Effects of a comprehensive brain computed tomography deep learning model on radiologist detection accuracy.

OBJECTIVES: Non-contrast computed tomography of the brain (NCCTB) is commonly used to detect intracranial pathology but is subject to interpretation errors. Machine learning can augment clinical decision-making and improve NCCTB scan interpretation. This retrospective detection accuracy study assessed the performance of radiologists assisted by a deep learning model and compared the standalone performance of the model with that of unassisted radiologists. METHODS: A deep learning model was trained on 212,484 NCCTB scans drawn from a private radiology group in Australia. Scans from inpatient, outpatient, and emergency settings were included. Scan inclusion criteria were age ≥ 18 years and series slice thickness ≤ 1.5 mm. Thirty-two radiologists reviewed 2848 scans with and without the assistance of the deep learning system and rated their confidence in the presence of each finding using a 7-point scale. Differences in AUC and Matthews correlation coefficient (MCC) were calculated using a ground-truth gold standard. RESULTS: The model demonstrated an average area under the receiver operating characteristic curve (AUC) of 0.93 across 144 NCCTB findings and significantly improved radiologist interpretation performance. Assisted and unassisted radiologists demonstrated an average AUC of 0.79 and 0.73 across 22 grouped parent findings and 0.72 and 0.68 across 189 child findings, respectively. When assisted by the model, radiologist AUC was significantly improved for 91 findings (158 findings were non-inferior), and reading time was significantly reduced. CONCLUSIONS: The assistance of a comprehensive deep learning model significantly improved radiologist detection accuracy across a wide range of clinical findings and demonstrated the potential to improve NCCTB interpretation. CLINICAL RELEVANCE STATEMENT: This study evaluated a comprehensive CT brain deep learning model, which performed strongly, improved the performance of radiologists, and reduced interpretation time. The model may reduce errors, improve efficiency, facilitate triage, and better enable the delivery of timely patient care. KEY POINTS: • This study demonstrated that the use of a comprehensive deep learning system assisted radiologists in the detection of a wide range of abnormalities on non-contrast brain computed tomography scans. • The deep learning model demonstrated an average area under the receiver operating characteristic curve of 0.93 across 144 findings and significantly improved radiologist interpretation performance. • The assistance of the comprehensive deep learning model significantly reduced the time required for radiologists to interpret computed tomography scans of the brain.

Developing, Purchasing, Implementing and Monitoring AI Tools in Radiology: Practical Considerations. A Multi-Society Statement From the ACR, CAR, ESR, RANZCR & RSNA.

Artificial Intelligence (AI) carries the potential for unprecedented disruption in radiology, with possible positive and negative consequences. The integration of AI in radiology holds the potential to revolutionize healthcare practices by advancing diagnosis, quantification, and management of multiple medical conditions. Nevertheless, the ever­growing availability of AI tools in radiology highlights an increasing need to critically evaluate claims for its utility and to differentiate safe product offerings from potentially harmful, or fundamentally unhelpful ones. This multi­society paper, presenting the views of Radiology Societies in the USA, Canada, Europe, Australia, and New Zealand, defines the potential practical problems and ethical issues surrounding the incorporation of AI into radiological practice. In addition to delineating the main points of concern that developers, regulators, and purchasers of AI tools should consider prior to their introduction into clinical practice, this statement also suggests methods to monitor their stability and safety in clinical use, and their suitability for possible autonomous function. This statement is intended to serve as a useful summary of the practical issues which should be considered by all parties involved in the development of radiology AI resources, and their implementation as clinical tools.

A qualitative exploration of the psychosocial needs of people living with long-term conditions and their perspectives on online peer support.

INTRODUCTION: Approximately 20% of people with a long-term condition (LTC) experience depressive symptoms (subthreshold depression [SUBD]). People with SUBD experience depressive symptoms that do not meet the diagnostic criteria for major depressive disorder. However, there is currently no targeted psychological support for people with LTCs also experiencing SUBD. Online peer support is accessible, inexpensive and scalable, and might offer a way of bridging the gap in psychosocial care for LTC patients. This article explores the psychosocial needs of people living with LTCs and investigates their perspectives on online peer support interventions to inform their future design. METHODS: Through a co-produced participatory approach, online focus groups were completed with people with lived experience of LTCs. Focus groups were audio recorded and transcribed verbatim. Reflexive thematic analysis (TA) was conducted adopting a critical-realist approach and an inductive analysis methodology that sought to follow participants' priorities and concerns. RESULTS: Ten people with a range of LTCs participated across three online focus groups, lasting an average of 95 (±10.1) min. The mean age was 57 (±11.4) years and 60% of participants identified as female. The three key emerging themes were: (1) relationship between self and outside world; (2) past experiences of peer support; and (3) philosophy and vision of peer support. Adults living with LTCs shared their past experiences of peer support and explored their perspectives on how future online peer support platforms may support their psychosocial needs. CONCLUSION: Despite the negative impact(s) of having a long-term physical health condition on mental health, physical and mental healthcare are often treated as separate entities. The need for an integrated approach for people with LTCs was clear. Implementation of online peer support to bridge this gap was supported, but there was a clear consensus that these interventions need to be co-produced and carefully designed to ensure they feel safe and not commercialised or prescriptive. Shared explorations of the potential benefits and concerns of these online spaces can shape the philosophy and vision of future platforms. PATIENT OR PUBLIC CONTRIBUTION: This work is set within a wider project which is developing an online peer support platform for those living with LTCs. A participatory, co-produced approach is integral to this work. The initial vision was steered by the experiences of our Patient and Public Involvement (PPI) groups, who emphasised the therapeutic value of peer-to-peer interaction. The focus groups confirmed the importance and potential benefit of this project. This paper represents the perspectives of PPI members who collaborate on research and public engagement at the mental-physical interface. A separate, independent Research Advisory Group (RAG), formed of members also living with LTCs, co-produced study documents, topic guides, and informed key decision-making processes. Finally, our co-investigator with lived experience (E. A.F.) undertook the analysis and write-up alongside colleagues, further strengthening the interpretation and resonance of our work. She shares first joint authorship, and as a core member of the research team, ensures that the conduct of the study is firmly grounded in the experience of people living with LTCs.

Professionalism and clinical short answer question marking with machine learning.

Machine learning may assist in medical student evaluation. This study involved scoring short answer questions administered at three centres. Bidirectional encoder representations from transformers were particularly effective for professionalism question scoring (accuracy ranging from 41.6% to 92.5%). In the scoring of 3-mark professionalism questions, as compared with clinical questions, machine learning had a lower classification accuracy (P < 0.05). The role of machine learning in medical professionalism evaluation warrants further investigation.

Common mental disorders within chronic inflammatory disorders: a primary care database prospective investigation.

OBJECTIVE: There is inconsistent evidence about the association between inflammatory disorders and depression and anxiety onset in a primary care context. The study aimed to evaluate the risk of depression and anxiety within multisystem and organ-specific inflammatory disorders. METHODS: This is a prospective cohort study with primary care patients from the UK Clinical Practice Research Datalink diagnosed with an inflammatory disorder between 1 January 2001 and 31 December 2016. These patients were matched on age, gender, practice and index date with patients without an inflammatory disorder. The study exposures were seven chronic inflammatory disorders. Clinical diagnosis of depression and anxiety represented the outcome measures of interest. RESULTS: Among 538 707 participants, the incidence of depression ranged from 14 per 1000 person-years (severe psoriasis) to 9 per 1000 person-years (systemic vasculitis), substantively higher compared with their comparison group (5-7 per 1000 person-years). HRs of multiple depression and anxiety events were 16% higher within inflammatory disorders (HR, 1.16, 95% CI 1.12 to 1.21, p<0.001) compared with the matched comparison group. The incidence of depression and anxiety was strongly associated with the age at inflammatory disorder onset. The overall HR estimate for depression was 1.90 (95% CI 1.66 to 2.17, p<0.001) within early-onset disorder (<40 years of age) and 0.93 (95% CI 0.90 to 1.09, p=0.80) within late-onset disorder (≥60 years of age). CONCLUSIONS: Primary care patients with inflammatory disorders have elevated rates of depression and anxiety incidence, particularly those patients with early-onset inflammatory disorders. This finding may reflect the impact of the underlying disease on patients' quality of life, although the precise mechanisms require further investigation.

I've had a good life, what's left is a bonus: factor analysis of the Mental Adjustment to Cancer Scale in a palliative care population.

BACKGROUND: The Mental Adjustment to Cancer Scale is an assessment tool commonly used to measure coping in cancer patients, which characterises adaptive coping under the label of 'fighting spirit'. AIM: This study explores adaptation in patients with advanced cancer, by examining the factor structure of the Mental Adjustment to Cancer Scale. Further aims were to examine associations between types of coping and psychological outcomes measured at the same time (time 1) and 4 weeks after referral to palliative care services (time 2). DESIGN: A cross-sectional study with a follow-up assessment 4 weeks later. Factor analysis examined the structure of the Mental Adjustment to Cancer Scale at time 1. SETTING/PARTICIPANTS: A total of 275 patients with advanced cancer receiving palliative care, of whom 193 took part at follow-up. RESULTS: This study provided evidence for the internal consistency and validity of a new scale of 'acceptance and positivity' for use in advanced cancer patients. Patients with a desire for hastened death had lower acceptance and positivity, and patients with higher global quality of life reported a higher level. Social support was positively associated with acceptance and positivity. Higher scores on the acceptance and positivity scale were associated with reduced odds of a desire for hastened death at time 2. CONCLUSION: Adaptation to advanced cancer differs from adaptation to early stage cancer, comprising a general acceptance of the illness and trying to make the most of the time that is left. Individuals with low social support were less likely to evidence appropriate adaptation to their illness.

Severity of acute phase reaction in children receiving the first dose of zoledronic acid and the impact of the underlying condition: a cross-sectional study.

INTRODUCTION: Zoledronic acid (ZA), used for treatment of children with osteoporosis, can cause acute phase reaction (APR) following the first infusion. Many institutions have a policy to admit and monitor all children for their first ZA infusion. OBJECTIVE: To determine if the APR with the first ZA dose warrants hospital-level care and evaluate if its severity correlates with the underlying condition. DESIGN: Retrospective cross-sectional analysis. SETTINGS: Two tertiary centres across the UK that run paediatric metabolic bone disease services. PATIENTS: Children who received first ZA infusion as inpatients at these centres. INTERVENTIONS: Nil. MAIN OUTCOME MEASURES: The Paediatric Early Warning Score (PEWS) and length of hospital stay to assess the severity of APR. RESULTS: 107 patients were included. Peak PEWS≤3 was found in 85% of children. 83% required admission for <24 hours. The various patient populations (osteogenesis imperfecta (OI), immobility-induced osteoporosis, idiopathic juvenile osteoporosis, systemic inflammatory disorders and steroid-induced osteoporosis, Duchenne muscular dystrophy (DMD)) did not differ significantly in the mean peak PEWS and the length of hospital stay. However, when compared directly, the group with DMD and that with systemic inflammatory disorders and steroid-induced osteoporosis differed significantly in the mean peak PEWS (p=0.011) and the length of hospital stay (p=0.048), respectively, as compared with the OI group. CONCLUSION: Most patients had a mild APR not requiring overnight hospital admission, after their first ZA dose. However, certain groups seem to suffer more severe APR and may warrant consideration of inpatient monitoring with the first infusion.

Prognostic modeling in early rheumatoid arthritis: reconsidering the predictive role of disease activity scores.

OBJECTIVE: In this prospective cohort study, we provide several prognostic models to predict functional status as measured by the modified Health Assessment Questionnaire (mHAQ). The early adoption of the treat-to-target strategy in this cohort offered a unique opportunity to identify predictive factors using longitudinal data across 20 years. METHODS: A cohort of 397 patients with early RA was used to develop statistical models to predict mHAQ score measured at baseline, 12 months, and 18 months post diagnosis, as well as serially measured mHAQ. Demographic data, clinical measures, autoantibodies, medication use, comorbid conditions, and baseline mHAQ were considered as predictors. RESULTS: The discriminative performance of models was comparable to previous work, with an area under the receiver operator curve ranging from 0.64 to 0.88. The most consistent predictive variable was baseline mHAQ. Patient-reported outcomes including early morning stiffness, tender joint count (TJC), fatigue, pain, and patient global assessment were positively predictive of a higher mHAQ at baseline and longitudinally, as was the physician global assessment and C-reactive protein. When considering future function, a higher TJC predicted persistent disability while a higher swollen joint count predicted functional improvements with treatment. CONCLUSION: In our study of mHAQ prediction in RA patients receiving treat-to-target therapy, patient-reported outcomes were most consistently predictive of function. Patients with high disease activity due predominantly to tenderness scores rather than swelling may benefit from less aggressive treatment escalation and an emphasis on non-pharmacological therapies, allowing for a more personalized approach to treatment. Key Points • Long-term use of the treat-to-target strategy in this patient cohort offers a unique opportunity to develop prognostic models for functional outcomes using extensive longitudinal data. • Patient reported outcomes were more consistent predictors of function than traditional prognostic markers. • Tender joint count and swollen joint count had discordant relationships with future function, adding weight to the possibility that disease activity may better guide treatment when the components are considered separately.

Impact of Transfer Learning Using Local Data on Performance of a Deep Learning Model for Screening Mammography.

Purpose To investigate the issues of generalizability and replication of deep learning models by assessing performance of a screening mammography deep learning system developed at New York University (NYU) on a local Australian dataset. Materials and Methods In this retrospective study, all individuals with biopsy or surgical pathology-proven lesions and age-matched controls were identified from a South Australian public mammography screening program (January 2010 to December 2016). The primary outcome was deep learning system performance-measured with area under the receiver operating characteristic curve (AUC)-in classifying invasive breast cancer or ductal carcinoma in situ (n = 425) versus no malignancy (n = 490) or benign lesions (n = 44). The NYU system, including models without (NYU1) and with (NYU2) heatmaps, was tested in its original form, after training from scratch (without transfer learning), and after retraining with transfer learning. Results The local test set comprised 959 individuals (mean age, 62.5 years ± 8.5 [SD]; all female). The original AUCs for the NYU1 and NYU2 models were 0.83 (95% CI: 0.82, 0.84) and 0.89 (95% CI: 0.88, 0.89), respectively. When NYU1 and NYU2 were applied in their original form to the local test set, the AUCs were 0.76 (95% CI: 0.73, 0.79) and 0.84 (95% CI: 0.82, 0.87), respectively. After local training without transfer learning, the AUCs were 0.66 (95% CI: 0.62, 0.69) and 0.86 (95% CI: 0.84, 0.88). After retraining with transfer learning, the AUCs were 0.82 (95% CI: 0.80, 0.85) and 0.86 (95% CI: 0.84, 0.88). Conclusion A deep learning system developed using a U.S. dataset showed reduced performance when applied "out of the box" to an Australian dataset. Local retraining with transfer learning using available model weights improved model performance. Keywords: Screening Mammography, Convolutional Neural Network (CNN), Deep Learning Algorithms, Breast Cancer Supplemental material is available for this article. © RSNA, 2024 See also commentary by Cadrin-Chênevert in this issue.

Developing, purchasing, implementing and monitoring AI tools in radiology: practical considerations. A multi-society statement from the ACR, CAR, ESR, RANZCR & RSNA.

Artificial Intelligence (AI) carries the potential for unprecedented disruption in radiology, with possible positive and negative consequences. The integration of AI in radiology holds the potential to revolutionize healthcare practices by advancing diagnosis, quantification, and management of multiple medical conditions. Nevertheless, the ever-growing availability of AI tools in radiology highlights an increasing need to critically evaluate claims for its utility and to differentiate safe product offerings from potentially harmful, or fundamentally unhelpful ones.This multi-society paper, presenting the views of Radiology Societies in the USA, Canada, Europe, Australia, and New Zealand, defines the potential practical problems and ethical issues surrounding the incorporation of AI into radiological practice. In addition to delineating the main points of concern that developers, regulators, and purchasers of AI tools should consider prior to their introduction into clinical practice, this statement also suggests methods to monitor their stability and safety in clinical use, and their suitability for possible autonomous function. This statement is intended to serve as a useful summary of the practical issues which should be considered by all parties involved in the development of radiology AI resources, and their implementation as clinical tools.Key points • The incorporation of artificial intelligence (AI) in radiological practice demands increased monitoring of its utility and safety.• Cooperation between developers, clinicians, and regulators will allow all involved to address ethical issues and monitor AI performance.• AI can fulfil its promise to advance patient well-being if all steps from development to integration in healthcare are rigorously evaluated.

Developing, Purchasing, Implementing and Monitoring AI Tools in Radiology: Practical Considerations. A Multi-Society Statement From the ACR, CAR, ESR, RANZCR & RSNA.

Artificial intelligence (AI) carries the potential for unprecedented disruption in radiology, with possible positive and negative consequences. The integration of AI in radiology holds the potential to revolutionize healthcare practices by advancing diagnosis, quantification, and management of multiple medical conditions. Nevertheless, the ever-growing availability of AI tools in radiology highlights an increasing need to critically evaluate claims for its utility and to differentiate safe product offerings from potentially harmful, or fundamentally unhelpful ones. This multi-society paper, presenting the views of Radiology Societies in the USA, Canada, Europe, Australia, and New Zealand, defines the potential practical problems and ethical issues surrounding the incorporation of AI into radiological practice. In addition to delineating the main points of concern that developers, regulators, and purchasers of AI tools should consider prior to their introduction into clinical practice, this statement also suggests methods to monitor their stability and safety in clinical use, and their suitability for possible autonomous function. This statement is intended to serve as a useful summary of the practical issues which should be considered by all parties involved in the development of radiology AI resources, and their implementation as clinical tools. KEY POINTS.

Developing, purchasing, implementing and monitoring AI tools in radiology: Practical considerations. A multi-society statement from the ACR, CAR, ESR, RANZCR & RSNA.

Artificial Intelligence (AI) carries the potential for unprecedented disruption in radiology, with possible positive and negative consequences. The integration of AI in radiology holds the potential to revolutionize healthcare practices by advancing diagnosis, quantification, and management of multiple medical conditions. Nevertheless, the ever-growing availability of AI tools in radiology highlights an increasing need to critically evaluate claims for its utility and to differentiate safe product offerings from potentially harmful, or fundamentally unhelpful ones. This multi-society paper, presenting the views of Radiology Societies in the USA, Canada, Europe, Australia, and New Zealand, defines the potential practical problems and ethical issues surrounding the incorporation of AI into radiological practice. In addition to delineating the main points of concern that developers, regulators, and purchasers of AI tools should consider prior to their introduction into clinical practice, this statement also suggests methods to monitor their stability and safety in clinical use, and their suitability for possible autonomous function. This statement is intended to serve as a useful summary of the practical issues which should be considered by all parties involved in the development of radiology AI resources, and their implementation as clinical tools.

Developing, Purchasing, Implementing and Monitoring AI Tools in Radiology: Practical Considerations. A Multi-Society Statement from the ACR, CAR, ESR, RANZCR and RSNA.

Artificial Intelligence (AI) carries the potential for unprecedented disruption in radiology, with possible positive and negative consequences. The integration of AI in radiology holds the potential to revolutionize healthcare practices by advancing diagnosis, quantification, and management of multiple medical conditions. Nevertheless, the ever-growing availability of AI tools in radiology highlights an increasing need to critically evaluate claims for its utility and to differentiate safe product offerings from potentially harmful, or fundamentally unhelpful ones. This multi-society paper, presenting the views of Radiology Societies in the USA, Canada, Europe, Australia, and New Zealand, defines the potential practical problems and ethical issues surrounding the incorporation of AI into radiological practice. In addition to delineating the main points of concern that developers, regulators, and purchasers of AI tools should consider prior to their introduction into clinical practice, this statement also suggests methods to monitor their stability and safety in clinical use, and their suitability for possible autonomous function. This statement is intended to serve as a useful summary of the practical issues which should be considered by all parties involved in the development of radiology AI resources, and their implementation as clinical tools. This article is simultaneously published in Insights into Imaging (DOI 10.1186/s13244-023-01541-3), Journal of Medical Imaging and Radiation Oncology (DOI 10.1111/1754-9485.13612), Canadian Association of Radiologists Journal (DOI 10.1177/08465371231222229), Journal of the American College of Radiology (DOI 10.1016/j.jacr.2023.12.005), and Radiology: Artificial Intelligence (DOI 10.1148/ryai.230513). Keywords: Artificial Intelligence, Radiology, Automation, Machine Learning Published under a CC BY 4.0 license. ©The Author(s) 2024. Editor's Note: The RSNA Board of Directors has endorsed this article. It has not undergone review or editing by this journal.

Concordance of randomised controlled trials for artificial intelligence interventions with the CONSORT-AI reporting guidelines.

The Consolidated Standards of Reporting Trials extension for Artificial Intelligence interventions (CONSORT-AI) was published in September 2020. Since its publication, several randomised controlled trials (RCTs) of AI interventions have been published but their completeness and transparency of reporting is unknown. This systematic review assesses the completeness of reporting of AI RCTs following publication of CONSORT-AI and provides a comprehensive summary of RCTs published in recent years. 65 RCTs were identified, mostly conducted in China (37%) and USA (18%). Median concordance with CONSORT-AI reporting was 90% (IQR 77-94%), although only 10 RCTs explicitly reported its use. Several items were consistently under-reported, including algorithm version, accessibility of the AI intervention or code, and references to a study protocol. Only 3 of 52 included journals explicitly endorsed or mandated CONSORT-AI. Despite a generally high concordance amongst recent AI RCTs, some AI-specific considerations remain systematically poorly reported. Further encouragement of CONSORT-AI adoption by journals and funders may enable more complete adoption of the full CONSORT-AI guidelines.

The prevalence of depression in rheumatoid arthritis: a systematic review and meta-analysis.

OBJECTIVE: There is substantial uncertainty regarding the prevalence of depression in RA. We conducted a systematic review aiming to describe the prevalence of depression in RA. METHODS: Web of Science, PsycINFO, CINAHL, Embase, Medline and PubMed were searched for cross-sectional studies reporting a prevalence estimate for depression in adult RA patients. Studies were reviewed in accordance with the Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA) guidelines and a meta-analysis was performed. RESULTS: A total of 72 studies, including 13,189 patients, were eligible for inclusion in the review. Forty-three methods of defining depression were reported. Meta-analyses revealed the prevalence of major depressive disorder to be 16.8% (95% CI 10%, 24%). According to the PHQ-9, the prevalence of depression was 38.8% (95% CI 34%, 43%), and prevalence levels according to the HADS with thresholds of 8 and 11 were 34.2% (95% CI 25%, 44%) and 14.8% (95% CI 12%, 18%), respectively. The main influence on depression prevalence was the mean age of the sample. CONCLUSION: Depression is highly prevalent in RA and associated with poorer RA outcomes. This suggests that optimal care of RA patients may include the detection and management of depression.

Fostering an inclusive workplace for LGBTQIA+ people in radiology and radiation oncology.

The inclusion and celebration of LGBTQIA+ staff in radiology and radiation oncology departments is crucial in developing a diverse and thriving workplace. Despite the substantial social change in Australia, LGBTQIA+ people still experience harassment and exclusion, negatively impacting their well-being and workplace productivity. We need to be proactive in creating policies that are properly implemented and translate to a safe and inclusive space for marginalised groups. In this work, we outline the role we all can play in creating inclusive environments, for both individuals and leaders working in radiology and radiation oncology. We can learn how to avoid normative assumptions about gender and sexuality, respect people's identities and speak out against witnessed discrimination or slights. Robust policies are needed to protect LGBTQIA+ members from discrimination and provide equal access across other pertinent parts of work life such as leave entitlements, representation in data collection and safe bathroom access. We all deserve to feel safe and respected at work and further effort is needed to ensure this extends to LGBTQIA+ staff in the radiology and radiation oncology workforces.

Assessment of a single-pass venous phase CT chest, abdomen and pelvis and dual-energy CT in general oncology outpatients.

INTRODUCTION: This study assessed replacing traditional protocol CT-arterial chest and venous abdomen and pelvis, with a single-pass, single-bolus, venous phase CT chest, abdomen and pelvis (CAP) protocol in general oncology outpatients at a single centre. METHODS: A traditional protocol is an arterial phase chest followed by venous phase abdomen and pelvis. A venous CAP (vCAP) protocol is a single acquisition 60 s after contrast injection, with optional arterial phase upper abdomen based on the primary tumour. Consecutive eligible patients were assessed, using each patient's prior study as a comparator. Attenuation for various structures, lesion conspicuity and dose were compared. Subset analysis of dual-energy (DE) CT scans in the vCAP protocol performed for lesion conspicuity on 50 keV virtual monoenergetic (VME) images. RESULTS: One hundred and eleven patients were assessed with both protocols. Forty-six patients had their vCAP scans using DECT. The vCAP protocol had no significant difference in the attenuation of abdominal structures, with reduced attenuation of mediastinal structures. There was a significant improvement in the visibility of pleural lesions (p < 0.001), a trend for improved mediastinal nodes assessment, and no significant difference for abdominal lesions. A significant increase in liver lesion conspicuity on 50 keV VME reconstructions was noted for both readers (p < 0.001). There were significant dose reductions with the vCAP protocol. CONCLUSION: A single-pass vCAP protocol offered an improved thoracic assessment with no loss of abdominal diagnostic confidence and significant dose reductions compared to traditional protocol. Improved liver lesion conspicuity on 50 keV VME images across a range of cancers is promising.

Machine learning and deep learning predictive models for long-term prognosis in patients with chronic obstructive pulmonary disease: a systematic review and meta-analysis.

BACKGROUND: Machine learning and deep learning models have been increasingly used to predict long-term disease progression in patients with chronic obstructive pulmonary disease (COPD). We aimed to summarise the performance of such prognostic models for COPD, compare their relative performances, and identify key research gaps. METHODS: We conducted a systematic review and meta-analysis to compare the performance of machine learning and deep learning prognostic models and identify pathways for future research. We searched PubMed, Embase, the Cochrane Library, ProQuest, Scopus, and Web of Science from database inception to April 6, 2023, for studies in English using machine learning or deep learning to predict patient outcomes at least 6 months after initial clinical presentation in those with COPD. We included studies comprising human adults aged 18-90 years and allowed for any input modalities. We reported area under the receiver operator characteristic curve (AUC) with 95% CI for predictions of mortality, exacerbation, and decline in forced expiratory volume in 1 s (FEV1). We reported the degree of interstudy heterogeneity using Cochran's Q test (significant heterogeneity was defined as p≤0·10 or I2>50%). Reporting quality was assessed using the TRIPOD checklist and a risk-of-bias assessment was done using the PROBAST checklist. This study was registered with PROSPERO (CRD42022323052). FINDINGS: We identified 3620 studies in the initial search. 18 studies were eligible, and, of these, 12 used conventional machine learning and six used deep learning models. Seven models analysed exacerbation risk, with only six reporting AUC and 95% CI on internal validation datasets (pooled AUC 0·77 [95% CI 0·69-0·85]) and there was significant heterogeneity (I2 97%, p<0·0001). 11 models analysed mortality risk, with only six reporting AUC and 95% CI on internal validation datasets (pooled AUC 0·77 [95% CI 0·74-0·80]) with significant degrees of heterogeneity (I2 60%, p=0·027). Two studies assessed decline in lung function and were unable to be pooled. Machine learning and deep learning models did not show significant improvement over pre-existing disease severity scores in predicting exacerbations (p=0·24). Three studies directly compared machine learning models against pre-existing severity scores for predicting mortality and pooled performance did not differ (p=0·57). Of the five studies that performed external validation, performance was worse than or equal to regression models. Incorrect handling of missing data, not reporting model uncertainty, and use of datasets that were too small relative to the number of predictive features included provided the largest risks of bias. INTERPRETATION: There is limited evidence that conventional machine learning and deep learning prognostic models demonstrate superior performance to pre-existing disease severity scores. More rigorous adherence to reporting guidelines would reduce the risk of bias in future studies and aid study reproducibility. FUNDING: None.

The value of standards for health datasets in artificial intelligence-based applications.

Artificial intelligence as a medical device is increasingly being applied to healthcare for diagnosis, risk stratification and resource allocation. However, a growing body of evidence has highlighted the risk of algorithmic bias, which may perpetuate existing health inequity. This problem arises in part because of systemic inequalities in dataset curation, unequal opportunity to participate in research and inequalities of access. This study aims to explore existing standards, frameworks and best practices for ensuring adequate data diversity in health datasets. Exploring the body of existing literature and expert views is an important step towards the development of consensus-based guidelines. The study comprises two parts: a systematic review of existing standards, frameworks and best practices for healthcare datasets; and a survey and thematic analysis of stakeholder views of bias, health equity and best practices for artificial intelligence as a medical device. We found that the need for dataset diversity was well described in literature, and experts generally favored the development of a robust set of guidelines, but there were mixed views about how these could be implemented practically. The outputs of this study will be used to inform the development of standards for transparency of data diversity in health datasets (the STANDING Together initiative).

Predictors of non-remission of depression in a palliative care population.

BACKGROUND: Prospective studies of depression in palliative care are rare. Two studies that examine depression prospectively in patients with advanced disease have not looked at predictors of remission. AIMS: to explore prospective predictors of non-remission of depression in palliative care. DESIGN AND PARTICIPANTS: The study design comprised two data collections: initial assessment on referral to a palliative care service in South London, UK, and a four-week follow-up. Seventy six participants met the criteria for 'any depressive syndrome' at the time 1 assessment, using the PRIME-MD, who also participated at time 2. The outcome measure was remission (N = 39) or non-remission (N = 37) of depression by time 2. RESULTS: The findings showed that reporting low social support from family and friends at time of referral was the most powerful risk factor for non-remission. There was also a strong association between improved physical symptoms, from time 1 to 2, and remission of depression. CONCLUSIONS: This study in palliative care is the first of which we are aware to explore factors associated with non-remission of depression. Depressed patients identified with low social support on referral to palliative care services might particularly benefit from additional psychosocial care in the treatment of their depression. This study provides evidence that effective physical symptom management in palliative care may be a valuable intervention for depressive symptoms.