BMJ Health & Care Informatics最新文献

Introduction In January, the National Institutes of Health (NIH) implemented a Data Management and Sharing Policy aiming to leverage data collected during NIH-funded research. The COVID-19 pandemic illustrated that this practice is equally vital for augmenting patient research. In addition, data sharing acts as a necessary safeguard against the introduction of analytical biases. While the pandemic provided an opportunity to curtail critical research issues such as reproducibility and validity through data sharing, this did not materialise in practice and became an example of 'Open Data in Appearance Only' (ODIAO). Here, we define ODIAO as the intent of data sharing without the occurrence of actual data sharing (eg, material or digital data transfers).Objective Propose a framework that states the main risks associated with data sharing, systematically present risk mitigation strategies and provide examples through a healthcare lens.Methods This framework was informed by critical aspects of both the Open Data Institute and the NIH's 2023 Data Management and Sharing Policy plan guidelines.Results Through our examination of legal, technical, reputational and commercial categories, we find barriers to data sharing ranging from misinterpretation of General Data Privacy Rule to lack of technical personnel able to execute large data transfers. From this, we deduce that at numerous touchpoints, data sharing is presently too disincentivised to become the norm.Conclusion In order to move towards Open Data, we propose the creation of mechanisms for incentivisation, beginning with recentring data sharing on patient benefits, additional clauses in grant requirements and committees to encourage adherence to data reporting practices.

Sepsis is a worldwide public health problem. Rapid identification is associated with improved patient outcomes-if followed by timely appropriate treatment.

Objectives: Describe digital sepsis alerts (DSAs) in use in English National Health Service (NHS) acute hospitals.

Methods: A Freedom of Information request surveyed acute NHS Trusts on their adoption of electronic patient records (EPRs) and DSAs.

Results: Of the 99 Trusts that responded, 84 had an EPR. Over 20 different EPR system providers were identified as operational in England. The most common providers were Cerner (21%). System C, Dedalus and Allscripts Sunrise were also relatively common (13%, 10% and 7%, respectively). 70% of NHS Trusts with an EPR responded that they had a DSA; most of these use the National Early Warning Score (NEWS2). There was evidence that the EPR provider was related to the DSA algorithm. We found no evidence that Trusts were using EPRs to introduce data driven algorithms or DSAs able to include, for example, pre-existing conditions that may be known to increase risk.Not all Trusts were willing or able to provide details of their EPR or the underlying algorithm.

Discussion: The majority of NHS Trusts use an EPR of some kind; many use a NEWS2-based DSA in keeping with national guidelines.

Conclusion: Many English NHS Trusts use DSAs; even those using similar triggers vary and many recreate paper systems. Despite the proliferation of machine learning algorithms being developed to support early detection of sepsis, there is little evidence that these are being used to improve personalised sepsis detection.

Background: Although mHealth applications are becoming more widely available and used, there is no evidence about why people are willing to use them. Therefore, this study aimed to assess the willingness of patients with diabetes to use mHealth applications and associated factors for self-care management in Ethiopia.

Methods: An institutional cross-sectional study was conducted among 422 patients with diabetes. Data were collected using pretested interviewer-administered questionnaire. Epi Data V.4.6 for entering the data and STATA V.14 for analysing the data were used. A multivariable logistic regression analysis was carried out to identify factors associated with patient's willingness to use mobile health applications.

Results: A total of 398 study participants were included in the study. About 284 (71.4%) 95% CI (66.8% to 75.9%)). Of participants were willing to use mobile health applications. Patients below 30 years of age (adjusted OR, AOR 2.21; 95% CI (1.22 to 4.10)), urban residents (AOR 2.12; 95% CI (1.12 to 3.98)), internet access (AOR 3.91; 95% CI (1.31 to 11.5)), favourable attitude (AOR 5.20; 95% CI (2.60 to 10.40)), perceived ease of use (AOR 2.57; 95% CI (1.34 to 4.85)) and perceived usefulness (AOR 4.67; 95% CI (1.95 to 5.77)) were significantly associated with patients' willingness to use mobile health applications.

Conclusions: Overall, diabetes patients' willingness to use mobile health applications was high. Patients' age, place of residence, internet access, attitude, perceived ease of use and perceived usefulness were significant factors concerning their willingness to use mobile health applications. Considering these factors could provide insight for developing and adopting diabetes management applications on mobile devices in Ethiopia.

Objectives: The objective of this study was to explore the use of natural language processing (NLP) algorithm to categorise contributing factors from patient safety event (PSE). Contributing factors are elements in the healthcare process (eg, communication failures) that instigate an event or allow an event to occur. Contributing factors can be used to further investigate why safety events occurred.

Methods: We used 10 years of self-reported PSE reports from a multihospital healthcare system in the USA. Reports were first selected by event date. We calculated χ² values for each ngram in the bag-of-words then selected N ngrams with the highest χ² values. Then, PSE reports were filtered to only include the sentences containing the selected ngrams. Such sentences were called information-rich sentences. We compared two feature extraction techniques from free-text data: (1) baseline bag-of-words features and (2) features from information-rich sentences. Three machine learning algorithms were used to categorise five contributing factors representing sociotechnical errors: communication/hand-off failure, technology issue, policy/procedure issue, distractions/interruptions and lapse/slip. We trained 15 binary classifiers (five contributing factors * three machine learning models). The models' performances were evaluated according to the area under the precision-recall curve (AUPRC), precision, recall, and F1-score.

Results: Applying the information-rich sentence selection algorithm boosted the contributing factor categorisation performance. Comparing the AUPRCs, the proposed NLP approach improved the categorisation performance of two and achieved comparable results with baseline in categorising three contributing factors.

Conclusions: Information-rich sentence selection can be incorporated to extract the sentences in free-text event narratives in which the contributing factor information is embedded.

Objectives: Artificial intelligence (AI) is increasingly tested and integrated into breast cancer screening. Still, there are unresolved issues regarding its possible ethical, social and legal impacts. Furthermore, the perspectives of different actors are lacking. This study investigates the views of breast radiologists on AI-supported mammography screening, with a focus on attitudes, perceived benefits and risks, accountability of AI use, and potential impact on the profession.

Methods: We conducted an online survey of Swedish breast radiologists. As early adopter of breast cancer screening, and digital technologies, Sweden is a particularly interesting case to study. The survey had different themes, including: attitudes and responsibilities pertaining to AI, and AI's impact on the profession. Responses were analysed using descriptive statistics and correlation analyses. Free texts and comments were analysed using an inductive approach.

Results: Overall, respondents (47/105, response rate 44.8%) were highly experienced in breast imaging and had a mixed knowledge of AI. A majority (n=38, 80.8%) were positive/somewhat positive towards integrating AI in mammography screening. Still, many considered there to be potential risks to a high/somewhat high degree (n=16, 34.1%) or were uncertain (n=16, 34.0%). Several important uncertainties were identified, such as defining liable actor(s) when AI is integrated into medical decision-making.

Conclusions: Swedish breast radiologists are largely positive towards integrating AI in mammography screening, but there are significant uncertainties that need to be addressed, especially regarding risks and responsibilities. The results stress the importance of understanding actor-specific and context-specific challenges to responsible implementation of AI in healthcare.

Objective: Clinical decision support systems (CDSSs) can reduce medical errors increasing drug prescription appropriateness. Deepening knowledge of existing CDSSs could increase their use by healthcare professionals in different settings (ie, hospitals, pharmacies, health research centres) of clinical practice. This review aims to identify the characteristics common to effective studies conducted with CDSSs.

Materials and methods: The article sources were Scopus, PubMed, Ovid MEDLINE and Web of Science, queried between January 2017 and January 2022. Inclusion criteria were prospective and retrospective studies that reported original research on CDSSs for clinical practice support; studies should describe a measurable comparison of the intervention or observation conducted with and without the CDSS; article language Italian or English. Reviews and studies with CDSSs used exclusively by patients were excluded. A Microsoft Excel spreadsheet was prepared to extract and summarise data from the included articles.

Results: The search resulted in the identification of 2424 articles. After title and abstract screening, 136 studies remained, 42 of which were included for final evaluation. Most of the studies included rule-based CDSSs that are integrated into existing databases with the main purpose of managing disease-related problems. The majority of the selected studies (25 studies; 59.5%) were successful in supporting clinical practice, with most being pre-post intervention studies and involving the presence of a pharmacist.

Discussion and conclusion: A number of characteristics have been identified that may help the design of studies feasible to demonstrate the effectiveness of CDSSs. Further studies are needed to encourage CDSS use.

Objectives: Applications of artificial intelligence (AI) have the potential to improve aspects of healthcare. However, studies have shown that healthcare AI algorithms also have the potential to perpetuate existing inequities in healthcare, performing less effectively for marginalised populations. Studies on public attitudes towards AI outside of the healthcare field have tended to show higher levels of support for AI among socioeconomically advantaged groups that are less likely to be sufferers of algorithmic harms. We aimed to examine the sociodemographic predictors of support for scenarios related to healthcare AI.Methods: The Australian Values and Attitudes toward AI survey was conducted in March 2020 to assess Australians' attitudes towards AI in healthcare. An innovative weighting methodology involved weighting a non-probability web-based panel against results from a shorter omnibus survey distributed to a representative sample of Australians. We used multinomial logistic regression to examine the relationship between support for AI and a suite of sociodemographic variables in various healthcare scenarios.Results: Where support for AI was predicted by measures of socioeconomic advantage such as education, household income and Socio-Economic Indexes for Areas index, the same variables were not predictors of support for the healthcare AI scenarios presented. Variables associated with support for healthcare AI included being male, having computer science or programming experience and being aged between 18 and 34 years. Other Australian studies suggest that these groups may have a higher level of perceived familiarity with AI.Conclusion: Our findings suggest that while support for AI in general is predicted by indicators of social advantage, these same indicators do not predict support for healthcare AI.

Background: Modern patient electronic health records form a core part of primary care; they contain both clinical codes and free text entered by the clinician. Natural language processing (NLP) could be employed to generate these records through 'listening' to a consultation conversation.

Objectives: This study develops and assesses several text classifiers for identifying clinical codes for primary care consultations based on the doctor-patient conversation. We evaluate the possibility of training classifiers using medical code descriptions, and the benefits of processing transcribed speech from patients as well as doctors. The study also highlights steps for improving future classifiers.

Methods: Using verbatim transcripts of 239 primary care consultation conversations (the 'One in a Million' dataset) and novel additional datasets for distant supervision, we trained NLP classifiers (naïve Bayes, support vector machine, nearest centroid, a conventional BERT classifier and few-shot BERT approaches) to identify the International Classification of Primary Care-2 clinical codes associated with each consultation.

Results: Of all models tested, a fine-tuned BERT classifier was the best performer. Distant supervision improved the model's performance (F1 score over 16 classes) from 0.45 with conventional supervision with 191 labelled transcripts to 0.51. Incorporating patients' speech in addition to clinician's speech increased the BERT classifier's performance from 0.45 to 0.55 F1 (p=0.01, paired bootstrap test).

Conclusions: Our findings demonstrate that NLP classifiers can be trained to identify clinical area(s) being discussed in a primary care consultation from audio transcriptions; this could represent an important step towards a smart digital assistant in the consultation room.