Search Results (1,390)

Background: With extensive research and development in the past decade, the affordability of Poly (ADP-ribose) polymerase (PARP) inhibitor therapy has drastically improved. Homologous recombination deficiency (HRD), a key biomarker, has been identified as an important guiding factor for PARP inhibitor therapeutic decisions in breast and ovarian cancer. However, identification of patients who will respond to Poly (ADP-ribose) polymerase (PARP) inhibitor therapy is challenging due to the lack of a unifying morphological phenotype. Current HRD testing via next-generation sequencing (NGS) is tissue-dependent, has high failure rates, misses relevant HRD genes, and involves longer turn-around times. Methods: To overcome these limitations, we developed a multimodal AI model, TRINITY, combining imaging, image-based transcriptome data, and clinico-molecular data, to examine whole-slide images (WSIs) obtained from hematoxylin and eosin (H&E)-stained samples to non-invasively predict HRD status. Results: The TRINITY model, tested on 316 TCGA breast and OV samples, presented a sensitivity of 0.77 and 0.91, NPV of 0.94 and 0.86, PPV of 0.63 and 0.58, specificity of 0.89 and 0.47, and AUC-ROC of 0.91 and 0.72, respectively. The model also yielded a similar outcome in a blind study of 74 samples, with a sensitivity of 81.2, NPV of 0.85, PPV of 0.77, specificity of 0.81, and high AUC-ROC value of 0.89, showing its promising preliminary evidence of predicting HRD status on external cohorts. Conclusions: These findings demonstrate TRINITY’s potential as a rapid, cost-effective, and tissue-sparing alternative to conventional NGS testing. While promising, further validation is needed to establish its generalizability across broader cancer types. Full article

Background: Colorectal cancer (CRC) is the second leading cause of cancer-related mortality worldwide, accounting for approximately 10% of all cancer cases. Despite the proven effectiveness of conventional screening modalities such as colonoscopy and fecal immunochemical testing (FIT), their invasive nature, high cost, and limited patient compliance hinder widespread adoption. Recent advancements in artificial intelligence (AI) and bowel sound-based signal processing have enabled non-invasive approaches for gastrointestinal diagnostics. Among these, bowel sound analysis—historically considered subjective—has reemerged as a promising biomarker using digital auscultation and machine learning. Objective: This review explores the potential of AI-powered bowel sound analytics for early detection, screening, and characterization of colorectal cancer. It aims to assess current methodologies, summarize reported performance metrics, and highlight translational opportunities and challenges in clinical implementation. Methods: A narrative review was conducted across PubMed, Scopus, Embase, and Cochrane databases using the terms colorectal cancer, bowel sounds, phonoenterography, artificial intelligence, and non-invasive diagnosis. Eligible studies involving human bowel sound-based recordings, AI-based sound analysis, or machine learning applications in gastrointestinal pathology were reviewed for study design, signal acquisition methods, AI model architecture, and diagnostic accuracy. Results: Across studies using convolutional neural networks (CNNs), gradient boosting, and transformer-based models, reported diagnostic accuracies ranged from 88% to 96%. Area under the curve (AUC) values were ≥0.83, with F1 scores between 0.71 and 0.85 for bowel sound classification. In CRC-specific frameworks such as BowelRCNN, AI models successfully differentiate abnormal bowel sound intervals and spectral patterns associated with tumor-related motility disturbances and partial obstruction. Distinct bowel sound-based signatures—such as prolonged sound-to-sound intervals and high-pitched “tinkling” proximal to lesions—demonstrate the physiological basis for CRC detection through bowel sound-based biomarkers. Conclusions: AI-driven bowel sound analysis represents an emerging, exploratory research direction rather than a validated colorectal cancer screening modality. While early studies demonstrate physiological plausibility and technical feasibility, no large-scale, CRC-specific validation studies currently establish sensitivity, specificity, PPV, or NPV for cancer detection. Accordingly, bowel sound analytics should be viewed as hypothesis-generating and potentially complementary to established screening tools, rather than a near-term alternative to validated modalities such as FIT, multitarget stool DNA testing, or colonoscopy. Full article

Background: Evidence guiding secondary repair of persistent full-thickness macular holes (FTMHs) remains limited and heterogeneous. Temporal arcuate relaxing retinotomy has been described as a salvage maneuver intended to increase temporal retinal compliance, yet functional safety data are scarce. We report consecutive real-world outcomes of temporal arcuate relaxing retinotomy for persistent FTMHs after failed standard repair(s). Methods: Retrospective consecutive case series of patients with persistent FTMH after ≥1 pars plana vitrectomy (PPV) with internal limiting membrane (ILM) peeling, treated with repeat PPV and temporal arcuate relaxing retinotomy. Outcomes included OCT (Optical Coherence Tomography)-confirmed closure after gas absorption and best-corrected visual acuity (BCVA, logMAR), ellipsoid zone (EZ) status, retinotomy-site morphology on OCT/fundus autofluorescence (FAF), and safety/functional outcomes (systematic scotoma symptom inquiry; Humphrey visual field testing when feasible). Exact binomial 95% confidence intervals (CI) were calculated for proportions. Results: Nine eyes (median age 70 years; range 55–76) underwent temporal arcuate relaxing retinotomy for persistent FTMH. Minimum linear diameter ranged 412–1037 µm (median 613 µm). OCT-confirmed closure was achieved in 7/9 eyes (77.8%; 95% CI 40.0–97.2) at a mean follow-up of 5.9 months (range 2–12). BCVA improved in 8/9 eyes (88.9%; 95% CI 51.8–99.7); mean BCVA improved from 1.26 ± 0.51 logMAR pre-operatively to 0.61 ± 0.18 logMAR at last follow-up (mean change −0.64 logMAR; Wilcoxon signed-rank test p = 0.011). As a sensitivity analysis, the paired t-test yielded p = 0.008. Humphrey visual fields were obtained in 6/9 eyes; one patient reported a new paracentral nasal scotoma, which was subjectively well tolerated. Conclusions: In this small consecutive series, temporal arcuate relaxing retinotomy was associated with a 78% closure rate and mean BCVA improvement in eyes with persistent FTMH after failed standard repair(s), with limited symptomatic scotoma reporting in those assessed. Given the retrospective design, small cohort, and incomplete standardized functional testing, larger comparative studies with uniform functional endpoints (microperimetry, RNFL/GCL metrics, and systematic perimetry) are needed to define patient selection, reproducibility, and relative performance versus contemporary salvage options. Full article

Background/Objectives: Septic arthritis of native joints is an orthopedic emergency in which rapid discrimination from non-infectious arthritis is crucial. Because cartilage damage can occur within hours, urgent irrigation and debridement are often pursued on an emergency basis (ideally within the first 6–8 h) of presentation, underscoring the need for rapidly available biomarkers. The delta neutrophil index (DNI) quantifies circulating immature granulocytes and may complement conventional inflammatory biomarkers such as C-reactive protein (CRP), erythrocyte sedimentation rate (ESR), white blood cell count (WBC), and procalcitonin (PCT). We evaluated the diagnostic performance of DNI for native-joint septic arthritis against both microbiologic and clinical reference standards. Methods: We retrospectively analyzed 85 adults who underwent surgical irrigation and debridement for suspected native joint septic arthritis at a tertiary center. Serum CRP, ESR, WBC, DNI, and PCT (available in 67 patients) were recorded together with synovial leukocyte counts. Infection status was defined using either positive synovial culture (microbiologic reference) or clinical adjudication according to the Guideline for management of septic arthritis in native joints (SANJO). Diagnostic performance was assessed using receiver operating characteristic (ROC) curves and the area under the ROC curve (AUC); exploratory cut-offs were identified by the Youden index, and pairwise AUCs were compared using DeLong’s test. Results: Synovial leukocyte analysis was highly sensitive but poorly specific (sensitivity 92.9%, specificity 10.3%). Against culture, DNI showed the highest discrimination (AUC = 0.914), exceeding CRP (0.687), ESR (0.643), WBC (0.648), and PCT (0.697); DeLong ΔAUC vs. CRP 0.227 (p < 0.001), ESR 0.270 (p < 0.001), WBC 0.266 (p < 0.001), PCT 0.227 (p = 0.001). At pre-specified cut-offs, DNI showed the most balanced sensitivity/specificity (94.3%/84.0%), corresponding to a negative predictive value (NPV) of 95.5% (42/44) and a positive predictive value (PPV) of 80.5% (33/41) against culture in this cohort. Against clinical infection, DNI outperformed others (AUC:0.921; ΔAUC vs. CRP = 0.204, ESR = 0.343, WBC = 0.244, PCT = 0.295; all p < 0.001). As a rule-in threshold, DNI ≥ 0.6 yielded a specificity of 100% with a sensitivity of 73.2%. In culture-negative patients (infected n = 21, uninfected n = 29), DNI remained discriminatory (AUC 0.80, p < 0.001), whereas other biomarkers were not. Conclusions: DNI demonstrated superior diagnostic accuracy compared with conventional inflammatory biomarkers. As a rapid parameter available with the initial complete blood count, DNI may support early risk stratification and rule-in decisions within the first hours of presentation; however, it should be used as a supplementary indicator alongside synovial fluid analysis and clinical assessment rather than as a stand-alone diagnostic tool. Full article

Between 2015 and 2022, we evaluated a novel broad-range (BR) 16S PCR rDNA PCR/Sanger sequencing assay to improve diagnosis of invasive infections in culture-negative specimens. Using dual-priming oligonucleotides (DPO), this assay analyzed ribosomal DNA from sterile fluids or tissues. A total of 762 specimens were analyzed from 661 patients: 61% had negative cultures and BR 16S PCR tests; 35% had negative cultures but positive BR 16S PCR tests; and only 4% had negative cultures with indeterminate BR 16S PCR results. After resolution of indeterminate BR 16S PCR results (i.e., 29 negative, 1 false-positive, and 1 positive) the assay showed a sensitivity of 98.26% (95% CI = 96.00–99.43%), specificity of 99.79% (95% CI: 99.82–99.99%), positive predictive value of 99.65% (95% CI: 97.56–99.95%), negative predictive value of 98.94% (95% CI: 97.51–99.55%), and accuracy of 99.21% (95% CI: 98.28–99.71%) for a disease prevalence of 38.10% (95% CI: 34.62–41.66%). Gram stain purulence predicted the BR 16S PCR result better (69.4%) than organisms (24.6%), but the latter had a higher PPV (78.5%). Increased peripheral WBC (86.1%) or CRP (71.8%) predicted positive BR 16S PCR results. Our DPO BR 16S PCR assay improved pathogen detection over culture and minimized contamination. Broad range 16S rDNA PCR/sequencing (BR 16S PCR) is an important diagnostic technique in cases with invasive infection due to fastidious or uncultivatable pathogens. However, appropriate case selection, the quality of clinical specimen, and the specific assay primers affect its performance. Our novel BR 16S PCR assay uses unique dual-priming oligonucleotides (DPO) primers and fast protocols for rapid, optimal detection of bacterial pathogens, while minimizing contamination. Fast BR 16S PCR assay reports occurred within 24–48 h. BR 16S PCR and culture analyzed a diverse range of clinical specimens from patients with invasive infections. BR 16S PCR demonstrated a high performance for accurately detecting pathogens, ruling out infections, and minimizing contamination. BR 16S PCR detection of a pathogen allowed the appropriate clinical management of one-third of patients in this cohort. BR 16S PCR is an essential tool for the clinical management of patients with invasive infection when primary cultures are negative or contaminated. Full article

Background: The persistently low 5-year survival rate for pancreatic cancer (PC) underscores the critical need for early detection. However, population-wide screening remains impractical. Artificial Intelligence (AI) models using electronic health record (EHR) data offer a promising avenue for pre-symptomatic risk stratification. Objective: To systematically review and meta-analyze the performance of AI models for PC prediction based exclusively on structured EHR data. Methods: We systematically searched PubMed, MedRxiv, BioRxiv, and Google Scholar (2010–2025). Inclusion criteria encompassed studies using EHR-derived data (excluding imaging/genomics), applying AI for PC prediction, reporting AUC, and including a non-cancer cohort. Two reviewers independently extracted data. Random-effects meta-analysis was performed for AUC, sensitivity (Se), and specificity (Sp) using R software version 4.5.1. Heterogeneity was assessed using I² statistics and publication bias was evaluated. Results: Of 946 screened records, 19 studies met the inclusion criteria. The pooled AUC across all models was 0.785 (95% CI: 0.759–0.810), indicating good overall discriminatory ability. Neural Network (NN) models demonstrated a statistically significantly higher pooled AUC (0.826) compared to Logistic Regression (LogReg, 0.799), Random Forests (RF, 0.762), and XGBoost (XGB, 0.779) (all p < 0.001). In analyses with sufficient data, models like Light Gradient Boosting (LGB) showed superior Se and Sp (99% and 98.7%, respectively) compared to NNs and LogReg, though based on limited studies. Meta-analysis of Se and Sp revealed extreme heterogeneity (I² ≥ 99.9%), and the positive predictive values (PPVs) reported across studies were consistently low (often < 1%), reflecting the challenge of screening a low-prevalence disease. Conclusions: AI models using EHR data show significant promise for early PC detection, with NNs achieving the highest pooled AUC. However, high heterogeneity and typically low PPV highlight the need for standardized methodologies and a targeted risk-stratification approach rather than general population screening. Future prospective validation and integration into clinical decision-support systems are essential. Full article

Background: Molecular testing is recommended to refine risk stratification in indeterminate thyroid nodules (Bethesda III–IV), but data on dual-gene (BRAF and RAS) testing using fresh FNA washout specimens are limited. We aimed to evaluate the performance of BRAF and RAS mutation analysis from fresh thyroid FNA washout material, with a focus on indeterminate cytology. Methods: We retrospectively analyzed 1139 patients who underwent washout-based molecular testing between May 2022 and October 2024 at a tertiary endocrine center. Of these, 307 had available histopathologic results after surgery. Primary outcomes were sample adequacy, mutation spectrum, and diagnostic metrics (sensitivity, specificity, PPV, NPV, and accuracy). Analyses were repeated under two assumptions that classified borderline/low-risk neoplasms as benign vs. malignant, and within the Bethesda III–IV subset. Results: Adequate material for molecular analysis was obtained in 1037/1139 samples (90.9%). In the operated cohort (n = 307), malignant lesions comprised 31.9% and low-risk neoplasms 8.5%. When borderline lesions were considered benign, mutation positivity yielded a sensitivity of 48.0%, a specificity of 89.6%, a PPV of 75.9%, an NPV of 71.9%, and an accuracy of 72.9%. In Bethesda III–IV nodules (n = 153), sensitivity, specificity, and accuracy were 41.0%, 85.2%, and 66.0% (malignant assumption). Isolated BRAF positivity showed high specificity (~96.7%) with modest sensitivity. Conclusions: Our findings extend current diagnostic approaches by showing that dual-gene (BRAF and RAS) testing from fresh FNA washouts is technically feasible (≥90% adequacy) and provides high specificity with modest sensitivity for malignancy in indeterminate nodules. In settings lacking comprehensive commercial panels, this low-complexity approach offers a practical adjunct to cytology and imaging for preoperative decision-making. Full article

Background/Objectives: Keratoconus, a condition in which the cornea becomes thinner and steeper, can cause visual problems, particularly when it is progressive. Early diagnosis is important for preserving visual acuity. Raw data, unlike preprocessed data, are unaffected by software modifications. They retain their native structure across versions, providing consistency for analytical purposes. The objective of this study was to design a deep learning-based graphical user interface for predicting the corneal ectasia score using raw optical coherence tomography data. Methods: The graphical user interface was developed using Tkinter, a Python library for building graphical user interfaces. The user is allowed to select raw data from the cornea/anterior segment optical coherence tomography Casia2, which is generated in the 3dv format, from the local system. To view the predicted corneal ectasia score, the user must determine whether the selected 3dv file corresponds to the left or right eye. Extracted optical coherence tomography images are cropped, resized to 224 × 224 pixels and processed by the modified EfficientNet-B0 convolutional neural network to predict the corneal ectasia score. The predicted corneal ectasia score value is displayed along with a diagnosis: ‘No detectable ectasia pattern’ or ‘Suspected ectasia’ or ‘Clinical ectasia’. Performance metric values were rounded to four decimal places, and the mean absolute error value was rounded to two decimal places. Results: The modified EfficientNet-B0 obtained a mean absolute error of 6.65 when evaluated on the test dataset. For the two-class classification, it achieved an accuracy of 87.96%, a sensitivity of 82.41%, a specificity of 96.69%, a PPV of 97.52% and an F1 score of 89.33%. For the three-class classification, it attained a weighted-average F1 score of 84.95% and an overall accuracy of 84.75%. Conclusions: The graphical user interface outputs numerical ectasia scores, which improves other categorical labels. The graphical user interface enables consistent diagnostics, regardless of software updates, by using raw data from the Casia2. The successful use of raw optical coherence tomography data indicates the potential for raw optical coherence tomography data to be used, rather than preprocessed optical coherence tomography data, for diagnosing keratoconus. Full article

The rapid construction and commissioning of battery energy storage system (BESS) installations, both standalone and combined with photovoltaic power plants (PVPPs), is rapidly reshaping the energy market. Mapping these latest iterations in the energy infrastructure allows for a detailed analysis of the effects they have on the grid, in correlation with the already abundant operational PPV. This paper will provide a list of all BESS installations commissioned between 1 January and 30 September 2025. Taking into consideration their grid-connection power, and respective battery capacity, along with their geographical location and co-located (or lack thereof) PVPPs, the following-up analysis aims to answer several key questions: how do these installations compare to one another in terms of power, capacity and distribution across Bulgaria; how do they affect the availability of electric power from PVPP, co-located or not, to the end consumers; and how does that shift in availability affect the profits, both for the BESS and PVPP owners, based on the shifting price of electricity? Full article

Background/Objectives: Early and accurate characterization of endometrial cancer (EC) is crucial for patient management, but current imaging modalities lack in diagnostic accuracy and ability to assess molecular profiles. The aim of this study is to evaluate hybrid [¹⁸F]FDG PET/MRI’s diagnostic accuracy in EC staging and role in predicting tumor aggressiveness, molecular characterization, and recurrence. Methods: A prospective study (ClinicalTrials.gov, ID:NCT04212910) evaluating EC patients undergoing [¹⁸F]FDG PET/MRI before surgery (2018–2024). Histology, immunohistochemistry, and patients’ follow-up (mean FU time: 3.13y) were used as the reference standard. [¹⁸F]FDG PET/MRI, PET only, and MRI only were independently reviewed to assess the diagnostic accuracy (ACC), sensitivity (SN), specificity (SP), and positive/negative predictive value (PPV, NPV). Imaging parameters were extracted from [¹⁸F]FDG PET and pcT1w, T2w, DWI, and DCE MRI. Spearman’s correlations, Fisher’s exact test, ROC-AUC analysis, Kaplan–Meier survival curves, log-rank tests and Cox proportional hazards models were applied. Results: Eighty participants with primary EC (median age 63 ± 12 years) were enrolled, with 17% showing LN involvement. [¹⁸F]FDG PET/MRI provided ACC = 98.75%, SN = 98.75%, and PPV = 100% for primary tumor detection, and ACC = 92.41%, SN = 84.62%, SP = 93.94%, PPV = 73.33%, and NPV = 96.88% for LN detection. PET/MRI parameters predicted LN involvement (AUC = 79.49%), deep myometrial invasion (79.78%), lymphovascular space invasion (82.00%), p53abn (71.47%), MMRd (74.51%), relapse (82.00%), and postoperative administration of adjuvant therapy (79.64%). Patients with a tumor cranio-caudal diameter ≥ 43 mm and MTV ≥ 13.5 cm³ showed increased probabilities of recurrence (p < 0.001). Conclusions: [¹⁸F]FDG PET/MR showed exceptional accuracy in EC primary tumor and LN detection. Derived parameters demonstrated potential ability in defining features of aggressiveness, molecular alterations, and tumor recurrence. Full article

Background/Objectives: The iBreast Exam (iBE) electronically palpates the breast to identify possible abnormalities. The purpose of this study was to assess iBE feasibility and compare it to Clinical Breast Exam (CBE) for breast lesion detection. Methods: Prospective evaluation of 300 asymptomatic women, ≥18 years old, with CBE, iBE, and mammography was performed. Sensitivity, specificity, positive predictive values (PPV), and negative predictive values (NPV) of iBE and CBE for detecting suspicious breast lesions were calculated using breast imaging as the reference standard. For women with one year follow up, the sensitivity, specificity, PPV, and NPV for cancer detection were calculated. Results: 300 women (mean age 58.9 years) underwent CBE, iBE, and mammography. In 2/300 (0.7%), CBE was positive; in 1/300 (0.3%), iBE was positive; and in 24/300 (8%), screening mammograms were positive. Nine had suspicious imaging findings with biopsy (three malignant and six benign). Of three cancers, all visualized mammographically, CBE and iBE detected an ipsilateral breast abnormality in one woman and missed two cancers (<2 cm). Sensitivity, specificity, NPV, and PPV of iBE and CBE were similar, with no statistically significant difference in NPV or PPV for detection of suspicious breast findings or breast cancer (p > 0.05). Conclusions: Mammography detected all breast cancers in our cohort and remains the standard of care. iBE is feasible to perform. Our pilot data demonstrates iBE performed similarly to CBE by trained nurse practitioners. Given our small study population, further investigation is warranted into the potential use of iBE where trained healthcare practitioners are not readily available. Full article

Background: Urine cytology remains widely used for surveillance of non-muscle-invasive bladder cancer despite well-known limitations in sensitivity, especially for low-grade tumors. Uromonitor^®, a molecular assay detecting TERT promoter, FGFR3, and KRAS mutations in voided urine, has emerged as a promising adjunct. To evaluate its suitability for routine use, a consolidated assessment of diagnostic performance and a direct comparison with urine cytology are needed. Methods: We conducted a prospectively registered systematic review (PROSPERO CRD420251173244), synthesizing all available studies that evaluated Uromonitor^® for the detection of urothelial carcinoma of the bladder (UCB). Methodological quality was assessed using the QUADAS-2 framework, and certainty of evidence was evaluated following GRADE for diagnostic tests. Sensitivity was prespecified as the primary endpoint. Comparative datasets were identified, and random-effects meta-analyses were performed for sensitivity, specificity, accuracy, and predictive values (PVs). Results: Across eight cohorts evaluating Uromonitor^®, 832 of 3196 patients (26.0%) had histologically confirmed UCB. Aggregated sensitivity was 0.55 (95% CI 0.52–0.58). Specificity was 0.95 (0.94–0.96). Accuracy was 0.85 (0.83–0.86). PPV was 0.79 (0.76–0.82), and NPV was 0.86 (0.84–0.87). Across seven paired datasets, urine cytology demonstrated a sensitivity of 0.42, a specificity of 0.91, an accuracy of 0.78, a PPV of 0.64, and an NPV of 0.81. Pooled odds ratio for sensitivity was 3.16 (0.73–13.76), while diagnostic accuracy yielded 1.71 (1.01–2.90). Differences in specificity and NPV were not statistically significant, whereas the PPV favored Uromonitor^®, reaching statistical significance in pooled analyses. Conclusions: Uromonitor^® demonstrates higher sensitivity and improved accuracy compared with urine cytology, although current performance remains insufficient for stand-alone surveillance. The sensitivity estimate showed very low certainty due to pronounced heterogeneity, underscoring the need for careful interpretation. With advancing DNA recovery methods, incorporation of droplet digital PCR, and rigorous evaluations in prospective multicenter studies, Uromonitor^® may become an integral element of risk-adapted follow-up strategies. Full article

Blast-induced vibrations from newly constructed tunnels may adversely affect adjacent existing tunnel structures. To ensure the safety of the existing tunnel, it is essential to investigate its dynamic response under blast disturbances. Based on an expansion project for a highway double-arch tunnel, this study employed the dynamic finite element program LS-DYNA to analyze the vibration velocity and effective stress in the tunnel lining subjected to blast vibrations. The distribution characteristics of vibration velocity and effective stress at different locations of tunnel lining were obtained. A relationship model between the peak particle velocity (PPV) and effective stress was established. According to the maximum tensile stress theory, a safety criterion based on vibration velocity was determined. To facilitate field monitoring, a correlation between the vibration velocity at the arch waist and foot was established, leading to a proposed safety threshold for the arch foot vibration velocity. Furthermore, a statistical relationship was developed between the charge weight per hole in the upper bench cut and the vibration velocity at the arch foot to guide blasting design. Using the arch foot vibration velocity as the safety standard, the maximum permissible charge weight to ensure the structural safety of the existing tunnel was recommended. Full article

Background/Objectives: Intracranial hemorrhage (ICH) is a life-threatening condition that can be rapidly detected by non-contrast head computed tomography (NCCT). RAPID ICH is a deep learning (DL) tool for automatic ICH identification using NCCT. Our aim was to assess the real-world performance of RAPID ICH compared to that of a first-year radiology resident on consecutively acquired NCCTs from patients referred from the Emergency Department. Methods: This single-center retrospective cohort study included NCCTs acquired on the same CT scanner over three months. Exclusion criteria were motion or metallic artifacts that substantially degraded the NCCT quality and incomplete NCCTs. Two senior neuroradiologists conducted ground-truth labeling of the NCCTs regarding ICH presence in a binary manner. The first-year radiology resident assessed NCCTs for ICH presence and was blinded to the ground-truth labeling. Sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were computed for the RAPID ICH identifications and for the first-year radiology resident’s ICH identifications. Results: After applying exclusion criteria, 844 NCCTs remained. Ground-truth labeling found ICH in 63 NCCTs. RAPID ICH showed 87.3% sensitivity, 74% specificity, 21.3% PPV, and 98.6% NPV, while the first-year radiology resident achieved 95.2% sensitivity, 90.8% specificity, 45.5% PPV, and 99.6% NPV. There were 8 false-negative and 203 false-positive RAPID ICH identifications. Conclusions: RAPID ICH’s sensitivity and specificity were lower than in prior studies performed using RAPID ICH, and there was a high number of false-positive RAPID ICH identifications, limiting the generalizability of the assessed version of this DL tool. Testing DL tools by comparing them with radiologists of varying experience can provide valuable insights into their performance. Full article

Poultry price instability remains a critical challenge for food security in Nigeria. This study examines the relationship between poultry price volatility (PPV), exchange rate (LEXR), and inflation (LCPI) from 1991 to 2024 using the Autoregressive Distributed Lag (ARDL) model. Descriptive results show that PPV had the highest variability (mean 0.65; standard deviation 1.07), while LEXR and LCPI were relatively more stable. Trend analysis indicates that poultry price volatility was high in the early 1990s but declined steadily after 2005, coinciding with persistent inflation and cycles of exchange rate depreciation and appreciation.Unit root and bounds tests confirm that the variables werecointegrated, with an F-statistic of 4.50 exceeding the upper bound at 5 percent significance. The long-run estimates reveal that inflation hada negative effect on poultry price volatility (−0.109), while the exchange rate exerteda positive effect (0.2702). The errorcorrection term (−0.336) indicates a 33.6 percent adjustment to equilibrium each period. In the short run, changes in inflation (0.942) and lagged exchange rate variations significantly influenced poultry price volatility. These findings underscore the importance of stabilizing exchange rates and controlling inflation to reduce price volatility in Nigeria’s poultry sector. Full article