Radiologist's Guide to Evaluating Publications of Clinical Research on AI: How We Do It.

Literacy in research studies of artificial intelligence (AI) has become an important skill for radiologists. It is required to make a proper assessment of the validity, reproducibility, and clinical applicability of AI studies. However, AI studies are generally perceived to be more difficult for clinician readers to evaluate than traditional clinical research studies. This special report-as an effective, concise guide for readers-aims to assist clinical radiologists in critically evaluating different types of clinical research articles involving AI. It does not intend to be a comprehensive checklist or methodological summary for complete clinical evaluation of AI or a reporting guideline. Ten key items for readers to check are described, regarding study purpose, function and clinical context of AI, training data, data preprocessing, AI modeling techniques, test data, AI performance, helpfulness and value of AI, interpretability of AI, and code sharing. The important aspects of each item are explained for readers to consider when reading publications on AI clinical research. Evaluating each item can help radiologists assess the validity, reproducibility, and clinical applicability of clinical research articles involving AI.

Survey on Value Elements Provided by Artificial Intelligence and Their Eligibility for Insurance Coverage With an Emphasis on Patient-Centered Outcomes.

OBJECTIVE: This study aims to explore the opinions on the insurance coverage of artificial intelligence (AI), as categorized based on the distinct value elements offered by AI, with a specific focus on patient-centered outcomes (PCOs). PCOs are distinguished from traditional clinical outcomes and focus on patient-reported experiences and values such as quality of life, functionality, well-being, physical or emotional status, and convenience. MATERIALS AND METHODS: We classified the value elements provided by AI into four dimensions: clinical outcomes, economic aspects, organizational aspects, and non-clinical PCOs. The survey comprised three sections: 1) experiences with PCOs in evaluating AI, 2) opinions on the coverage of AI by the National Health Insurance of the Republic of Korea when AI demonstrated benefits across the four value elements, and 3) respondent characteristics. The opinions regarding AI insurance coverage were assessed dichotomously and semi-quantitatively: non-approval (0) vs. approval (on a 1-10 weight scale, with 10 indicating the strongest approval). The survey was conducted from July 4 to 26, 2023, using a web-based method. Responses to PCOs and other value elements were compared. RESULTS: Among 200 respondents, 44 (22%) were patients/patient representatives, 64 (32%) were industry/developers, 60 (30%) were medical practitioners/doctors, and 32 (16%) were government health personnel. The level of experience with PCOs regarding AI was low, with only 7% (14/200) having direct experience and 10% (20/200) having any experience (either direct or indirect). The approval rate for insurance coverage for PCOs was 74% (148/200), significantly lower than the corresponding rates for other value elements (82.5%-93.5%; P ≤ 0.034). The approval strength was significantly lower for PCOs, with a mean weight ± standard deviation of 5.1 ± 3.5, compared to other value elements (P ≤ 0.036). CONCLUSION: There is currently limited demand for insurance coverage for AI that demonstrates benefits in terms of non-clinical PCOs.

Effectiveness of telemonitoring versus usual care for chronic obstructive pulmonary disease: A systematic review and meta-analysis.

AIMS: The purpose of this research was to investigate the effectiveness of telemonitoring for chronic obstructive pulmonary disease. METHODS: We searched MEDLINE, EMBASE, the Cochrane Central Register of Controlled Trials and CINAHL up to September 2018. We selected randomised controlled trials comparing telemonitoring and control groups for chronic obstructive pulmonary disease management. Two reviewers independently examined articles based on eligibility, extracted data and evaluated the risk of bias. The Cochrane tool was applied for assessing the risk of bias. The 95% confidence interval was calculated. RESULTS: A total of 28 randomised controlled trials were included. Meta-analysis revealed that there were no variables showing a statistically significant difference between telemonitoring and control groups. Chronic obstructive pulmonary disease exacerbation rate (six studies) was not different between two groups (risk ratio 0.67, 95% confidence interval 0.31-1.42). Subgroup analysis showed that telemonitoring reduced exacerbation rates when the intervention continued for longer than six months or pulmonary function was monitored. No differences between groups were noticed for mortality (seven studies, risk ratio 0.89, 95% confidence interval 0.60-1.34). Similarly, no differences between groups were observed in the patient-reported outcomes (St George's Respiratory Questionnaire, Chronic Respiratory Disease Questionnaire-Dyspnea score) and for health service utilization (length of hospital stay, number of hospital admissions, number of emergency room visits). CONCLUSIONS: Telemonitoring for chronic obstructive pulmonary disease was unlikely to result in statistically significant improvements in health outcomes. However, our novel finding was that at least six months of intervention duration and monitoring of pulmonary function play roles in activating the effects of telemonitoring.

Questionnaire survey on the management of pregnant women with preterm premature rupture of membranes.

OBJECTIVE: The aim of this survey was to study the status of the actual practice in the management of preterm premature rupture of membranes (PPROM) between 34.0 and 36.6 weeks of gestation. METHODS: This survey was designed for obstetricians who work in secondary or tertiary medical institutions and attended the Korean Society of Maternal Fetal Medicine conference held on July 1, 2017, in Korea, using a structured questionnaire consisting of 5 questions. RESULTS: The most commonly used antibiotic was cephalosporin monotherapy (34.5%). Antenatal corticosteroids were applied up to 34.0 weeks of gestation in half of the respondents. The frequency of expectant management was higher than that of immediate delivery in women with PPROM between 34.0 and 36.6 weeks of gestation (57.4%). The most important factor in determining immediate delivery was the symptoms of chorioamnionitis. CONCLUSION: The present survey showed a considerable variation in the actual management of PPROM in women, especially the optimal timing of delivery. More evidenced-based studies with statistical power are required to decrease the heterogeneity of clinical practice.

Comparative study of peritoneal dialysis versus hemodialysis on the clinical outcomes in Korea: a population-based approach.

There has been paucity of data regarding the secular trend of adverse outcomes in peritoneal dialysis (PD) as compared with hemodialysis (HD) in Korea. 96,596 patients who started dialysis between 2004-2015 in Korea were identified using the National Health Insurance Service database. The adjusted hazard ratio (HR) (95% confidence interval, CI) of PD over HD for mortality was 1.31 (1.27-1.36; P < 0.001) in the period of 2004-2007 and 1.21 (1.16-1.27; P < 0.001) in the period of 2008-2011. However, the hazard of PD over HD for mortality turned out to be insignificant in the period of 2012-2015. Similar trend was noted for nonfatal cardiovascular events (CVEs). In subgroup analysis, the hazard of PD over HD for mortality was evident, regardless of the status of age, diabetes, and comorbidity burden in 2004-2011. In 2012-2015, however, the hazard of PD over HD for mortality was insignificant when follow up was censored at one year, which became significant when follow up follow up was censored at three or five year. In conclusion, the mortality of PD over HD in Korea has been significantly improved, a finding that was paralleled by the improved nonfatal CVEs.

Effects of sinusoidal electromagnetic field on structure and function of different kinds of cell lines.

This study investigated that whether a 2 mT, 60 Hz, sinusoidal electromagnetic field (EMF) alters the structure and function of cells. This research compared the effects of EMF on four kinds of cell lines: hFOB 1.19 (fetal osteoblast), T/G HA-VSMC (aortic vascular smooth muscle cell), RPMI 7666 (B lymphoblast), and HCN-2 (cortical neuronal cell). Over 14 days, cells were exposed to EMF for 1, 3, or 6 hours per day (hrs/d). The results pointed to a cell type-specific reaction to EMF exposure. In addition, the cellular responses were dependent on duration of EMF exposure. In the present study, cell proliferation was the trait most sensitive to EMF. EMF treatment promoted growth of hFOB 1.19 and HCN-2 compared with control cells at 7 and 14 days of incubation. When the exposure time was 3 hrs/d, EMF enhanced the proliferation of RPMI 7666 but inhibited that of T/G HA- VSMC. On the other hand, the effects of EMF on cell cycle distribution, cell differentiation, and actin distribution were unclear. Furthermore, we hardly found any correlation between EMF exposure and gap junctional intercellular communication in hFOB 1.19. This study revealed that EMF might serve as a potential tool for manipulating cell proliferation.

Cerebrospinal fluid ß-amyloid1-42 levels in the differential diagnosis of Alzheimer's disease--systematic review and meta-analysis.

OBJECTIVES: The purpose of this study was to carry out systematic review of the literature and meta-analysis to evaluate the diagnostic utility of cerebrospinal fluid (CSF) levels of the 42 amino acid form of amyloid-beta (Aß1-42) as a biomarker for differentiating Alzheimer's disease (AD) from non-AD dementia. METHODS: Design. Systematic literature review was used to evaluate the effectiveness of the Aß for the diagnosis of AD. The Scottish Intercollegiate Guidelines Network (SIGN) tool was used to evaluate independently the quality of the studies. Data sources. The literature review covered from January 1, 2004, to October 22, 2013, and searched eight domestic databases including Korea Med and international databases including Ovid-MEDLINE, EMBASE, and Cochrane Library. Data Extraction and Synthesis. Primary criteria for inclusion were valid studies on (i) patients with mild cognitive impairment with confirmed or suspected AD and non-AD dementia, and (ii) assessment of Aß1-42 levels using appropriate comparative tests. RESULTS: A total of 17 diagnostic evaluation studies were identified in which levels of CSF Aß1-42 were assessed. Meta-analysis was performed on 11 robust studies that compared confirmed AD (n = 2211) with healthy individuals (n = 1030), 10 studies that compared AD with non-AD dementias (n = 627), and 5 studies that compared amnestic mild cognitive impairment (n = 1133) with non-amnestic type subjects (n = 1276). Overall, the CSF Aß1-42 levels were reduced in AD compared to controls or non-AD dementia. The effectiveness of test was evaluated for diagnostic accuracy (pooled sensitivity, 0.80 (95% CI 0.78-0.82); pooled specificity, 0.76 (95% CI 0.74-0.78). CONCLUSIONS: Reduced CSF Aß1-42 levels are of potential utility in the differential diagnosis of AD versus non-AD dementias and controls. Diagnostic accuracy was high in AD versus healthy controls. However, differential diagnosis for MCI or non-AD might be evaluated by other biomarkers.