International Journal of Medical Informatics最新文献

Background

Methods

Results

Conclusion

Introduction

Materials and methods

Results

Conclusions

Background

Standardized Nursing Languages (SNLs) have enabled nursing assessments and care to be better documented and visible in electronic health records (EHRs). However, its implementation is challenging and heterogeneous across clinical settings. This study aimed to demonstrate the challenges experienced by members of a European nursing organization, ACENDIO, in implementing SNLs in documentation systems across countries and offer recommendations about its use.

Material and methods

The study was executed in two phases. First, an online survey was distributed among ACENDIO members. Second, members participated in two expert panels. Discussions were recorded, and thematic analysis was performed to formulate challenges and recommendations on the use of SNLs.

Results

The findings highlight that nurses across Europe are faced with several issues with current documentation systems in clinical settings, limited education on SNLs, and challenges in research on SNLs. Nurses, managers, vendors, educators and researchers should work closely together to face the challenges in the implementation of SNLs in electronic documentation systems.

Conclusion

To fully utilize the beneficial effects of the use of SNLs, the call to action is to develop comprehensive collaborations of nursing practice, education, and research.

Background

Objectives

Methods

Results

Conclusions

Background

As the number of revision total knee arthroplasty (TKA) continues to rise, close attention has been paid to factors influencing postoperative length of stay (LOS). The aim of this study is to develop generalizable machine learning (ML) algorithms to predict extended LOS following revision TKA using data from a national database.

Methods

23,656 patients undergoing revision TKA between 2013 and 2020 were identified using the American College of Surgeons National Surgical Quality Improvement Program (ACS-NSQIP) database. Patients with missing data and those undergoing re-revision or conversion from unicompartmental knee arthroplasty were excluded. Four ML algorithms were applied and evaluated based on their (1) ability to distinguish between at-risk and not-at-risk patients, (2) accuracy, (3) calibration, and (4) clinical utility.

Results

All four ML predictive algorithms demonstrated good accuracy, calibration, clinical utility, and discrimination, with all models achieving a similar area under the curve (AUC) (AUC_LR=AUC_RF=AUC_HGB=0.75, AUC_ANN=0.74). The most important predictors of prolonged LOS were found to be operative time, preoperative diagnosis of sepsis, and body mass index (BMI).

Conclusions

ML models developed in this study demonstrated good performance in predicting extended LOS in patients undergoing revision TKA. Our findings highlight the importance of utilizing nationally representative patient data for model development. Prolonged operative time, preoperative sepsis, BMI, and elevated preoperative serum creatinine and BUN were noted to be significant predictors of prolonged LOS. Knowledge of these associations may aid with patient-specific preoperative planning, discharge planning, patient counseling, and cost containment with revision TKA.

Background

Methods

Findings

Principal conclusions

Purpose

Biomedical research is a pillar of every medical student’s career. When collecting data, several regulations are established to ensure the protection of individuals. Most medical students are not compliant with the guidelines, and this is probably due to a lack of knowledge. The aim of our research is to evaluate the knowledge and behavior of medical students regarding these rules, then attempt to explain the results obtained.

Methods

This is a sequential explanatory mixed study including an initial quantitative section followed by an explanatory qualitative section. For the quantitative part, we administered a questionnaire based on the information security regulation and the GDPR to third- and fourth-year medical students. We evaluated their knowledge and behaviors and their correlation. For the qualitative part, we conducted semi-structured interviews with eight students followed by thematic analysis to explain the results.

Results

Most students have a lack of knowledge. A correlation was found between the non-compliant behavior of keeping the laptop unattended in a public place and a low level of knowledge. For the qualitative section, the thematic analysis represents three groups to explain non-compliant behavior: lack of knowledge, work overload, and consideration of the hospital as a safe place.

Conclusion

Data collection and information security rules are rarely followed by medical students. This is mainly due to lack of knowledge, work overload and assuming the hospital as a safe place. Future awareness interventions would be necessary to improve non-compliant behavior and subsequently ensure a more secure environment during medical research.

Objectives

Teleconsultation is anticipated to have a long-term role in primary care. However, conducting virtual physical examinations is a well-known limitation. To anticipate unmet needs general practitioners (GPs) and patients may experience during teleconsultation, this study aims to automatically identify physical examinations typically conducted during in-person GP consultation.

Material and Methods

This study utilizes 281 GP in-person consultations (de-identified transcripts & video recordings) within UK general practices, where 169 eligible ones were included in this study. We propose an automated text-based approach using regular expressions on keywords in GP-patient consultation dialogue (e.g., “roll up your sleeves”) to identify physical examinations (e.g. blood pressure measurement). This approach involves the construction of conceptual diagrams to visually inspect the relationship between keywords and physical examinations, syntax analysis to identify patterns between keywords and generate regular expressions, and the use of these regular expressions in consultation transcripts to detect potential instances of physical examinations, where matching video frames were subsequently retrieved. The performance of our automated text-based approach is compared to manual classification by 2 independent researchers using 5-fold cross-validation (precision, recall, and F1-score).

Results

Among the 169 eligible GP in-person consultations, 133 (79%) required a physical examination, while the other 33 visits were for psychological reasons. Out of these 133 consultations, a total of 283 physical examinations were observed, with 21 instances conducted behind a curtain. We identified 42 distinct types of physical examinations from these 283 instances, grouped into 10 physical examination categories based on body areas and physical artefacts. The most frequent category of physical examinations is Vital Signs 26.80% (76/283). Overall, blood pressure measurement (also belonging to the Vital Signs category) is the most frequent physical examination at 59.2% (45/76). The comparison between manual classification and the regular expression model demonstrates an average precision of 88.3%, recall of 78.9%, and an F1-score of 83.3% from 5-fold cross-validation, providing significant insights into the frequency and types of physical examinations conducted during in-person GP consultations.

Conclusion

By using regular expressions in consultation dialogues between GPs and patients, we can automatically identify physical examinations in GP consultations with a precision of 88.3%. Findings from this study, i.e. physical examinations during in-person GP consultations, provide insights into areas where GPs and patients may need support during teleconsultation.