Citations

OBJECTIVES: This systematic review evaluates artificial intelligence (AI)-based predictive models developed for early sepsis detection in adult hospitalized patients. It explores model types, input features, validation strategies, performance metrics, clinical integration, and implementation challenges. DATA SOURCES: A systematic search was conducted across PubMed, Scopus, Web of Science, Google Scholar, and CENTRAL for studies published between January 2015 and March 2025. STUDY SELECTION: Eligible studies included those developing or validating AI models for adult inpatient sepsis prediction using electronic health record data and reporting at least one performance metric (area under the curve [AUC], sensitivity, specificity, or F1 score). Studies focusing on pediatric populations, lacking quantitative evaluation, or unpublished in peer-reviewed journals were excluded. DATA EXTRACTION: Data extraction followed preferred reporting items for systematic reviews and meta-analyses guidelines. Extracted variables included study design, patient population, model type, input features, validation approach, and performance outcomes. DATA SYNTHESIS: A total of 52 studies met the inclusion criteria. Most used retrospective designs, with limited prospective or real-time clinical validation. Commonly used algorithms included random forests, neural networks, support vector machines, and deep learning architectures (long short-term memory, convolutional neural network). Input data varied from structured sources (vital signs, laboratory values, demographics) to unstructured clinical notes processed via natural language processing. Reported AUC values ranged from 0.79 to 0.96, indicating strong predictive performance across models. CONCLUSIONS: AI models demonstrate significant promise for early sepsis detection, outperforming conventional scoring systems in many cases. However, generalizability, interpretability, and clinical implementation remain major challenges. Future research should emphasize externally validated, explainable, and scalable AI solutions integrated into real-time clinical workflows.

Background. As cancer therapeutics improve, more liver transplant (LT) candidates will have a history of prior to transplant malignancy (PTM), an established risk for cancer posttransplant. Methods. This study provides granular analysis (with focus on nonliver PTM) of posttransplant cancer risk relating to PTM in 1105 consecutive adult LT recipients (2009–2019, N = 542 with PTM). Results. PTM prevalence increased from 37.8% to 63.2% during this timeframe. Post-LT survival was lower (10 y: 61.2% versus 75.1%; P < 0.001) with higher cancer-related mortality (17.6% versus 2.2%; P < 0.001) in patients with any PTM. The higher cumulative incidence of cancer post-LT associated with PTM (59.7% versus 37.6%; P < 0.001) was not attributable to de novo cancer (38.5% versus 37.7%; P = 0.21) but to recurrence. Cancer recurrence rate (10 y) was lowest in nonliver/nonskin (“other”) PTM (10.6%) with mortality rates from recurrence of only 4% in this cohort. De novo cancers may present at more advanced stage in patients with PTM and lung cancer the most common nonskin de novo malignancy (PTM 21%, no PTM 7%). Family history of cancer was an independent predictor for de novo cancer. Conclusions. PTM associated post-LT cancer outcomes are dominated by skin and liver cancer recurrence and not recurrence of “other” cancers or de novo cancer. This data supports the guidance proposals for cautious liberalization of “other” cancer remission requirements before transplantation. As post-LT cancer is highly prevalent regardless of PTM status, adherence to posttransplant cancer screening and surveillance is critical to identify early cancer after transplant.

Abstract Hematologic malignancies are associated with an increased risk of venous thromboembolism (VTE) with aggressive lymphomas and multiple myeloma exhibiting the highest VTE incidence. The performance of VTE risk scores in hematologic malignancies remains suboptimal. Concomitant thrombocytopenia and coagulopathies complicate thrombosis prevention and management. This review synthesizes current evidence on anticoagulation in hematologic malignancies (excluding myeloproliferative neoplasms), outlines key clinical challenges, and proposes practical strategies to guide decision-making.

Abstract POEMS (polyneuropathy, organomegaly, endocrinopathy, M protein, skin changes) syndrome is a complex paraneoplastic syndrome related to a lambda-restricted low–tumor burden neoplasm. The diagnosis must be considered in the context of what might otherwise be believed to be a “monoclonal gammopathy of undetermined significance,” with unusual features including, but not limited to, peripheral neuropathy, thrombocytosis, and extracellular volume overload. Once a diagnosis of POEMS syndrome is made, besides very specific supportive care, the treatments resemble those of multiple myeloma or solitary plasmacytoma of the bone. Based on case series, autologous stem cell transplant is still a favored therapy with durable remissions even without maintenance therapy. Even before the era of therapeutic monoclonal antibodies, bispecific T-cell engagers, and chimeric antigen receptor antibodies, 10-year overall survival approached 80%. Patients achieving a complete hematologic response have a progression-free survival of 88% even without maintenance therapy. Herein, a case of a patient with a less-than-average outcome is described to highlight some of the long-term challenges and complexities of managing patients with POEMS syndrome.

Abstract Atherosclerotic cardiovascular disease (ASCVD) encompasses a spectrum of vascular conditions, including coronary artery disease (CAD) and lower extremity peripheral artery disease (PAD), which frequently coexist. In the setting of ASCVD, there is a common underlying pathophysiology for acute ischemic events related to platelet activation and thrombin generation. The scope of this review focuses on the role of dual-pathway inhibition, the approach combining antiplatelet and antithrombotic therapy, for improvement in cardiovascular outcomes in patients with ASCVD. To determine which patients with CAD and PAD may benefit from dual-pathway inhibition, a brief overview of clinical presentations for both stable CAD and the spectrum of lower extremity PAD is outlined.

Abstract Histiocytic neoplasms with xanthogranulomatous morphology encompass a continuum of disorders—from isolated cutaneous juvenile xanthogranuloma (JXG) or adult xanthogranuloma (AXG) to the multisystem Erdheim-Chester disease (ECD)—that share overlapping histopathologic and molecular features. In this article, we (1) define the spectrum of xanthogranuloma lesions, highlighting morphologic and immunohistochemical commonalities; (2) examine the clinical and radiographic criteria that distinguish localized juvenile xanthogranuloma/adult xanthogranuloma from classical Erdheim-Chester disease and related entities; (3) review the latest insights into MAPK pathway alterations that blur traditional diagnostic boundaries; and (4) outline contemporary management strategies, including approaches to staging “occult” disease, patient selection for BRAF and MEK inhibitors, and the role of other targeted and nontargeted agents. Readers will gain practical frameworks for recognizing early or atypical presentations, integrating molecular testing into routine practice, and optimizing personalized therapy across the xanthogranuloma family.

Abstract JAK2 unmutated/wild-type erythrocytosis is a prevalent condition encompassing a wide spectrum of hereditary and acquired entities. It is conventionally defined by the same hemoglobin/hematocrit thresholds as for polycythemia vera. Incidence has been reported to be between 0.13% and 4.1%. The most clinically relevant step in the workup of erythrocytosis is the exclusion of polycythemia vera through JAK2 mutation screening. Consideration of relative polycythemia, normal outliers, and the influence of erythropoietic drugs and comorbidities is also imperative. Distinguishing long-standing from newly acquired erythrocytosis further streamlines the diagnostic process. Hereditary erythrocytosis (HE) is lifelong and typically associated with a positive family history. Subnormal serum erythropoietin (EPO) suggests an EPO receptor mutation. Otherwise, oxygen tension at 50% hemoglobin saturation (p50) discerns between high oxygen-affinity hemoglobin variants, 3-bisphosphoglycerate deficiency, methemoglobinemia, and PIEZO1 mutations (low p50) and germline oxygen-sensing pathway/other rare mutations (normal p50). Acquired erythrocytosis results from hypoxia-driven factors (eg, cardiopulmonary, altitude, renal artery stenosis) and other mechanisms of EPO overproduction (eg, EPO-secreting tumors) or hypersensitivity, as well as EPO-independent mechanisms. Drugs (eg, sodium glucose co-transporter-2 inhibitors, testosterone) are also common causes. Idiopathic erythrocytosis is a diagnosis of exclusion, increasingly attributed to underlying genetic mutations/polymorphisms. There are currently no evidence-based treatment guidelines. Low-dose aspirin and/or phlebotomy (with frequency determined by symptom relief) might be considered on an individualized basis in the presence of hyperviscosity symptoms, cardiovascular comorbidities, and/or a history of thrombosis. Aggressive control of cardiovascular risk factors is recommended in all. A graphic abstract representation is provided in Figure 1.

BACKGROUND AND OBJECTIVES: Preventive treatment of unruptured intracranial aneurysms (UIAs) requires assessment of treatment risks vs expected benefit. Although established scores exist to estimate rupture and growth risk, currently, no externally validated tools exist to estimate the risks of microsurgical treatment of UIAs. Clinical prediction models based on machine learning enable generation of personalized risk estimates for each individual patient based on their specific patient and aneurysm characteristics. METHODS: Using data from 20 international centers from the prediction of adverse events after microsurgery for intracranial unruptured aneurysms study on patients treated microsurgically for UIAs, we developed and externally validated clinical prediction models for 3 outcomes measured at hospital discharge: poor neurological outcome (modified Rankin Score ≥3), new sensorimotor neurological deficits, and all-cause adverse events (Clavien-Dindo Grade ≥1). RESULTS: A total of 3705 patients were included. Data from 13 centers (2881, 78%) were used for model development. Fully trained models were evaluated on 824 patients (22%) from 7 additional centers. Average age was 56 ± 12 years, and 1049 (28%) were male. At discharge, poor neurological outcome was seen in 514 patients (14%). New sensorimotor deficits were observed in 534 patients (14%), and 894 patients (24%) experienced adverse events until discharge. At external validation, prediction of poor neurological outcome was achieved with good calibration and an area under the curve (AUC) = 0.70 (95% CI: 0.63-0.75). Similarly, new neurological deficits were predicted with good calibration and with an AUC = 0.69 (95% CI: 0.63-0.74). Prediction of all-cause adverse events only achieved an AUC = 0.59 (95% CI: 0.55-0.64) with fair calibration. The prediction model was integrated into a web application accessible at https://neurosurgery.shinyapps.io/PRAEMIUM/. CONCLUSION: The developed models for prediction of poor neurological outcome and new sensorimotor neurological deficits at discharge exhibit good calibration and fair discrimination based on a multinational external validation, indicating that the predicted probabilities correspond well to real-world risks and may thus be clinically useful in more objectively estimating the risk of microsurgical treatment.

Abstract Background Concerns exist regarding inflatable penile prosthesis (IPP) placement after transcorporal artificial urinary sphincter (TC-AUS) surgery due to potential risk of damaging the AUS cuff during corporal dilation and device placement. Aim To evaluate perioperative complications, infections, revision rates, and device longevity in patients undergoing IPP placement following prior TC-AUS surgery. Methods We present a case series of men who underwent IPP surgery with an existing TC-AUS in place. A retrospective review was conducted of all patients who underwent TC-AUS placement at a single tertiary institution between 2015 and 2025. Patients who subsequently received IPP surgery were identified. Standard IPP techniques were used with additional precautions to protect the AUS, including use of electrocautery instead of sharp dissection and contralateral reservoir placement. Demographics, operative details, complications, infections, revision events, and device survival were collected through review of operative notes and patient records. Outcomes Primary outcomes included intra-operative difficulties, perioperative complications, infection and erosion rates, and revision or failure rates for both the TC-AUS and IPP devices. Results Among 757 TC-AUS placements, 17 patients subsequently underwent IPP surgery. Seven patients (41%) had a history of pelvic irradiation. The median operative time for IPP placement was 83 minutes (interquartile range [IQR] 68-87), and median follow-up was 31.5 months (IQR 11.2-40.6). All reservoirs were positioned contralateral to the AUS reservoir. A 12 Fr catheter was left postoperatively in 10 patients (59%) for &lt;24 hours. Proximal corporal dilation was noted to be challenging in 3 patients (18%) but dilation was completed without cuff injury or corporal perforation. One patient (6%) had TC-AUS cuff erosion 9.5 months after IPP surgery; one patient (6%) experienced TC-AUS device infection 11.5 months after IPP surgery when his AUD pump eroded through the scrotum. Four patients (24%) developed AUS mechanical failure due to cuff leak at a median of 31.9 months after IPP placement (39.9 months post-AUS). Clinical implications IPP implantation following TC-AUS can be performed safely using careful surgical technique, though vigilance for later AUS mechanical failure is warranted. Strengths and limitations This study represents one of the largest single-institution series evaluating IPP after TC-AUS and includes detailed operative and follow-up data. However, its retrospective design, small cohort size, and limited follow-up duration restrict generalizability. Conclusion IPP placement after TC-AUS appears safe, with low infection and erosion rates, though AUS cuff leaks may occur more frequently than when either device is implanted alone.