, throughout the world. This is not to pretend that the distribution is uniform, but to highlight the potential for this domain to play a prominent role in supporting progress in medicine, healthcare, and wellbeing everywhere. We conclude with the observation that CRI and its practitioners would make apt stewards of the new medical knowledge that their methods will bring forward.

Ontology-Based Interactive Visualization of Patient-Generated Research Questions

BACKGROUND

Crohn's disease and colitis are chronic conditions that affect every facet of patients' lives (e.g., social interaction, family, work, diet, and sleep). Thus, treatment consists largely of disease management. The University of North Carolina at Chapel Hill chapter of the Crohn's and Colitis Foundation-IBD Partners-has created an interactive website that, in addition to providing helpful information and disease management tools, provides a discussion forum for patients to talk about their experiences and suggest new lines of research into Crohn's disease and colitis.

OBJECTIVES

The primary objective of this work is to enable researchers to more effectively browse the forum content. Researchers wish to identify important/popular patient-suggested research topics, appreciate the full breadth of the research topics, and see connections between them, in order to more effectively prioritize research agendas.

METHODS

To help structure the forum content we have developed an ontology describing the major themes in the discussion forum. We have also created a prototype interactive visualization tool that leverages the ontology to help researchers identify common themes and related patient-generated research topics via linked views of (1) the ontology, (2) a research topic overview clustered by relevant ontology terms, and (3) a detailed view of the discussion forum content.

RESULTS

We discuss visualizations and interactions enabled by the visualization tool, provide an example scenario using the tool, and discuss limitations and future work based on feedback from potential users.

CONCLUSION

The integration of a user-community specific ontology with an interactive visualization tool is a promising approach for enabling researchers to more effectively study user-generated research questions.