-
JMIR Research Protocols Jun 2024Artificial intelligence (AI) medical devices have the potential to transform existing clinical workflows and ultimately improve patient outcomes. AI medical devices have...
BACKGROUND
Artificial intelligence (AI) medical devices have the potential to transform existing clinical workflows and ultimately improve patient outcomes. AI medical devices have shown potential for a range of clinical tasks such as diagnostics, prognostics, and therapeutic decision-making such as drug dosing. There is, however, an urgent need to ensure that these technologies remain safe for all populations. Recent literature demonstrates the need for rigorous performance error analysis to identify issues such as algorithmic encoding of spurious correlations (eg, protected characteristics) or specific failure modes that may lead to patient harm. Guidelines for reporting on studies that evaluate AI medical devices require the mention of performance error analysis; however, there is still a lack of understanding around how performance errors should be analyzed in clinical studies, and what harms authors should aim to detect and report.
OBJECTIVE
This systematic review will assess the frequency and severity of AI errors and adverse events (AEs) in randomized controlled trials (RCTs) investigating AI medical devices as interventions in clinical settings. The review will also explore how performance errors are analyzed including whether the analysis includes the investigation of subgroup-level outcomes.
METHODS
This systematic review will identify and select RCTs assessing AI medical devices. Search strategies will be deployed in MEDLINE (Ovid), Embase (Ovid), Cochrane CENTRAL, and clinical trial registries to identify relevant papers. RCTs identified in bibliographic databases will be cross-referenced with clinical trial registries. The primary outcomes of interest are the frequency and severity of AI errors, patient harms, and reported AEs. Quality assessment of RCTs will be based on version 2 of the Cochrane risk-of-bias tool (RoB2). Data analysis will include a comparison of error rates and patient harms between study arms, and a meta-analysis of the rates of patient harm in control versus intervention arms will be conducted if appropriate.
RESULTS
The project was registered on PROSPERO in February 2023. Preliminary searches have been completed and the search strategy has been designed in consultation with an information specialist and methodologist. Title and abstract screening started in September 2023. Full-text screening is ongoing and data collection and analysis began in April 2024.
CONCLUSIONS
Evaluations of AI medical devices have shown promising results; however, reporting of studies has been variable. Detection, analysis, and reporting of performance errors and patient harms is vital to robustly assess the safety of AI medical devices in RCTs. Scoping searches have illustrated that the reporting of harms is variable, often with no mention of AEs. The findings of this systematic review will identify the frequency and severity of AI performance errors and patient harms and generate insights into how errors should be analyzed to account for both overall and subgroup performance.
TRIAL REGISTRATION
PROSPERO CRD42023387747; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=387747.
INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)
PRR1-10.2196/51614.
PubMed: 38941147
DOI: 10.2196/51614 -
JMIR Research Protocols Jun 2024The lack of regular physical activity (PA) in individuals with spinal cord injury (SCI) in the United States is an ongoing health crisis. Regular PA and exercise-based...
mHealth-Based Just-in-Time Adaptive Intervention to Improve the Physical Activity Levels of Individuals With Spinal Cord Injury: Protocol for a Randomized Controlled Trial.
BACKGROUND
The lack of regular physical activity (PA) in individuals with spinal cord injury (SCI) in the United States is an ongoing health crisis. Regular PA and exercise-based interventions have been linked with improved outcomes and healthier lifestyles among those with SCI. Providing people with an accurate estimate of their everyday PA level can promote PA. Furthermore, PA tracking can be combined with mobile health technology such as smartphones and smartwatches to provide a just-in-time adaptive intervention (JITAI) for individuals with SCI as they go about everyday life. A JITAI can prompt an individual to set a PA goal or provide feedback about their PA levels.
OBJECTIVE
The primary aim of this study is to investigate whether minutes of moderate-intensity PA among individuals with SCI can be increased by integrating a JITAI with a web-based PA intervention (WI) program. The WI program is a 14-week web-based PA program widely recommended for individuals with disabilities. A secondary aim is to investigate the benefit of a JITAI on proximal PA, defined as minutes of moderate-intensity PA within 120 minutes of a PA feedback prompt.
METHODS
Individuals with SCI (N=196) will be randomized to a WI arm or a WI+JITAI arm. Within the WI+JITAI arm, a microrandomized trial will be used to randomize participants several times a day to different tailored feedback and PA recommendations. Participants will take part in the 24-week study from their home environment in the community. The study has three phases: (1) baseline, (2) WI program with or without JITAI, and (3) PA sustainability. Participants will provide survey-based information at the initial meeting and at the end of weeks 2, 8, 16, and 24. Participants will be asked to wear a smartwatch every day for ≥12 hours for the duration of the study.
RESULTS
Recruitment and enrollment began in May 2023. Data analysis is expected to be completed within 6 months of finishing participant data collection.
CONCLUSIONS
The JITAI has the potential to achieve long-term PA performance by delivering tailored, just-in-time feedback based on the person's actual PA behavior rather than a generic PA recommendation. New insights from this study may guide intervention designers to develop engaging PA interventions for individuals with disability.
TRIAL REGISTRATION
ClinicalTrials.gov NCT05317832; https://clinicaltrials.gov/study/NCT05317832.
INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)
DERR1-10.2196/57699.
PubMed: 38941145
DOI: 10.2196/57699 -
JMIR Medical Informatics Jun 2024Integrating machine learning (ML) models into clinical practice presents a challenge of maintaining their efficacy over time. While existing literature offers valuable...
Integrating machine learning (ML) models into clinical practice presents a challenge of maintaining their efficacy over time. While existing literature offers valuable strategies for detecting declining model performance, there is a need to document the broader challenges and solutions associated with the real-world development and integration of model monitoring solutions. This work details the development and use of a platform for monitoring the performance of a production-level ML model operating in Mayo Clinic. In this paper, we aimed to provide a series of considerations and guidelines necessary for integrating such a platform into a team's technical infrastructure and workflow. We have documented our experiences with this integration process, discussed the broader challenges encountered with real-world implementation and maintenance, and included the source code for the platform. Our monitoring platform was built as an R shiny application, developed and implemented over the course of 6 months. The platform has been used and maintained for 2 years and is still in use as of July 2023. The considerations necessary for the implementation of the monitoring platform center around 4 pillars: feasibility (what resources can be used for platform development?); design (through what statistics or models will the model be monitored, and how will these results be efficiently displayed to the end user?); implementation (how will this platform be built, and where will it exist within the IT ecosystem?); and policy (based on monitoring feedback, when and what actions will be taken to fix problems, and how will these problems be translated to clinical staff?). While much of the literature surrounding ML performance monitoring emphasizes methodological approaches for capturing changes in performance, there remains a battery of other challenges and considerations that must be addressed for successful real-world implementation.
PubMed: 38941140
DOI: 10.2196/50437 -
The Journal of Clinical Endocrinology... Jun 2024Investigating the co-occurrence of obstructive sleep apnea (OSA) and primary aldosteronism (PA) is crucial for understanding their interrelation.
CONTEXT
Investigating the co-occurrence of obstructive sleep apnea (OSA) and primary aldosteronism (PA) is crucial for understanding their interrelation.
OBJECTIVE
This work aimed to evaluate the prevalence of OSA in individuals diagnosed with PA and to assess the prevalence of PA within the OSA population, with a specific focus on hypertensive individuals.
METHODS
An exhaustive search was performed across PubMed, Embase, CINAHL, Scopus, and Web of Science up to September 2023, without restrictions on language or publication date. Studies were selected based on their focus on the prevalence of OSA in PA patients and vice versa, specifically in hypertensive individuals. Data were extracted using standard guidelines, focusing on patient characteristics, prevalence rates, and other relevant clinical parameters.
RESULTS
Proportional meta-analysis using a random-effects model revealed a 59.8% prevalence of OSA in hypertensive PA patients, with 45.4% exhibiting moderate-to-severe OSA. Meta-regression showed no significant effect of age, sex, body mass index, antihypertensive medication, systolic blood pressure, diastolic blood pressure, or serum potassium on OSA prevalence. However, a significant positive association was found with the glomerular filtration rate (GFR) (P < .001). Subgroup analysis also revealed that a hyperfiltration rate (GFR ≥ 100 mL/min per 1.73 m2) may be associated with a higher prevalence of OSA (71%, P value for interaction < .01). Among hypertensive OSA patients, 11.2% had PA.
CONCLUSION
A substantial prevalence of OSA in individuals with PA was identified, demonstrating a complex interplay between these conditions in hypertensive patients. Notably, the prevalence of OSA was significantly associated with kidney hyperfiltration.
PubMed: 38941133
DOI: 10.1210/clinem/dgae415 -
JMIR Research Protocols Jun 2024Pulmonary rehabilitation is widely recommended to improve functional status and as secondary and tertiary prevention in individuals with chronic pulmonary diseases....
Assessing Functional Capacity in Directly and Remotely Monitored Home-Based Settings in Individuals With Chronic Respiratory Diseases: Protocol for a Multinational Validation Study.
BACKGROUND
Pulmonary rehabilitation is widely recommended to improve functional status and as secondary and tertiary prevention in individuals with chronic pulmonary diseases. Unfortunately, access to timely and appropriate rehabilitation remains limited. To help close this inaccessibility gap, telerehabilitation has been proposed. However, exercise testing is necessary for effective and safe exercise prescription. Current gold-standard tests, such as maximal cardiopulmonary exercise testing (CPET) and the 6-minute walk test (6MWT), are poorly adapted to home-based or telerehabilitation settings. This was an obstacle to the continuity of services during the COVID-19 pandemic. It is essential to validate tests adapted to these new realities, such as the 6-minute stepper test (6MST). This test, strongly inspired by 6MWT, consists of taking as many steps as possible on a "stepper" for 6 minutes.
OBJECTIVE
This study aims to evaluate the metrological qualities of 6MST by (1) establishing concurrent validity and agreement between the 6MST and CPET, as well as with the 6MWT; (2) determining test-retest reliability in a home-based setting with direct and remote (videoconferencing) monitoring; and (3) documenting adverse events and participant perspectives when performing the 6MST in home-based settings.
METHODS
Three centers (Centre de recherche de l'Institut universitaire de cardiologie et de pneumologie de Québec in Québec, Groupement des Hôpitaux de l'Institut Catholique de Lille in France, and FormAction Santé in France) will be involved in this multinational project, which is divided into 2 studies. For study 1 (objective 1), 30 participants (Québec, n=15; France, n=15) will be recruited. Two laboratory visits will be performed to assess anthropometric data, pulmonary function, and the 3 exercise tolerance tests (CPET, 6MWT, and 6MST). Concurrent validity (paired sample t tests and Pearson correlations) and agreement (Bland-Altman plots with 95% agreement limits) will be evaluated. For study 2 (objectives 2 and 3), 52 participants (Québec, n=26; France, n=26) will be recruited. Following a familiarization trial (trial 1), the 6MST will be conducted on 2 separate occasions (trials 2 and 3), once under direct supervision and once under remote supervision, in a randomized order. Paired sample t test, Bland-Altman plots, and intraclass correlations will be used to compare trials 2 and 3. A semistructured interview will be conducted after the third trial to collect participants' perspectives.
RESULTS
Ethical approval was received for this project (October 12, 2023, in Québec and September 25, 2023, in France) and the first participant was recruited in February 2024.
CONCLUSIONS
This study innovates by validating a new clinical test necessary for the development and implementation of new models of rehabilitation adapted to home and telerehabilitation contexts. This study also aligns with the United Nations Sustainable Development Goals by contributing to augmenting health care service delivery (goal 3) and reducing health care access inequalities (goal 11).
TRIAL REGISTRATION
ClinicalTrials.gov NCT06447831; https://clinicaltrials.gov/study/NCT06447831.
INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)
DERR1-10.2196/57404.
PubMed: 38941132
DOI: 10.2196/57404 -
Cancer Nursing Jun 2024Balance impairment in cancer survivors can be a consequence of chemotherapy-induced peripheral neuropathy (CIPN). Previous meta-analyses suggested that exercise...
BACKGROUND
Balance impairment in cancer survivors can be a consequence of chemotherapy-induced peripheral neuropathy (CIPN). Previous meta-analyses suggested that exercise significantly improved balance, but the results were only based on 3 and 4 primary studies.
OBJECTIVES
This meta-analysis examined the effects of exercise on balance in cancer survivors with CIPN and investigated the moderating effects of source, methods, interventions, and participant characteristics.
METHODS
We searched 12 electronic databases and 5 websites without date restriction through December 18, 2023, for primary studies examining the effect of exercise to improve balance in cancer survivors with CIPN reported in English. We retrieved 12 studies that provided 14 comparisons (N = 576), coded them, assessed quality indicators, and evaluated effect sizes across studies.
RESULTS
Using the random-effects model, the estimated summary effect (Hedges' g) of exercise on balance was 0.68 (Knapp-Hartung adjusted 95% confidence interval, 0.41-0.94; P = .0001) compared with comparison groups. Subgroup analysis revealed that blinded data collectors, intervention fidelity examination, and difference in exercise protocol significantly influenced effect size. Meta-regression analysis showed that session minutes was associated with higher effect sizes.
CONCLUSION
Exercise with balance training significantly improved balance in cancer survivors. Balance training should be integrated into the current exercise guidelines for cancer survivors with CIPN.
IMPLICATIONS FOR PRACTICE
Nurses should encourage cancer survivors to engage in exercise with balance training when undergoing chemotherapy. Physical function and barriers to exercise should be assessed before delivering exercise interventions. Exercises should be tailored according to individual performance.
PubMed: 38941127
DOI: 10.1097/NCC.0000000000001382 -
Anti-cancer Drugs Jun 2024Patients with recurrent/metastatic (R/M) platinum-refractory squamous cell carcinoma of the head and neck (SCCHN) have fewer treatment options and harbor an especially...
Patients with recurrent/metastatic (R/M) platinum-refractory squamous cell carcinoma of the head and neck (SCCHN) have fewer treatment options and harbor an especially poor prognosis. Maintaining treatment with anti-PD1 agents beyond response evaluation criteria in solid tumors-defined disease progression (TBP) has been shown to be efficacious in several solid tumors, including head and neck cancer. We present the case of a platinum-refractory locally recurrent, PD-L1-negative hypopharyngeal carcinoma, that received second-line nivolumab which was then maintained beyond progression under the following criteria: no Eastern Cooperative Oncology Group performance status deterioration, no rapidly progressive disease, no severe toxicity, and evidence of overall treatment benefit. The patient achieved a partial response 8 months after starting second-line nivolumab, with progressive disease at 26 months, then followed by the first TBP with nivolumab lasting for 15 months due to a new tumor progression. A second TBP with nivolumab lasting for 7 months, was followed by a third TBP with nivolumab for 12 months and achieving a major tumor response. Treatment is still ongoing 60 months after starting nivolumab, with excellent tolerance to therapy. Maintaining anti-PD1 agents beyond progression is an efficacious treatment option for patients with R/M SCCHN, that may achieve very durable disease control and even late major responses.
PubMed: 38941120
DOI: 10.1097/CAD.0000000000001635 -
Age and Ageing Jun 2024Epigenetic ageing is among the most promising ageing biomarkers and may be a useful marker of physical function decline, beyond chronological age. This study...
BACKGROUND
Epigenetic ageing is among the most promising ageing biomarkers and may be a useful marker of physical function decline, beyond chronological age. This study investigated whether epigenetic age acceleration (AA) is associated with the change in frailty scores over 7 years and the 7-year risk of incident frailty and persistent Activities of Daily Living (ADL) disability among 560 Australians (50.7% females) aged ≥70 years.
METHODS
Seven AA indices, including GrimAge, GrimAge2, FitAge and DunedinPACE, were estimated from baseline peripheral-blood DNA-methylation. Frailty was assessed using both the 67-item deficit-accumulation frailty index (FI) and Fried phenotype (Fried). Persistent ADL disability was defined as loss of ability to perform one or more basic ADLs for at least 6 months. Linear mixed models and Cox proportional-hazard regression models were used as appropriate.
RESULTS
Accelerated GrimAge, GrimAge2, FitAge and DunedinPACE at baseline were associated with increasing FI scores per year (adjusted-Beta ranged from 0.0015 to 0.0021, P < 0.05), and accelerated GrimAge and GrimAge2 were associated with an increased risk of incident FI-defined frailty (adjusted-HRs 1.43 and 1.39, respectively, P < 0.05). The association between DunedinPACE and the change in FI scores was stronger in females (adjusted-Beta 0.0029, P 0.001 than in males (adjusted-Beta 0.0002, P 0.81). DunedinPACE, but not the other AA measures, was also associated with worsening Fried scores (adjusted-Beta 0.0175, P 0.04). No associations were observed with persistent ADL disability.
CONCLUSION
Epigenetic AA in later life is associated with increasing frailty scores per year and the risk of incident FI-defined frailty.
PubMed: 38941117
DOI: 10.1093/ageing/afae127 -
Chemphyschem : a European Journal of... Jun 2024Cu-exchanged chabazite (Cu-CHA) is widely applied for ammonia assisted selective catalytic reduction of nitrogen oxides (NH3-SCR). The Cu+ ions are at low temperatures...
Cu-exchanged chabazite (Cu-CHA) is widely applied for ammonia assisted selective catalytic reduction of nitrogen oxides (NH3-SCR). The Cu+ ions are at low temperatures solvated by NH3 forming mobile [Cu(NH3)2]+ complexes. The dynamic behaviour of the complexes is critical as O2 adsorption requires a pair of complexes to form a [Cu2(NH3)4O2]2+ peroxo-species over which NO couples with NH3. Here we introduce a first principles-based kinetic Monte Carlo approach to explore the effect of the Al-distribution on the reaction kinetics of NH3-SCR over Cu-CHA. The method allows us to scrutinize the interplay between the pairing of [Cu(NH3)2]+ complexes and the reaction landscape for the NH3-SCR reaction over the peroxo-complex. The Al-distribution affects the stability of the [Cu(NH3)2]+ pairs as well as the kinetic parameters of the SCR-reaction. The turn-over frequency is determined by the stability of the [Cu(NH3)2]+ pairs and the relative strength of NO and NH3 adsorption once a pair is present. The results establish the hierarchy of effects that influences the performance of Cu-CHA over NH3-SCR and provide a computational basis for further development of the Cu-CHA material.
PubMed: 38941111
DOI: 10.1002/cphc.202400558 -
Cancer Nursing Jun 2024Interventions to foster resilience may promote mental health recovery after exposure to stressors. However, comprehensive systematic syntheses of such evidence in family...
BACKGROUND
Interventions to foster resilience may promote mental health recovery after exposure to stressors. However, comprehensive systematic syntheses of such evidence in family members of pediatric cancer patients are lacking.
OBJECTIVE
To systematically review and meta-analyze the evidence for the effects of psychological interventions at fostering resilience in family members of pediatric cancer patients.
METHODS
PubMed, Cumulative Index to Nursing and Allied Health Literature, and 9 other databases were searched for articles published until March 2023. Empirical studies on psychological interventions to improve resilience in family members of pediatric cancer patients were included. Full-text and quality appraisals were performed independently by 2 reviewers. Pooled effect sizes were calculated using random-effects meta-analyses.
RESULTS
Seventeen studies were included, of which 10 were included in the meta-analyses. There was a positive effect of interventions on resilience at postintervention time points, but no effects on depressive symptoms, stress, or well-being. The improvement in resilience was sustained in the short term (≤3 months) and medium term (>3 to ≤6 months), with delayed effects on depressive symptoms and stress. In the 6 studies that reported moderate effect sizes, the interventions comprised problem-solving skills, cognitive strategies, promotion of personal strength, and social resources.
CONCLUSION
The findings indicated that psychological interventions targeting resilience have the potential to positively affect the resilience and mental health outcomes of family members, particularly parents.
IMPLICATIONS FOR PRACTICE
Psychological interventions targeting resilience hold promise in improving the mental health of family members. Future interventions should clearly specify the characteristics of the intervention, such as mode of delivery, format, and duration.
PubMed: 38941110
DOI: 10.1097/NCC.0000000000001368