Computer-aided detection of tuberculosis from chest radiographs in a tuberculosis prevalence survey in South Africa: external validation and modelled impacts of commercially available artificial intelligence software.

BACKGROUND: Computer-aided detection (CAD) can help identify people with active tuberculosis left undetected. However, few studies have compared the performance of commercially available CAD products for screening in high tuberculosis and high HIV settings, and there is poor understanding of threshold selection across products in different populations. We aimed to compare CAD products' performance, with further analyses on subgroup performance and threshold selection. METHODS: We evaluated 12 CAD products on a case-control sample of participants from a South African tuberculosis prevalence survey. Only those with microbiological test results were eligible. The primary outcome was comparing products' accuracy using the area under the receiver operating characteristic curve (AUC) against microbiological evidence. Threshold analyses were performed based on pre-defined criteria and across all thresholds. We conducted subgroup analyses including age, gender, HIV status, previous tuberculosis history, symptoms presence, and current smoking status. FINDINGS: Of the 774 people included, 516 were bacteriologically negative and 258 were bacteriologically positive. Diverse accuracy was noted: Lunit and Nexus had AUCs near 0·9, followed by qXR, JF CXR-2, InferRead, Xvision, and ChestEye (AUCs 0·8-0·9). XrayAME, RADIFY, and TiSepX-TB had AUC under 0·8. Thresholds varied notably across these products and different versions of the same products. Certain products (Lunit, Nexus, JF CXR-2, and qXR) maintained high sensitivity (>90%) across a wide threshold range while reducing the number of individuals requiring confirmatory diagnostic testing. All products generally performed worst in older individuals, people with previous tuberculosis, and people with HIV. Variations in thresholds, sensitivity, and specificity existed across groups and settings. INTERPRETATION: Several previously unevaluated products performed similarly to those evaluated by WHO. Thresholds differed across products and demographic subgroups. The rapid emergence of products and versions necessitates a global strategy to validate new versions and software to support CAD product and threshold selections. FUNDING: Government of Canada.

Training Health Care Practitioners to Include Family Caregivers With Web-Based Learning Modules.

Background Caregivers play a key role in supporting patient health; however, they have largely been excluded from participating in health care teams. This paper describes development and evaluation of web-based training for health care professionals about including family caregivers, implemented within the Department of Veterans Affairs Veterans Health Administration. Systematically training health care professionals constitutes a critical step toward shifting to a culture of purposefully and effectively utilizing and supporting family caregivers for better patient and health system outcomes. Methods Module development included Department of Veterans Affairs health care stakeholders and consisted of preliminary research and a design approach to set the framework, followed by iterative, collaborative team processes to write the content. Evaluation included pre- and postassessments of knowledge, attitudes, and beliefs. Results Overall, 154 health professionals completed pretest questions and 63 additionally completed the posttest. There was no observable change in knowledge. However, participants indicated a perceived desire and need for practicing inclusive care as well as an increase in self-efficacy (belief in their ability to accomplish a task successfully under certain conditions). Conclusion This project demonstrates the feasibility of developing web-based training to improve the beliefs and attitudes of health care professionals about inclusive care. Training constitutes one step toward shifting to a culture of inclusive care, and research should identify longer-term effects and other evidence-based interventions.

Early user experience and lessons learned using ultra-portable digital X-ray with computer-aided detection (DXR-CAD) products: A qualitative study from the perspective of healthcare providers.

BACKGROUND: Recent technological and radiological advances have renewed interest in using X-rays to screen and triage people with tuberculosis (TB). The miniaturization of digital X-ray (DXR), combined with automatic interpretation using computer-aided detection (CAD) software can extend the reach of DXR screening interventions for TB. This qualitative study assessed early implementers' experiences and lessons learned when using ultra-portable (UP) DXR systems integrated with CAD software to screen and triage TB. METHODS: Semi-structured interviews were conducted with project staff and healthcare workers at six pilot sites. Transcripts were coded and analyzed using a framework approach. The themes that emerged were subsequently organized and presented using the Consolidated Framework for Implementation Research (CFIR). RESULTS: There were 26 interviewees with varying roles: supervisory, clinicians, radiographers, and radiologists. Participants recognized the portability as the main advantage, but criticize that it involves several compromises on throughput, internet dependence, manoeuvrability, and stability, as well as suitability for patients with larger body sizes. Furthermore, compared to using hardware and software from the same supplier and without digital health information systems, complexity increases with interoperability between hardware and software, and between different electronic health information systems. Currently, there is a limited capacity to implement these technologies, especially due to the need for threshold selection, and lack of guidance on radiation protection suitable for UP DXR machines. Finally, the respondents stressed the importance of having protected means of sharing patient medical data, as well as comprehensive support and warranty plans. CONCLUSION: Study findings suggest that UP DXR with CAD was overall well received to decentralize radiological assessment for TB, however, the improved portability involved programmatic compromises. The main barriers to uptake included insufficient capacity and lack of guidance on radiation protection suitable for UP DXR.

Comparing different versions of computer-aided detection products when reading chest X-rays for tuberculosis.

Computer-aided detection (CAD) was recently recommended by the WHO for TB screening and triage based on several evaluations, but unlike traditional diagnostic tests, software versions are updated frequently and require constant evaluation. Since then, newer versions of two of the evaluated products have already been released. We used a case control sample of 12,890 chest X-rays to compare performance and model the programmatic effect of upgrading to newer versions of CAD4TB and qXR. We compared the area under the receiver operating characteristic curve (AUC), overall, and with data stratified by age, TB history, gender, and patient source. All versions were compared against radiologist readings and WHO's Target Product Profile (TPP) for a TB triage test. Both newer versions significantly outperformed their predecessors in terms of AUC: CAD4TB version 6 (0.823 [0.816-0.830]), version 7 (0.903 [0.897-0.908]) and qXR version 2 (0.872 [0.866-0.878]), version 3 (0.906 [0.901-0.911]). Newer versions met WHO TPP values, older versions did not. All products equalled or surpassed the human radiologist performance with improvements in triage ability in newer versions. Humans and CAD performed worse in older age groups and among those with TB history. New versions of CAD outperform their predecessors. Prior to implementation CAD should be evaluated using local data because underlying neural networks can differ significantly. An independent rapid evaluation centre is necessitated to provide implementers with performance data on new versions of CAD products as they are developed.

Tuberculosis detection from chest x-rays for triaging in a high tuberculosis-burden setting: an evaluation of five artificial intelligence algorithms.

BACKGROUND: Artificial intelligence (AI) algorithms can be trained to recognise tuberculosis-related abnormalities on chest radiographs. Various AI algorithms are available commercially, yet there is little impartial evidence on how their performance compares with each other and with radiologists. We aimed to evaluate five commercial AI algorithms for triaging tuberculosis using a large dataset that had not previously been used to train any AI algorithms. METHODS: Individuals aged 15 years or older presenting or referred to three tuberculosis screening centres in Dhaka, Bangladesh, between May 15, 2014, and Oct 4, 2016, were recruited consecutively. Every participant was verbally screened for symptoms and received a digital posterior-anterior chest x-ray and an Xpert MTB/RIF (Xpert) test. All chest x-rays were read independently by a group of three registered radiologists and five commercial AI algorithms: CAD4TB (version 7), InferRead DR (version 2), Lunit INSIGHT CXR (version 4.9.0), JF CXR-1 (version 2), and qXR (version 3). We compared the performance of the AI algorithms with each other, with the radiologists, and with the WHO's Target Product Profile (TPP) of triage tests (≥90% sensitivity and ≥70% specificity). We used a new evaluation framework that simultaneously evaluates sensitivity, proportion of Xpert tests avoided, and number needed to test to inform implementers' choice of software and selection of threshold abnormality scores. FINDINGS: Chest x-rays from 23 954 individuals were included in the analysis. All five AI algorithms significantly outperformed the radiologists. The areas under the receiver operating characteristic curve were 90·81% (95% CI 90·33-91·29) for qXR, 90·34% (89·81-90·87) for CAD4TB, 88·61% (88·03-89·20) for Lunit INSIGHT CXR, 84·90% (84·27-85·54) for InferRead DR, and 84·89% (84·26-85·53) for JF CXR-1. Only qXR (74·3% specificity [95% CI 73·3-74·9]) and CAD4TB (72·9% specificity [72·3-73·5]) met the TPP at 90% sensitivity. All five AI algorithms reduced the number of Xpert tests required by 50% while maintaining a sensitivity above 90%. All AI algorithms performed worse among older age groups (>60 years) and people with a history of tuberculosis. INTERPRETATION: AI algorithms can be highly accurate and useful triage tools for tuberculosis detection in high-burden regions, and outperform human readers. FUNDING: Government of Canada.

Including Family Caregivers In Seriously Ill Veterans' Care: A Mixed-Methods Study.

Family caregivers often serve as unpaid members of the home and community-based care workforce for people with serious illness; as key partners in the home-clinic continuum, they should be included in health care teams. The Campaign for Inclusive Care is an initiative within the Veterans Affairs health care system to improve provider practices for including caregivers of military members in treatment planning and decisions. We defined inclusive care using a literature review, provider interviews, and a caregiver survey. We found that inclusive care involves clear definition of the caregiver role, system policies for inclusion, assessment of caregivers' capacity, explicit involvement of caregivers, and mutuality in caregiver-provider communication. We recommend solutions based on this definition that can inform development of a national caregiver strategy, required of the Department of Health and Human Services by the Recognize, Assist, Include, Support, and Engage Family Caregivers Act of 2018.

"Chase CRP", "Review patient": Improving the Quality of Weekend Medical Handover at a London Teaching Hospital.

Clinical handover has been identified as a "major preventable cause of harm" by the Royal College of Physicians (RCP). Whilst working at a London teaching hospital from August 2013, we noted substandard weekend handover of medical patients. The existing pro forma was filled incompletely by day doctors so it was difficult for weekend colleagues to identify unwell patients, with inherent safety implications. Furthermore, on-call medical staff noted that poor accessibility of vital information in patients' files was affecting acute clinical management. We audited the pro formas over a six week period (n=83) and the Friday ward round (WR) entries for medical inpatients over two weekends (n=84) against the RCP's handover guidance. The results showed poor documentation of several important details on the pro formas, for example, ceiling of care (4%) and past medical history (PMH) (23%). Problem lists were specified on 62% of the WR entries. We designed new handover pro formas and 'Friday WR sheets' to provide prompts for this information and used Medical Meetings and emails to explain the project's aims. Re-audit demonstrated significant improvement in all parameters; for instance, PMH increased to 52% on the pro formas. Only 10% of Friday WR entries used our sheet. However, when used, outcomes were much better, for example, problem list documentation increased to 100%. In conclusion, our interventions improved the provision of crucial information needed to prioritise and manage patients over the weekend. Future work should further highlight the importance of safe handover to all doctors to induce a shift in culture and optimise patient care.

Hand hygiene practices: nursing students' perceptions.

AIMS AND OBJECTIVES: The present study examines nursing students' perceptions of hand hygiene practices in clinical settings. The objectives were to investigate any factors that affect students' perceptions of their own and healthcare workers' (HCWs) hand hygiene compliance, and to make recommendations for future practice and hand hygiene training in preregistration nursing courses. BACKGROUND: Effective hand hygiene decontamination can lower the prevalence of healthcare-associated infections (HCAIs); unfortunately, the prevalence of HCAIs continues to rise and so poses challenges to healthcare providers to reduce such infections. Previous studies have shown that hand hygiene compliance in HCWs is generally low and that any increase in compliance is difficult to sustain. Several barriers to hand hygiene compliance have been identified in the literature. DESIGN: A qualitative interpretive design was used to examine nursing students' perceptions of hand hygiene practices. METHODS: Ten preregistration students participated in semi-structured qualitative interviews, which were analysed thematically. RESULTS: Hand hygiene compliance was perceived to be effected by specific barriers which included: time and busyness; clinical procedure; skin condition; lack of knowledge and glove use. Importantly, students perceived other HCWs as being the influencing factor for hand hygiene compliance resulting from the perception that they should 'fit in' with those working in the clinical area. CONCLUSIONS: The findings support previous literature and found that respondents emphasised the importance of fitting into the clinical area and role models in shaping hand hygiene compliance. RELEVANCE TO CLINICAL PRACTICE: For nursing students, the influence of other HCWs as role models should not be underestimated.