Dataset Information

Clusters of medical specialties around patients with multimorbidity - employing fuzzy c-means clustering to explore multidisciplinary collaboration.

ABSTRACT:

Background

Hospital care organization, structured around medical specialties and focused on the separate treatment of individual organ systems, is challenged by the increasing prevalence of multimorbidity. To support the hospitals' realization of multidisciplinary care, we hypothesized that using machine learning on clinical data helps to identify groups of medical specialties who are simultaneously involved in hospital care for patients with multimorbidity.

Methods

We conducted a cross-sectional study of patients in a Dutch general hospital and used a fuzzy c-means clustering algorithm for the analysis. We explored the patients' membership degrees in each cluster to identify subgroups of medical specialties that provide care to the same patients with multimorbidity. We used retrospectively collected electronic health record data from 2017. We extracted data from 22,133 patients aged ≥18 years who had received outpatient clinical care for two or more chronic and/ or oncological diagnoses.

Results

We found six clusters of medical specialties and identified 22 subgroups. The clusters were labeled based on the specialties that most characterized them: 1. dermatology/ plastic surgery, 2. six specialties (gynecology/ rheumatology/ orthopedic surgery/ urology/ gastroenterology/ otorhinolaryngology), 3. pulmonology, 4. internal medicine/ cardiology/ geriatrics, 5. neurology/ physiatry (rehabilitation)/ anesthesiology, and 6. internal medicine. Most patients had a full or dominant membership to one of these clusters of medical specialties (11 subgroups), whereas fewer patients had a membership to two clusters. The prevalence of specific diagnosis groups, patient characteristics, and healthcare utilization differed between subgroups.

Conclusion

Our study shows that clusters and subgroups of medical specialties simultaneously involved in hospital care for patients with multimorbidity can be identified with fuzzy c-means cluster analysis using clinical data. Clusters and subgroups differed regarding the involved medical specialties, diagnoses, patient characteristics, and healthcare utilization. With this strategy, hospitals and medical specialists can further analyze which subgroups are target populations that might benefit from improved multidisciplinary collaboration.

SUBMITTER: Verhoeff M

PROVIDER: S-EPMC10492354 | biostudies-literature | 2023 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Clusters of medical specialties around patients with multimorbidity - employing fuzzy c-means clustering to explore multidisciplinary collaboration.

Verhoeff Marlies M Weil Liann I LI Chu Hung H Vermeeren Yolande Y de Groot Janke J Burgers Jako S JS Jeurissen Patrick P T PPT Zwerwer Leslie R LR van Munster Barbara C BC

BMC health services research 20230909 1

<h4>Background</h4>Hospital care organization, structured around medical specialties and focused on the separate treatment of individual organ systems, is challenged by the increasing prevalence of multimorbidity. To support the hospitals' realization of multidisciplinary care, we hypothesized that using machine learning on clinical data helps to identify groups of medical specialties who are simultaneously involved in hospital care for patients with multimorbidity.<h4>Methods</h4>We conducted a ...[more]

PMID: 37689648

Similar Datasets

Project description:BackgroundOne of the main objectives of Electronic Health Records (EHRs) is to enhance collaboration among healthcare professionals. However, our knowledge of how EHRs actually affect collaborative practices is limited. This study examines how an EHR facilitates and constrains collaboration in five outpatient clinics.MethodsWe conducted an embedded case study at five outpatient clinics of a Dutch hospital that had implemented an organization-wide EHR. Data were collected through interviews with representatives of medical specialties, administration, nursing, and management. Documents were analyzed to contextualize these data. We examined the following collaborative affordances of EHRs: (1) portability, (2) co-located access, (3) shared overviews, (4) mutual awareness, (5) messaging, and (6) orchestrating.ResultsOur findings demonstrate how an EHR will both facilitate and constrain collaboration among specialties and disciplines. Affordances that were inscribed in the system for collaboration purposes were not fully actualized in the hospital because: (a) The EHR helps health professionals coordinate patient care on an informed basis at any time and in any place but only allows asynchronous patient record use. (b) The comprehensive patient file affords joint clinical decision-making based on shared data, but specialty- and discipline-specific user-interfaces constrain mutual understanding of that data. Moreover, not all relevant information can be easily shared across specialties and outside the hospital. (c) The reduced necessity for face-to-face communication saves time but is experienced as hindering collective responsibility for a smooth workflow. (d) The EHR affords registration at the source and registration of activities through orders, but the heightened administrative burden for physicians and the strict authorization rules on inputting data constrain the flexible, multidisciplinary collaboration. (e) While the EHR affords a complete overview, information overload occurs due to the parallel generation of individually owned notes and the high frequency of asynchronous communication through messages of varying clinical priority.ConclusionsFor the optimal actualization of EHRs' collaborative affordances in hospitals, coordinated use of these affordances by health professionals is a prerequisite. Such coordinated use requires organizational, technical, and behavioral adaptations. Suggestions for hospital-wide policies to enhance trust in both the EHR and in its coordinated use for effective collaboration are offered.

Dataset Information

Clusters of medical specialties around patients with multimorbidity - employing fuzzy c-means clustering to explore multidisciplinary collaboration.

Background

Methods

Results

Conclusion

Publications

Clusters of medical specialties around patients with multimorbidity - employing fuzzy c-means clustering to explore multidisciplinary collaboration.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets