Artificial Intelligence-assisted Diagnosis of Carotid Artery Calcifications on Panoramic Radiographs: A Meta-analysis.

Human papillomavirus circulating free DNA (HPV cfDNA) is an emerging biomarker with potential utility in the detection and treatment monitoring of cervical cancer. To conduct a systematic review and meta-analysis evaluating the diagnostic and prognostic performance of HPV cfDNA in cervical cancer. A comprehensive literature search was conducted in PubMed, CINAHL, Cochrane Library, Scopus, and Embase through April 2025. Eligible studies reported or allowed calculation of diagnostic performance of HPV cfDNA in HPV-positive cervical cancer patients and/or included serial HPV cfDNA testing during post-treatment follow-up. Meta-analyses were conducted using a random-effects model. Heterogeneity was assessed with the I² statistic. The review followed PRISMA guidelines, and study quality was assessed using QUADAS-2. Of 106 studies screened, 20 met the inclusion criteria. Eleven studies contributed to the diagnostic meta-analysis and six to the prognostic analysis. The pooled sensitivity and specificity of HPV cfDNA for cervical cancer detection were 0.47 (95 % CI, 0.43-0.52) and 0.96 (95 % CI, 0.92-0.98), respectively. Positive and negative likelihood ratios were 10.49 and 0.28, with a diagnostic odds ratio of 71.31. The area under the SROC curve was 0.9825, indicating excellent overall diagnostic performance. Prognostically, HPV cfDNA positivity at 3 months post-treatment was significantly associated with reduced progression-free survival (HR = 8.50; 95 % CI, 4.69-15.41; I² = 0 %). HPV cfDNA shows high specificity and strong prognostic value, supporting its clinical utility in cervical cancer detection and treatment surveillance.

The aims of this study were: ① to evaluate the diagnostic efficacy of six mainstream TI-RADS (Thyroid Imaging Reporting and Data System) classification systems (C-TIRADS, ACR-TIRADS, etc.) in the Northwestern Chinese population; and ② to identify risk factors for malignant thyroid nodules (TNs) using logistic regression based on clinical and ultrasound features, construct a quantifiable scoring Nomogram model, enable rapid and objective risk assessment, and assist in clinical decision-making. A total of 2,047 patients with TNs (1,433 malignant and 614 benign) were enrolled from January 2018 to January 2024 at Shaanxi Provincial People's Hospital. The nodules were divided into a training group (1,435 nodules) and a validation group (612 nodules) in a 7:3 ratio. Twelve characteristics were collected, including age, nodule size, margin, calcification, and the presence of suspicious lymph nodes. Independent risk factors were identified through univariate and multivariate logistic regression analyses to construct a Nomogram model. The model's performance was evaluated using receiver operating characteristic (ROC) curves, accuracy, and other metrics, and compared with the six traditional TI-RADS systems. Ten independent risk factors were identified, including age, nodule size, and irregular margins. In the validation group, the Nomogram model achieved an accuracy of 78.4%, a sensitivity of 81.6%, a specificity of 71.7%, and an area under the ROC curve (AUC) of 0.849. The sensitivities of the six TI-RADS systems (C-TIRADS, ACR-TIRADS, EU-TIRADS, ATA Guidelines, Kwak-TIRADS, and AACE) for distinguishing benign and malignant nodules were 86.0%, 93.2%, 96.9%, 98.3%, 84.4%, and 98.1%, respectively; specificities were 55.6%, 34.8%, 25.3%, 22.2%, 57.1%, and 21.7%, respectively; accuracies were 76.1%, 74.3%, 73.7%, 73.7%, 75.8%, and 73.4%, respectively; and AUCs were 0.752, 0.661, 0.628, 0.617, 0.757, and 0.616, respectively, with no statistically significant differences among them. The Nomogram model significantly outperformed the traditional systems in measures such as AUC, Net Reclassification Improvement (NRI), Integrated Discrimination Improvement (IDI), Positive Likelihood Ratio (PLR), and Negative Likelihood Ratio (NLR) (P < 0.001). The six traditional TI-RADS systems demonstrate similar but overall limited diagnostic efficacy in the Northwestern Chinese population. The Nomogram model, by integrating multidimensional features and applying a quantitative scoring approach, improves the accuracy and objectivity of malignancy risk assessment. Compared to traditional models, it offers better clinical utility, supports optimized decision-making, and helps reduce unnecessary invasive procedures.

To evaluate the diagnostic performance of a rapid point-of-care immunoassay measuring pancreatic stone protein (PSP) for early sepsis identification within the first three days of ICU admission. Subgroup analyses (sex, age, febrile status) were conducted, and the combined diagnostic value of PSP and C-reactive protein (CRP) was assessed. Multicenter, prospective, observational study. Four hundred sixty-six adults the ICU. Six ICUs in the United States who were expected to required at least 24 hours of ICU care. None. We calculated the Youden Index to evaluate the clinical performance of the PSP assay, and the resulting threshold was used to identify patients with sepsis. Diagnostic performance metrics included sensitivity, specificity, accuracy, positive predictive value (PPV), negative predictive value (NPV), positive likelihood ratio (LR+), and negative likelihood ratio (LR-). Receiver operating characteristic analysis were performed for PSP and CRP. At the optimal PSP cutoff point of 117 ng/mL, PSP demonstrated a sensitivity of 74.2%, specificity of 67.8%, accuracy of 71.0%, PPV of 70.3%, NPV of 71.9%, and LR+ and LR- ratios of 2.30 and 0.38, respectively. Combining PSP and CRP improved diagnostic specificity to 95.2%. Subgroup analyses demonstrated consistent performance across sex, and higher specificity was observed in patients 18-60 years old. In febrile patients, PSP achieved high specificity (87.5%) but lower sensitivity (63.6%). In non-febrile patients, sensitivity and specificity were 67.7% and 76.6%, respectively. PSP can serve as a biomarker for the early identification of sepsis. Diagnostic performance across diverse ages, sex, and clinical presentation supports the assay's broad applicability. The combination of PSP and CRP enhances diagnostic specificity for sepsis detection, offering a complementary approach to improve sepsis detection and lead to earlier appropriate management.

This systematic review and meta-analysis aimed to evaluate the diagnostic accuracy of endometrial thickness (EMT) alone, serum human chorionic gonadotropin (hCG) alone, and their combination for detecting retained products of conception (RPOC), providing evidence-based references for standardized clinical diagnosis. We systematically searched PubMed, Cochrane Library, Scopus, China National Knowledge Infrastructure (CNKI), and Wanfang Database for diagnostic studies published from January 2014 to June 2025. Study quality was assessed using the QUADAS-2 tool, and meta-analyses were performed using Stata 17.0 software. Primary outcomes included pooled sensitivity (SEN), specificity (SPE), positive likelihood ratio (PLR), negative likelihood ratio (NLR), diagnostic odds ratio (DOR), and area under the receiver operating characteristic curve (AUC). Heterogeneity was explored via subgroup analyses (ultrasound technique, study population, reference standard, hCG cutoff) and I² statistic/Cochran's Q test. Publication bias was evaluated using Deeks' funnel plot asymmetry test, and sensitivity analyses were conducted by sequential exclusion of individual studies. Analysis of 15 studies (3,268 patients) showed that serum hCG alone (cutoff: 50 mIU/mL) had a sensitivity of 0.89, specificity of 0.87, and AUC of 0.92. EMT alone (cutoff: 8mm) had a sensitivity of 0.72, specificity of 0.86, and AUC of 0.84. The combination achieved a sensitivity of 0.93, specificity of 0.91, and AUC of 0.96. Subgroup analysis confirmed higher diagnostic efficacy for transvaginal versus transabdominal ultrasound (AUC: 0.86 vs. 0.79). Serum hCG alone has higher diagnostic accuracy for RPOC than EMT alone, and their combination significantly improves diagnostic performance. We suggest the clinical use of the combined protocol: "serum hCG (cutoff: 50 mIU/mL) + TVUS-measured EMT (cutoff: 8mm)" for RPOC diagnosis, with recognition of study limitations (e.g., heterogeneity in EMT measurement, limited cutoff exploration). Future research should validate optimal cutoffs for diverse populations and evaluate the protocol's impact on patient outcomes.

Procalcitonin and interleukin-6 to diagnose infection in cardiac surgery patients with hyperinflammation: a two-centre, prospective cross-sectional study.

Background/Objectives: We aimed to evaluate the diagnostic accuracy of the MONA.health artificial intelligence (AI) software (Version 1.0.0; MONA.health, Leuven, Belgium) and compare its advantages in screening for diabetic retinopathy (DR) and diabetic macular edema (DME) with standard fundus photography. Methods: This cross-sectional, real-life instrument validation study was conducted at the Vuk Vrhovac University Clinic in Zagreb during routine DR screening and included 296 patients (592 eyes) with diabetes. Following standard fundus photography using a 45° Zeiss VISUCAM NM/FA camera (Carl Zeiss Meditec AG, Jena, Germany), each patient also underwent imaging with an automated portable retinal camera (NFC-600, Crystalvue Ophthalmic Instruments, Taoyuan City, Taiwan). Two retina specialists independently graded images from the standard camera, while images from the NFC-600 were analyzed using the MONA.health AI software. Results: Among the 592 eyes, human grading identified 81 with any DR, including 17 with mild NPDR, 64 with referable DR (moderate/severe NPDR or PDR), and 13 with DME. The MONA.health AI software identified 65 eyes with referable DR and 19 with DME. For MONA DR screening compared to the standard fundus camera, the area under the curve, sensitivity, specificity, positive predictive value, negative predictive value, positive likelihood ratio, negative likelihood ratio, kappa agreement, diagnostic odds ratio, and diagnostic effectiveness were 99.74%, 100%, 99.81%, 99.33%, 100%, 528.00, 0.00, 0.99, infinity, and 99.85%, respectively. For MONA DME screening, these metrics were 97.97%, 100%, 98.95%, 85.93%, 100%, 95.67, 0.00, 0.81, infinity, and 99.02%, respectively. The MONA AI screening process required 1 day of training and approximately 5 min for image capture and analysis, compared to 7 days of training and 13 min for image acquisition and grading with the standard method. Conclusions: These findings demonstrate that the MONA.health AI software matches the accuracy of standard fundus photography for screening and early detection of referable DR and DME, while offering a faster, simpler, and more user-friendly workflow that significantly reduces the time to obtain screening results.

Background: Metabolic dysfunction-associated steatotic liver disease (MASLD), previously known as non-alcoholic fatty liver disease (NAFLD), is increasingly prevalent in children. However, reliable noninvasive diagnostic tools remain limited. The hepatorenal index (HRI) has been proposed as a quantitative ultrasound method to assess hepatic steatosis. This study aims to evaluate the diagnostic accuracy of HRI in detecting pediatric MASLD. Methods: A systematic review and meta-analysis were conducted on 13 September 2025, following PRISMA-DTA guidelines, with the protocol registered in PROSPERO (CRD420251146939). MEDLINE, PubMed, Cochrane Library, ScienceDirect, and Google Scholar were searched. Studies that assessed HRI against reference standards (MRI-PDFF or liver biopsy) in pediatric MASLD were included. Pooled diagnostic parameters were estimated using a bivariate random-effects model, with heterogeneity evaluated by I2 statistics and publication bias by funnel plot asymmetry. Results: Four studies involving 194 pediatric patients (47.9% MASLD), mostly male (57.7%), met the inclusion criteria. The suggested HRI cut-off varies from ≥1.215 to 1.99. The pooled sensitivity and specificity were 90% (95% CI 70-97) and 84% (95% CI 73-92), respectively, with an AUC of 0.91 (95% CI 0.88-0.93). Positive and negative likelihood ratios were 6 and 0.12, corresponding to post-test probabilities of 32% and 1%, respectively. No significant publication bias or heterogeneity was detected. Conclusions: Although HRI demonstrates strong diagnostic performance, it currently lacks sufficient discriminatory power to definitively confirm or exclude MASLD in pediatric populations and should therefore be regarded as a supportive rather than definitive diagnostic tool pending further high-quality validation studies.

Limited evidence exists on the predictive value of preoperative magnetic resonance cholangiopancreatography (MRCP) features of common bile duct stones (CBDS) for identifying post-endoscopic retrograde cholangiopancreatography pancreatitis (PEP). Radiomics texture analysis was performed using 3D Slicer software (version 5.0.3) and the least absolute shrinkage and selection operator (LASSO) algorithm. Model performance was evaluated using receiver operating characteristic (ROC) curves, decision curve analysis (DCA), and calibration plots. A total of 1690 patients who underwent ERCP at our center were enrolled, among whom 134 (7.93%) developed PEP. In the training cohort, the complex model, combining radiomics and clinical factors, exhibited optimal predictive value. It achieved an area under the curve (AUC) of 0.863 (95% CI: 0.825-0.901), a sensitivity of 0.847 (95% CI: 0.757-0.909), and a specificity of 0.743 (95% CI: 0.688-0.792). The positive and negative likelihood ratios were 3.296 and 0.206, respectively. In contrast, the radiomics model showed moderate performance (AUC, 0.813, 95%CI: 0.767-0.859), while the clinical risk model performed the lowest performance (AUC,0.736, 95%CI: 0.678-0.794). Similarly, in the testing cohort, the complex model outperformed both the radiomics model and the clinical risk model. DeLong's test highlighted significant differences among the three models. Furthermore, decision curve analysis (DCA) and calibration curves indicated that both the complex model and the radiomics model surpassed the clinical risk model in terms of clinical applicability and value. The radiomic features of CBDS are significant independent predictors of PEP. The model incorporating these radiomics features demonstrates strong performance for the clinical prediction of PEP.

Efficacy of Computed Tomography Calcium (CT Ca) Score as a Screening Tool for Coronary Artery Disease in Wait Listed Liver Transplant Recipients.

The ABCD2 score is a validated risk stratification tool used to quantify the risk of stroke within 48 hours among patients presenting with suspected transient ischemic attack (TIA). Limited data exist regarding its performance among patients in an emergency department observation unit (EDOU). The objective of this study was to determine the safety and efficacy of the ABCD2 score in a US EDOU cohort. We conducted an observational cohort study using the Wake Forest Emergency Medicine TIA Registry. Patients ≥18 years old who were evaluated for possible TIA in the EDOU of Atrium Health Wake Forest Baptist from July 1, 2021 to December 1, 2023 were accrued. This analysis included patients without a persistent neurologic deficit, except for amaurosis fugax, vertigo, or paresthesias, as determined by the consulting neurologist and attending emergency physician. Patients were risk-stratified using the ABCD2 score as low- (0-3), moderate- (4-5), and high- (≥6) risk for short-term stroke. The primary safety outcome was index encounter stroke, as determined by the consulting neurologist and imaging. Efficacy was defined as the proportion of patients classified to the low-risk group. Negative predictive values and positive predictive values, and negative likelihood ratios and positive likelihood ratios for the ABCD2 score were calculated for index stroke and reported with 95% confidence intervals (CI). Of the 340 EDOU TIA patients, 55.9% (190/340) were female, 27.9% (95/340) were nonwhite, and the mean age was 67.1 ± 13.6 years. During the index visit, 21.8% (74/340) were diagnosed with acute stroke. The ABCD2 score classified 45.0% (153/340) as low-, 45.6% (155/340) as moderate-, and 9.4% (32/340) as high-risk. Of those identified as low-risk, 17.7% (27/153) had an index acute stroke. Negative predictive values and negative likelihood ratios of the ABCD2 score for index stroke were 63.5% (95% CI, 53.3-72.6) and 0.7 (95% CI, 0.5-1.1). Among patients classified as high-risk, 34.4% (11/32) had an index stroke, corresponding to a positive predictive value of 34.4% (95% CI, 20.9-50.9) and a positive likelihood ratio of 1.9 (95% CI, 1.0-3.7). Although the ABCD2 score classified approximately half of patients as low-risk, nearly 20% of this group were diagnosed with an acute stroke during EDOU evaluation. These findings suggest that the ABCD2 score is not appropriate for ruling-out acute stroke among EDOU patients as it would lead to a high rate of missed strokes.

Spinal cord reactive-antibodies identified by serological antigen selection show prognostic value in traumatic spinal cord injury patients.

This is a protocol for a Cochrane Review (diagnostic). The objectives are as follows: The primary objective of this review is to determine the diagnostic accuracy of any form of ML algorithm for detecting ICH in participants who underwent hCT. We will assess diagnostic accuracy by individual and pooled indicators such as sensitivity and specificity with 95% confidence intervals, positive and negative likelihood ratios, and the summary receiver operating characteristic curve. Secondary objectives To investigate the following potential sources of heterogeneity in the diagnostic accuracy of ML: type of ML algorithm; year of development of the ML algorithm; certification of ML algorithm (Yes/No); type of reference standard; participant age (adults only/children only/mixed); hCT quality; hCT protocol; type of study (retrospective cohort study/prospective cohort study/RCT).

Objectives: Methicillin-resistant Staphylococcus aureus (MRSA) NAAT polymerase chain reaction (PCR) has been a valuable tool for de-escalating vancomycin, including for management of skin and soft tissue infections (SSTIs). Providers have reported instances where a negative MRSA NAAT has led to narrowing antibiotics, but the wound culture revealed MRSA growth. Previous research shows MRSA NAAT negative predictive value (NPV) for all SSTIs to be between 80% and 98.4%. In this study, we assessed the NPV of MRSA NAAT PCR to determine if it is lower for SSTIs than previously reported. Materials and Methods: Retrospective, single Center study evaluating 162 patients with diagnosis of SSTI between November 2022 and January 2025. Analyzed impact of data using sensitivity, specificity, positive predicative value (PPV), NPV, positive likelihood ratio, and negative likelihood ratio. Results: This population included most purulent infections ( n = 134, 82.7%) and patients with a diagnosis of cellulitis ( n = 65, 40.1%). Of the patients included in this study, 92 (56.8%) had a negative MRSA NAAT PCR with no MRSA growth, 37 (22.8%) had a positive MRSA NAAT PCR with MRSA growth, 15 (9.3%) had a negative MRSA NAAT PCR with MRSA growth, and 18 (11.1%) had a positive MRSA NAAT PCR with no MRSA growth. This data calculated a NPV of 86% (95% confidence interval [CI], 77.6–91.7%) and a PPV of 67.3% (95% CI, 53.2–79%). Conclusion: MRSA NAAT PCR testing is a valuable tool for de-escalation; however, other factors need consideration prior to de-escalation of vancomycin in the setting of SSTIs.

Background/Objectives: Age-related macular degeneration (AMD) is a leading cause of irreversible central vision loss in older adults. Detection of referable AMD-typically intermediate or advanced disease requiring specialist evaluation-is critical for timely intervention. Deep learning (DL) applied to color fundus photographs has emerged as a potential tool to support large-scale AMD screening. This systematic review and meta-analysis evaluated the diagnostic accuracy of DL algorithms for detecting referable AMD and compared their performance with human graders. Methods: We systematically searched PubMed, Embase, Web of Science, and IEEE Xplore through 18 December 2025. Diagnostic accuracy studies assessing DL algorithms on color fundus photographs for referable AMD in adults were included. Two reviewers independently screened studies, extracted data, and assessed risk of bias using an AI-adapted PROBAST framework. Pooled sensitivity and specificity were estimated using a bivariate random-effects model. Clinical utility was evaluated using likelihood ratios, and paired head-to-head comparisons were synthesized using a contrast-based meta-analysis. Results: Fourteen studies were included. DL algorithms achieved a pooled sensitivity of 0.91 (95% CI: 0.86-0.94) and specificity of 0.93 (95% CI: 0.86-0.96), with substantial heterogeneity. The pooled positive and negative likelihood ratios were 12.22 and 0.10, respectively, indicating strong diagnostic utility. In direct comparisons, DL systems showed slightly lower sensitivity but higher specificity than human graders. Conclusions: Deep learning demonstrates high diagnostic accuracy for detecting referable AMD from fundus photographs and may support screening and referral workflows. Further prospective validation and standardized evaluation are needed before widespread clinical implementation.

Background: Upper tract urothelial carcinoma (UTUC) is a rare malignancy with a poor prognosis. Current diagnostic methods such as ureteroscopic biopsy and imaging techniques are invasive, costly, or have low sensitivity. Urine-based biomarkers represent a promising non-invasive alternative. Objective: To systematically review and meta-analyze the diagnostic accuracy of various urine-based biomarkers for UTUC and provide a head-to-head comparison. Methods: A comprehensive literature search was conducted in PubMed, Scopus, Embase, Cochrane, and Web of Science from January 2000 to October 2025. Studies meeting PICOS criteria were included. Diagnostic performance metrics including sensitivity (SEN), specificity (SPE), positive likelihood ratio (PLR), negative likelihood ratio (NLR), diagnostic odds ratio (DOR), and area under the curve (AUC) were extracted. Data were synthesized using the MIDAS module in StataMP 18.0. Results: Seventeen studies involving 2734 patients were included. The overall pooled sensitivity was 0.86, specificity 0.94, diagnostic odds ratio 93, and AUC 0.94. DNA methylation assays showed balanced performance (SEN = 0.89, SPE = 0.92), gene mutation assays had the highest specificity (SPE = 0.97), RNA assays had the highest sensitivity (SEN = 0.97) but low specificity (SPE = 0.25). Significant heterogeneity was observed, but no notable publication bias was detected. Conclusions: Urine-based biomarkers demonstrate high diagnostic performance for UTUC, particularly DNA methylation assays. Future prospective studies are warranted to validate their clinical utility.

Incisional hernia (IH) is the most common long-term complication following open pancreatic surgery. This study aimed to evaluate the transportability of the Penn Hernia Risk Calculator (PHRC) Hepato-Pancreato-Biliary (HPB) model in a geo-temporally diverse population. Adult patients undergoing non-palliative pancreatic surgery via a transverse laparotomy from April 2012 to December 2023 at a single tertiary academic center were included. Patients with prior IH diagnosis and/or repair were excluded. Demographics, medical history, lab, and operative data were collected. Composite IH risk scores were calculated using the PHRC. Model performance was assessed using the Area Under the Receiver Operating Characteristic Curve (AUROC) and positive likelihood ratios (LR+) across risk thresholds. A total of 403 patients were included with 4.2% developing IH. The study population differed significantly from the PHRC cohort in 19 of 20 predictive variables. The overall AUROC was 0.548, and LR + values were consistently below 1.8 at all risk thresholds. Calibration plots indicated systematic overprediction of IH risk. Subgroup analysis showed improved performance (AUROC = 0.875, LR + = 0.467) among patients with BMI > 30kg/m². Malignancy was a protective factor, while undergoing left hemipancreatectomy or central pancreatectomy and BMI 20-30kg/m² were associated with IH development. In this small single-center cohort, the PHRC HPB model demonstrated poor accuracy in predicting early IH following pancreatic surgery through transverse laparotomy. Performance improved in obese patients, suggesting case-mix and outcome incidence differences may largely explain the lack of model transportability.

Radiomics for Detection of Pancreatic Cancer: A Systematic Review and Meta-Analysis.

Objective Impaired awareness of hypoglycemia (IAH) contributes to severe hypoglycemia (SH) in adults with type 1 diabetes mellitus (T1DM). This study compared the validity of the Gold, Clarke, and Pedersen-Bjergaard methods for predicting SH in Japanese adults with T1DM. Methods IAH was assessed at baseline using three methods, and a prospective cohort study was conducted in adults with T1DM. Multivariate Cox proportional hazards regression models adjusted for covariates were used to compare the three methods for predicting SH, and diagnostic validity was calculated. Patients We enrolled 286 participants (mean age: 50.5±14.6 years, men: 36.7%, diabetes duration: 17.6±11.1 years, mean HbA1c level: 7.7±0.9%). Results The prevalence of IAH identified using the Gold, Clarke, and Pedersen-Bjergaard methods was 12.2%, 19.2%, and 30.1%, respectively. The Clarke method showed the strongest association with SH [adjusted hazard ratio (aHR), 8.27; 95% confidence interval (CI), 3.43-20.0, p<0.001], whereas the Gold and Pedersen-Bjergaard methods had associations of aHR 1.90 (95% CI: 0.67-5.36, p=0.227) and aHR 2.65 (95% CI: 1.16-6.03; p=0.020), respectively. The Clarke method demonstrated 65.2% sensitivity, 84.8% specificity, a 27.3% positive predictive value, a 96.5% negative predictive value, a positive likelihood ratio of 4.29, a negative likelihood ratio of 0.41, and an overall diagnostic validity of 83.2%. Conclusion Among the three methods, the Clarke method demonstrated the highest validity for predicting SH development. This information may assist physicians in assessing IAH in clinical practice.

Accurate prediction of endometrial receptivity remains a key challenge in assisted reproductive technology (ART), with implantation failure often attributed to suboptimal endometrial conditions. This prospective observational study was conducted at the Department of Reproductive Medicine & Surgery, Kasturba Hospital, Manipal, between September 2024 and June 2025, to develop novel ultrasound-based scoring systems for predicting clinical pregnancy in frozen embryo transfer (FET) cycles. A total of 256 women aged 21–50 years undergoing FET with embryo(s) derived using their own gametes in natural, stimulated, or hormone replacement cycles were recruited, provided they had at least one good-quality embryo transferred. Patients with Müllerian anomalies or acquired intrauterine pathologies were excluded. Endometrial parameters including thickness, echogenicity, vascularity, peristalsis, uterine artery pulsatility index and 3D endometrial volume were evaluated on the day of FET using standardised ultrasonography. The primary outcome was clinical pregnancy, confirmed by visualisation of a gestational sac at six weeks. The study was registered with the Clinical Trials Registry – India (CTRI/2024/10/075117). The trial was approved on 11/10/2024. Of the 256 FETs, 103 resulted in clinical pregnancy (40.23%). Women who conceived had significantly greater endometrial volume (median 4.40 vs 3.60 mm³; p < 0.01), higher vascularity (74.8% vs 62.1%; p = 0.0417), and lower peristalsis (2 vs 3 waves/min; p = 0.0231) than those who did not conceive. Male factor infertility was more frequent in the pregnant than in the non-pregnant cohort (32.03% vs 10.45%; p < 0.01). Logistic regression confirmed endometrial volume, vascularity, and reduced peristalsis as independent predictors of pregnancy (p < 0.05). Three scoring systems were developed: the Total Screening Score (all predictors), the Targeted Endometrial Receptivity Score (volume, vascularity, peristalsis), and the Endometrial Volume Score. The Total Screening Score (≥14) offered the highest specificity (0.712) but poor sensitivity (0.097) and overall accuracy (0.464). The Targeted Score (≥7) achieved balanced performance, with sensitivity 0.631, specificity 0.621, accuracy 0.625, and the highest positive likelihood ratio (1.665). The Endometrial Volume Score (≥2) demonstrated the best sensitivity (0.796) and negative predictive value (0.727), serving as a strong screening tool, though limited by low specificity (0.366). This study introduces the first multiparametric ultrasound-based scoring framework for FET outcomes developed in the Indian context. The Targeted Endometrial Receptivity Score provides a balanced, reproducible tool for FET planning and patient counselling, while endometrial volume alone can serve as a rapid screening parameter. These systems offer a cost-effective, non-invasive approach to optimise FET outcomes, though validation in larger, multicentre cohorts is warranted.