Citations

Background: Mosquito-borne viral diseases are a growing global health threat, and artificial intelligence (AI) and machine learning (ML) are increasingly proposed as forecasting tools to support early-warning and response. However, the available evidence is fragmented across pathogens, settings and modelling approaches. This review provides, to the best of our knowledge, the first comprehensive comparative assessment of AI/ML models forecasting mosquito-borne viral diseases in human populations, jointly synthesising predictive performance across model families and appraising both methodological quality and operational readiness. Methods: Following PRISMA 2020, we searched PubMed, Embase and Scopus up to August 2025. We included studies applying AI/ML or statistical models to predict arboviral incidence, outbreaks or temporal trends and reporting at least one quantitative performance metric. Given the substantial heterogeneity in outcomes, predictors and time–space scales, we conducted a descriptive synthesis. Risk of bias and applicability were evaluated using PROBAST. Results: Ninety-eight studies met the inclusion criteria, of which 91 focused on dengue. The forecasts spanned national to city-level settings and annual-to-weekly resolutions. Across classification tasks, tree-ensemble models showed the most consistent performance, with accuracies typically above 0.85, while classical ML and deep-learning models showed wider variability. For regression tasks, errors increased with temporal horizon and spatial aggregation: short-term, fine-scale forecasts (e.g., weekly city level) often achieved low absolute errors, whereas long-horizon national models frequently exhibited very large errors and unstable performance. PROBAST assessment indicated that most studies (63/98) were at high risk of bias, with only 24 judged at low risk and limited external validation. Conclusions: AI/ML models, especially tree-ensemble approaches, show strong potential for short-term, fine-scale forecasting, but their reliability drops substantially at broader spatial and temporal scales. Most remain research-stage, with limited external validation and minimal operational deployment. This review clarifies current capabilities and highlights three priorities for real-world use: standardised reporting, rigorous external validation, and context-specific calibration.

Purpose of review TP53- mutated ( TP53 -MT) myeloid neoplasms (MN) represent one of the most challenging disease subsets due to their distinct pathobiology, frequent association with therapy-related disease, chemo-resistant phenotype, and dismal outcomes. The prognostic impact of TP53 -MT is not uniform and is influenced by disease state, allelic burden, and co-occurring cytogenetic and molecular aberrations that shape disease trajectory. While current prognostic models incorporate TP53 status, they incompletely capture the heterogeneity within TP53 -MT MN. Therapeutic options remain limited, with allogeneic stem cell transplantation being the only intervention offering long-term survival in selected patients. Recent findings Novel approaches, including p53 reactivators and anti-CD47 antibodies in combination with standard-of-care therapies, have been explored; however, none has yet transformed the natural history of TP53 -MT MN. Summary This review highlights the current understanding of TP53 -MT MN, evolving strategies of prognostic stratification and propose a practical framework for clinical management. We further discuss the critical unmet need for collaborative, biologically informed clinical trials to improve outcomes of this challenging disease entity.

Abstract Background Despite advancements in care, pregnant individuals with congenital heart disease (CHD) face disproportionately high risks. Objectives To address these challenges, a national consortium was established to improve maternal outcomes in CHD through multidisciplinary collaboration and patient engagement. Study design As part of a 2.5‐year multi‐phase consortium initiative, an in‐person research summit followed by three virtual focus groups (Project PHASE 3) was conducted with patients, clinicians, researchers, advocates, and policy representatives. Qualitative data were collected, and reflexive thematic analysis was performed to identify shared priorities. Results A total of 48 individuals participated in the in‐person meeting, including 18 patients (83% female; 11% Black/African American, 17% Asian, 11% Hispanic, 61% White) and 30 clinicians/researchers. An additional 19 patients (100% female; 32% rural/non‐urban; 16% Black/African American, 10% Hispanic, 74% White) participated in virtual focus groups. Key priorities identified included improved patient–healthcare provider communication, expanded access to multidisciplinary and adult CHD‐specialized care, and greater inclusion of patient voices in reproductive planning and research. Focus groups underscored racial disparities in care, limited CHD education for patients of color, and the need for culturally tailored resources. Participants emphasized the importance of representative research cohorts, integration of genetic counseling, and dissemination of research in accessible, plain‐language formats. Conclusions Findings demonstrate the value of integrating patient expertise and partnership in shaping cardio‐obstetric research, care models, and education. Addressing maternal health concerns in CHD research requires both structural changes and community‐driven, inclusive research strategies.

Erdheim-Chester disease (ECD) is a rare disease characterized by the accumulation of neoplastic histiocytes in various extra-nodal tissues. Tissue biopsies involved by ECD are difficult to distinguish from reactive inflammatory infiltrates given the bland appearance of the neoplastic histiocytes. Confirmation of the ECD diagnosis often relies on molecular studies to confirm BRAF V600E mutation or other activating mutations involving MAPK pathway genes. In this study, we examined the diagnostic utility of cyclin D1 and pERK as immunohistochemical markers of MAPK pathway activation in ECD compared with its histopathologic mimics. The cohort included 41 clinically confirmed ECD patients, most with known genetic alterations in MAPK pathway genes (n=38). In 3 cases no mutation was identified. 37 of 41 (90%) of ECD cases showed cyclin D1 overexpression, with frequent staining in the cytoplasm as well as the nucleus. pERK expression was observed in 32 of 39 (82%) cases. Cyclin D1 staining was negative in histopathologic mimics of ECD, apart from weak patchy staining in fat necrosis and uniform staining in a subset of cases of juvenile/adult xanthogranuloma. While not entirely sensitive or specific, in the proper clinical and radiologic context strong nuclear and cytoplasmic cyclin D1 expression within histiocytic infiltrates helps to support a diagnosis of ECD.

Abstract Cutaneous squamous cell carcinoma (cSCC) poses significant clinical challenges due to its rising incidence and potential for metastasis. Histopathologic risk stratification is further limited by substantial inter-observer variability. Unsupervised AI approaches based on content-based image retrieval offer scalable and interpretable decision support for diagnostic pathology. The objective of this study was to evaluate the use of image retrieval within histopathology atlases to stratify cSCC tumor differentiation from whole-slide images (WSIs), while comparing different patch selection and feature extraction strategies. This retrospective study included 552 archived WSIs comprising 385 well-differentiated, 102 moderately differentiated, and 66 poorly differentiated cases collected across Mayo Clinic sites in Arizona, Florida, and Minnesota. Image atlases were constructed using multiple patch aggregation strategies (Mosaic, Collage, and Montage) and deep learning encoders (KimiaNet, PathDino, and H-Optimus-0). A leave-one-WSI-out evaluation framework was used to assess differentiation classification performance using accuracy, specificity, sensitivity, and F1 score. Mosaic combined with KimiaNet achieved the highest Top-1 accuracy (74.9%) and specificity (92.6%), while Mosaic with H-Optimus-0 yielded the best Top-5 accuracy (79.0%) and macro-F1 score (62.6%). Collage combined with KimiaNet produced the highest Top-5 specificity (99.5%). The generalizability of the evaluated AI models varied across hospitals, reflecting differences in imaging protocols, staining practices, and patient populations. Overall, unsupervised image search and retrieval provides effective, annotation-free support for cSCC differentiation and has the potential to enhance dermatopathology workflows when appropriate combinations of patch selection and feature ex-traction methods are employed.

This study investigated the first multiomics data for association with tolerance to central hypovolemia in humans. Analyzing gene expression, proteins, and genetic variants in individuals with high and low tolerance to simulated hemorrhage, the findings show that severe blood loss causes widespread transcriptional changes, including the activation of innate immune system pathways and inhibition of gas transport processes. This research can help identify molecular factors that influence individuals’ tolerance levels for progressive blood loss.

Airway hyperreactivity and hASM cell proliferation (hyperplasia) are hallmark characteristics of asthma. The results of the present study showed that short-term exposure of nonasthmatic hASM to TNFα (a proinflammatory cytokine) can also induce hASM cell proliferation via activation of an ER stress pathway. Identification of the ER stress signaling pathway as important in mediating hASM hyperplasia may provide an important therapeutic target for treating asthma or acute inflammation.

Abstract The purpose of this study was to evaluate the incidence and outcomes of traumatic lunate fractures in a Level I trauma center over a 20-year period. Traumatic lunate fractures are rare, making it difficult to determine their frequency, outcomes, and patterns in clinical practice. A retrospective evaluation of 57 patients was conducted at a single institution from 2000 to 2022. Imaging studies, including radiographs, computed tomography, and magnetic resonance imaging, were reviewed to confirm traumatic etiology and fracture pattern. Fifty-seven lunate fractures met inclusion criteria: 11 were isolated and 46 had associated carpal fractures. Treatment included immobilization in 31 patients and surgery in 26. At a mean follow-up of 20.5 months (range, 2–186), average wrist flexion–extension range of motion was 90 degrees (range, 45–160), and grip strength averaged 26 kg (range, 6–48). Patient-reported outcomes were collected at a mean of 105 months (range, 12–226), with mean scores of 27 for the Disabilities of the Arm, Shoulder, and Hand, 19 for the Patient-Rated Wrist Evaluation, and 77 for the Mayo Wrist Score. Complications included 25 cases of posttraumatic arthritis, 2 cases each of avascular necrosis (AVN), nonunion, and complex regional pain syndrome, and 1 hardware infection. Posttraumatic arthritis was more frequently observed in patients with dorsal intercalated segment instability (DISI), age over 50 years, and displaced fractures. Lunate fractures occur in conjunction with greater arc injuries. Volar pole fractures were the most common fracture type observed. Predictors of long-term osteoarthritis included age over 50 years, DISI deformity, and displaced fractures at the time of diagnosis. Surgical fixation methods resulted in comparable outcomes. Two lunates progressed to AVN, both of which occurred following open operative fixation. Prognostic, Level IV

Abstract Column-type wrists, which exhibit increased scaphoid flexion during radial deviation, often experience greater loss of motion after periscaphoid arthrodesis compared with row-type wrists. Dynamic radiographic series are typically used to differentiate these kinematic patterns. In this study, we evaluate capitate morphology as a means of predicting column- or row-type carpal kinematics. This study investigated whether wrist kinematic patterns could be predicted using simple anteroposterior (AP) radiographs. We hypothesized that capitate morphology, given its close articulation with the scaphoid, influences these patterns. We analyzed 75 wrist motion radiographic series from 45 patients. Capitates were classified as either Type I (rectangular) or Type II (pentagonal) based on their shape. Wrist kinematic patterns were categorized as row- or column-type based on the degree of scaphoid length shortening during radial deviation. Our analysis revealed that a Type II capitate was a significant predictor of column-type wrists, with an odds ratio of 6.01 compared with Type I (p = 0.014). Furthermore, Type II capitates were associated with increased scaphoid flexion and reduced translation. Capitate morphology, as assessed from a plain AP radiograph, can serve as an easily accessible marker and reliable predictor of wrist motion patterns. This could potentially aid in surgical planning and patient counseling, particularly when dynamic radiographic series are not feasible. Diagnostic, Level III.