SEARCH · Search PubMed

Search Search PubMed

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

6 recordsLinked to original sources

PubMed2026

Diagnostic Performance of Machine Learning for Systemic Lupus Erythematosus: Systematic Review and Meta-Analysis.

BACKGROUND: Early and accurate diagnosis of systemic lupus erythematosus (SLE) and its organ involvement is essential. Previous reviews of machine learning (ML) in SLE combined heterogeneous tasks and validation strategies and may have overinterpreted model performance. OBJECTIVE: This study evaluated the diagnostic performance of ML and deep learning (DL) models for 3 clinically distinct SLE-related tasks: SLE classification or diagnosis, lupus nephritis (LN) diagnosis, and neuropsychiatric systemic lupus erythematosus (NPSLE) discrimination. We also assessed methodological quality and certainty of evidence. METHODS: PubMed, Embase, Cochrane Library, Web of Science, and IEEE Xplore were searched from January 2014 to April 2026. Eligible peer-reviewed diagnostic accuracy studies developed or validated ML or DL models for 1 of the 3 prespecified tasks, used an accepted reference standard, and provided data for a 2×2 contingency table. Bivariate random-effects meta-analyses with the Hartung-Knapp-Sidik-Jonkman adjustment were used to pool sensitivity and specificity. We reported 95% prediction intervals (PIs), assessed risk of bias using the Quality Assessment of Diagnostic Accuracy Studies for Artificial Intelligence tool (QUADAS-AI; Viknesh Sounderajah [Imperial College London]), and evaluated certainty of evidence using the Grading of Recommendations Assessment, Development, and Evaluation framework for diagnostic test accuracy. RESULTS: Twenty-nine studies were included: 17 for SLE classification, 5 for LN diagnosis, and 7 for NPSLE discrimination. In the primary task-stratified analysis, pooled sensitivity was 0.91 (95% CI 0.86-0.94; 95% PI 0.56-0.99), and pooled specificity was 0.94 (95% CI 0.91-0.96; 95% PI 0.69-0.99), with low heterogeneity (I²=23.9% and 22.9%, respectively). DL models showed a sensitivity of 0.93 and specificity of 0.95, compared with 0.88 and 0.94 for traditional ML models. Certainty of evidence was high for most analyses but low for LN diagnosis because of inconsistency and imprecision. All studies were retrospective, and only 9 of 29 (31%) performed independent external validation. Overall risk of bias was high or unclear in 22 of 29 (75.9%) studies. No study reported model calibration, decision-curve analysis, or net clinical benefit. CONCLUSIONS: ML models showed promising diagnostic accuracy across 3 distinct SLE-related tasks, but wide PIs, limited external validation, and pervasive risk of bias restrict conclusions about real-world generalizability. Prospective multicenter studies with standardized tasks and reference standards, independent external validation, and formal assessment of calibration and clinical utility are required before clinical implementation.

Humans↗

PubMed2026

Analysis of deep learning techniques in computer-aided diagnosis for meniscus injuries: a systematic literature review.

Meniscus informatics is a growing subject of study in the healthcare industry. One of the major hindrances to the healthcare system's transformation is obtaining knowledge and meaningful information from complicated, high-dimensional and diverse sources. Modern biomedical research, for instance, has seen an increase in the use of complex, dissimilar, poorly documented, and generally unstructured electronic health records, imaging, sensor data and text, even after many current techniques have been used to extract more robust and useful elements from the data for analysis. New efficient standards for building end-to-end learning models from complex data are therefore needed. Therefore, the current study aims to examine the most recent research on the use of deep learning techniques for diagnosing meniscus tears and recommend creating comprehensive and meaningful interpretable structures that might benefit the healthcare industry. We also draw attention to shortcomings and the need for better technique development, and we provide new perspectives about this exciting new development in the field.

Humans↗

PubMed2026

Evaluation of the difference between automated and measured QTc intervals in children.

BACKGROUND: The corrected QT interval (QTc) is obtained through automated ECG computations or manual physician measurements. We hypothesized that differences exist in children between the measured and automated QTc intervals within and between Healthy and hypertrophic cardiomyopathy (HCM) subjects with greater differences for HCM due to structural abnormalities. METHODS: QT measurements - Bazett correction- automated (aQTc) and measured (mQTc), were extracted from the GE MUSE database for 385 Healthy pediatric (single ECG) and 208 HCM subjects (2 ECGs), stratified by age < 12 and ≥ 12 yrs., sex, race, and ethnicity. QTc means (SD), automated and measured differences, and the difference of the differences of aQTc and mQTc were analyzed overall and by subgroups. All ECGs were read by one pediatric cardiologist with a second cardiologist reading a random subset of HCM ECGs to evaluate intraclass correlations and agreement. RESULTS: The mQTc intervals were shorter than aQTc intervals within Healthy (p < 0.001) and within first HCM ECGs (p < 0.001) with both aQTc and mQTc shorter in Healthy than HCM (p < 0.001). The difference in these differences was significant overall using HCM ECG 1 but not HCM ECG 2. Healthy subject aQTc and mQTc intervals differed by age, sex, and race (p < 0.002). HCM ECG 1 aQTc- mQTc intervals differed for age < 12 yrs., as well as by sex and race. HCM ECG 2 intervals differed only for age < 12 yrs. CONCLUSIONS: Compared to measured values, automated QTc values were significantly longer in both Healthy and HCM subjects. Automated measurements may overestimate the QTc.

Humans↗

PubMed2026

Artificial intelligence-assisted detection and optical differentiation of colorectal lesions in Lynch syndrome surveillance (CADLY2): a multicentre, open-label, randomised controlled superiority trial.

BACKGROUND: Artificial intelligence (AI)-based computer-aided detection (CADe) systems improve adenoma detection in average-risk colorectal cancer screening. Meanwhile, evidence in Lynch syndrome surveillance is sparse and inconsistent. We assessed the effect of CADe on adenoma detection during Lynch syndrome surveillance. Computer-aided optical diagnosis (CADx) performance for optical differentiation of colorectal lesions was evaluated as a secondary aim. METHODS: CADLY2 was an international, multicentre, open-label, randomised controlled superiority trial at nine specialised hereditary cancer surveillance centres in Belgium, Germany, the Netherlands, and Spain. Adults aged 18 years or older with genetically confirmed Lynch syndrome scheduled for surveillance colonoscopy were randomly assigned (1:1) to high-definition white-light (HD-WL) colonoscopy alone or to HD-WL colonoscopy with computer-aided assistance from CAD EYE (Fujifilm, Tokyo, Japan). CAD EYE was used for CADe during withdrawal and for CADx after lesion detection. Randomisation was done centrally through a secure web-based system using Pocock's minimisation algorithm with a stochastic component and was stratified by centre, sex, previous colorectal cancer, underlying pathogenic variant, and interval since previous colonoscopy. Allocation concealment was ensured through the centralised web-based system. Patients were masked to group allocation until the start of withdrawal in procedures with mild sedation, or until completion of the procedure in procedures with propofol-based sedation. Endoscopists were not masked. The primary outcome was adenoma detection rate, defined as the proportion of patients with at least one histopathologically confirmed adenoma, analysed in the full analysis set (defined as all randomly allocated patients with available data for the primary outcome). The diagnostic performance of the CADx system was evaluated as a secondary outcome. The safety analysis set comprised all randomly allocated patients who underwent a study colonoscopy. This study is registered with the German Clinical Trials Register, DRKS00030695, and is completed. FINDINGS: Between May 9, 2023, and Oct 30, 2025, 757 patients were randomly allocated to HD-WL colonoscopy (377 patients) or to AI-assisted colonoscopy (380 patients); 733 patients were included in the full analysis set (369 HD-WL and 364 AI-assisted). The median age was 49 years (IQR 38-59) in the HD-WL group and 50 years (38-59) in the AI-assisted group; 213 (58%) were female and 156 (42%) male in the HD-WL group, and 207 (57%) were female and 157 (43%) male in the AI-assisted group. The adenoma detection rate was 30·9% (114 of 369 patients) with HD-WL versus 33·8% (123 of 364 patients) with CADe assistance (odds ratio 1·14 [95% CI 0·83-1·57], p=0·41). For CADx differentiation of neoplastic versus non-neoplastic lesions in the paired lesion-level analysis, with histopathology as the reference standard and sessile serrated lesions and traditional serrated adenomas classified as non-neoplastic, CADx sensitivity was 85·9% (95% CI 82·0-89·1) and specificity was 91·4% (89·4-93·0). Three adverse events occurred in the AI-assisted group: two mild post-polypectomy bleedings and one serious pulmonary embolism or deep venous thrombosis unrelated to the procedure. No adverse events occurred in the HD-WL group. INTERPRETATION: CADe-assisted colonoscopy did not show the absolute improvement in adenoma detection rate that was assumed in the prespecified sample-size calculation. CADx did not clearly improve lesion differentiation beyond expert optical diagnosis in expert Lynch syndrome surveillance settings. FUNDING: Third-party research funding of the National Center for Hereditary Tumor Syndromes, University Hospital Bonn.

Humans↗

PubMed2026

Fundamentals of pacemakers ECG interpretation - part 2.

BACKGROUND: Modern pacemakers incorporate arrhythmia-response algorithms, ventricular pacing minimization protocols, and safety mechanisms that generate ECG patterns indistinguishable from pathological AV block, sensing malfunction, or device-mediated tachycardia. Failure to recognize these algorithm-driven signatures leads to unnecessary interventions, misdiagnosis, and inappropriate device reprogramming. This manuscript is the second in a two-part series on pacemaker ECG interpretation. METHODS: We conducted a narrative review of peer-reviewed literature and device-specific documentation on algorithm-driven ECG behavior, synthesizing evidence across arrhythmia recognition, upper rate physiology, ventricular pacing minimization, mode switching, safety mechanisms, and hysteresis algorithms. RESULTS: Pacemaker-mediated tachycardia produces regular paced wide-complex tachycardia locked at the upper tracking rate, initiated by any event with retrograde VA conduction. Ventricular tachycardia is identified by QRS morphology diverging from the known paced pattern, absent pacing spikes, and AV dissociation. Upper rate Wenckebach behavior mimics Mobitz type I AV block; 2:1 upper rate response mimics second-degree AV block. Ventricular pacing minimization algorithms produce isolated nonconducted P waves and prolonged AV intervals that simulate pathological conduction disease. Mode switching causes abrupt rate drops misidentified as output failure. Ventricular safety pacing generates a conspicuously short, fixed AV interval. Three discrete pacing artifacts reflect AV-sequential cardiac resynchronization therapy (CRT), ventricular safety pacing in CRT, or His-bundle pacing with backup RV output. Rate and AV hysteresis produce pauses and wandering AV intervals mimicking oversensing or Wenckebach periodicity. CONCLUSIONS: Recognizing algorithm-driven ECG patterns requires knowledge of device timing intervals and refractory periods, which lets clinicians distinguish programmed behavior from true malfunction or cardiac arrhythmia.

Humans↗

PubMed2026

Linked-color imaging with computer-aided detection and the proximal adenoma miss rate: a randomized tandem trial.

BACKGROUND AND AIMS: Linked-color imaging (LCI) aids the detection and characterization of lesions. Computer-aided detection (CADe) systems have been introduced to improve lesion detection during colonoscopy. Although several studies have been reported regarding LCI, few have investigated the combination of LCI and CADe. This study aimed to evaluate the efficacy of LCI with CADe colonoscopy compared to conventional white-light colonoscopy. METHODS: A single-center, randomized tandem trial was conducted. Participants referred for first-time colonoscopy after fecal immunochemical test (FIT)-positive, asymptomatic screening, or surveillance colonoscopy were randomized (1:1) to undergo CADe-assisted colonoscopy of LCI or white-light imaging (WLI) in the right side of the colon. The primary outcome was adenoma miss rate (AMR) in the right side of the colon. Secondary outcomes included polyp miss rate (PMR), diminutive adenoma miss rate (dAMR), sessile serrated lesion miss rate (SSLMR), advanced adenoma miss rate, advanced neoplasia miss rate, flat-type lesion miss rate (FMR), and the differences in miss rates based on expertise. RESULTS: Among 232 randomized participants, 209 were analyzed (LCI/CADe: 102; WLI: 107). AMR (WLI: 39% vs LCI/CADe: 20%; P = .001), PMR (42% vs 18%; P < .001), and dAMR (42% vs 21%; P = .003) were significantly lower in the LCI/CADe arm, particularly among experts. SSLMR (46% vs 0%), advanced AMR (30% vs 0%), advanced neoplasia miss rate (25% vs 0%), and FMR (27% vs 5.6%) were lower in LCI/CADe, although without statistical significance. CONCLUSIONS: Compared to conventional colonoscopy, LCI with CADe colonoscopy resulted in a statistically significant decrease, especially in AMR. (UMIN 000050685).

Humans↗