Embedding patient-reported outcomes at the heart of artificial intelligence health-care technologies

Randomised controlled trials evaluating artificial intelligence in clinical practice: a scoping review

This scoping review of randomised controlled trials on artificial intelligence (AI) in clinical practice reveals an expanding interest in AI across clinical specialties and locations. The USA and China are leading in the number of trials, with a focus on deep learning systems for medical imaging, particularly in gastroenterology and radiology. A majority of trials (70 [81%] of 86) report positive primary endpoints, primarily related to diagnostic yield or performance; however, the predominance of single-centre trials, little demographic reporting, and varying reports of operational efficiency raise concerns about the generalisability and practicality of these results. Despite the promising outcomes, considering the likelihood of publication bias and the need for more comprehensive research including multicentre trials, diverse outcome measures, and improved reporting standards is crucial. Future AI trials should prioritise patient-relevant outcomes to fully understand AI's true effects and limitations in health care.

What can patients tell us in Sjögren's syndrome?

In Sjögren's Syndrome (SS), clinical heterogeneity and discordance between disease activity measures and patient experience are key obstacles to effective therapeutic development. Patient reported outcome measures (PROMs) are useful tools for understanding the unmet needs from the patients' perspective and therefore they are key for the development of patient centric healthcare systems. Initial concern about the subjectivity of PROMs has given way to methodological rigour and clear guidance for the development of PROMs. To date, several studies of patient stratification using PROMs have identified similar symptom-based subgroups. There is evidence to suggest that these subgroups may represent different disease endotypes with differing responses to therapeutic interventions. Stratified medicine approaches, alongside sensitive outcome measures, have the potential to improve our understanding of SS pathobiology and therapeutic development. The inclusion of PROMs is important for the success of such approaches. In this review we discuss the opportunities of using PROMs in understanding the pathogenesis of and therapeutic development for SS.

DENTAL PATIENT-REPORTED OUTCOMES UPDATE 2023

The emergence and rapid development of disruptive innovations are quickly turning our profession into personalized dentistry, built upon evidence-based, data-oriented, and patient-centered research. In order to help improve the quality and quantity of patient-centered evidence in dentistry, further promote the wide and standard use of dental patient-reported outcomes (dPROs) and dental patient-reported outcome measures (dPROMs), the Journal of Evidence-Based Dental Practice has put together this special issue, the third of a series entitled Dental Patient-Reported Outcomes Update. A total of 7 solicited articles are collected in this issue. To put them into a broader perspective, this review provides a concise summary of key, selected PRO and dPRO articles published during 2023. A brief introduction to those articles included in this Special Issue follows. Four main domains are covered in this Special Issue: (1) dPROs and digital dentistry, (2) standardization of dPRO-related methodology, (3) current usage of dPROs and dPROMs in published research, and (iv) the significance and relevance of dPRO usage.

Clinical Deployment of Machine Learning Tools in Transplant Medicine: What Does the Future Hold?

Medical applications of machine learning (ML) have shown promise in analyzing patient data to support clinical decision-making and provide patient-specific outcomes. In transplantation, several applications of ML exist which include pretransplant: patient prioritization, donor-recipient matching, organ allocation, and posttransplant outcomes. Numerous studies have shown the development and utility of ML models, which have the potential to augment transplant medicine. Despite increasing efforts to develop robust ML models for clinical use, very few of these tools are deployed in the healthcare setting. Here, we summarize the current applications of ML in transplant and discuss a potential clinical deployment framework using examples in organ transplantation. We identified that creating an interdisciplinary team, curating a reliable dataset, addressing the barriers to implementation, and understanding current clinical evaluation models could help in deploying ML models into the transplant clinic setting.

Enhancing patient experience assessment with psychological care in severe mental disorders: A study of the PREMIUM program

Incorporating the experiences of patients with severe mental disorders (SMD) into clinical practice offers valuable insights for optimizing psychological care's effectiveness with more patient-centered and personalized interventions. The study aimed to develop a patient-reported experience measure regarding psychological care (PREMIUM-PSY) using adaptive testing and investigate its association with quality of life. In a multicenter study involving 443 patients with SMD, PREMIUM-PSY demonstrated both validity and efficiency (6-item average). Positive patient experiences were associated with enhanced mental and physical quality of life (β = 3.15[2.17;4.12], p < 0.001 and β = 1.18[0.04;2.32], p = 0.042), suggesting PREMIUM-PSY's potential for optimizing psychological care outcomes.

Development of the PREMIUM computerized adaptive testing for measuring the access and care coordination for patients with severe mental illness

Severe mental illness (SMI) patients often have complex health needs, which makes it difficult to access and coordinate their care. This study aimed to develop a computerized adaptive testing (CAT) tool, PREMIUM CAT-ACC, to measure SMI patients' experience with access and care coordination. This multicenter and cross-sectional study included 496 adult in- and out-patients with SMI (i.e., schizophrenia, bipolar disorder, or major depressive disorder). Psychometric analysis of the 13-item bank showed adequate properties, with preliminary evidence of external validity and no substantial differential item functioning for sex, age, care setting, and diagnosis, making it suitable for CAT administration. A post-hoc CAT simulation demonstrated that the tool was efficient and accurate, with an average of seven items, compared to the full item bank administration. Its use by clinicians can contribute to optimizing patient care pathways and transitioning towards more person-centered healthcare.

Reducing Health Inequalities in Individuals with Severe Mental Disorders: Harnessing Real-World Data and Patient-Reported Measures

Mental disorders are the leading cause of diminished lifespans worldwide and make up 5 of the top 10 most significant causes of disability [...].

The role of patient-reported outcome measures in trials of artificial intelligence health technologies: a systematic evaluation of ClinicalTrials.gov records (1997-2022)

The extent to which patient-reported outcome measures (PROMs) are used in clinical trials for artificial intelligence (AI) technologies is unknown. In this systematic evaluation, we aim to establish how PROMs are being used to assess AI health technologies. We searched ClinicalTrials.gov for interventional trials registered from inception to Sept 20, 2022, and included trials that tested an AI health technology. We excluded observational studies, patient registries, and expanded access reports. We extracted data regarding the form, function, and intended use population of the AI health technology, in addition to the PROMs used and whether PROMs were incorporated as an input or output in the AI model. The search identified 2958 trials, of which 627 were included in the analysis. 152 (24%) of the included trials used one or more PROM, visual analogue scale, patient-reported experience measure, or usability measure as a trial endpoint. The type of AI health technologies used by these trials included AI-enabled smart devices, clinical decision support systems, and chatbots. The number of clinical trials of AI health technologies registered on ClinicalTrials.gov and the proportion of trials that used PROMs increased from registry inception to 2022. The most common clinical areas AI health technologies were designed for were digestive system health for non-PROM trials and musculoskeletal health (followed by mental and behavioural health) for PROM trials, with PROMs commonly used in clinical areas for which assessment of health-related quality of life and symptom burden is particularly important. Additionally, AI-enabled smart devices were the most common applications tested in trials that used at least one PROM. 24 trials tested AI models that captured PROM data as an input for the AI model. PROM use in clinical trials of AI health technologies falls behind PROM use in all clinical trials. Trial records having inadequate detail regarding the PROMs used or the type of AI health technology tested was a limitation of this systematic evaluation and might have contributed to inaccuracies in the data synthesised. Overall, the use of PROMs in the function and assessment of AI health technologies is not only possible, but is a powerful way of showing that, even in the most technologically advanced health-care systems, patients' perspectives remain central.