Citations

Purpose of review Machine learning algorithms are occupying a larger space in medical and urology applications. However, typical medical physicians are not trained on these technologies and do not master the possibilities offered by these tools, to imagine their applications in the medical field. This manuscript is indented to be a guide in the use of machine learning in different urology applications, and to demystify the available machine learning and artificial intelligence algorithms. This manuscript reviews some of their applications and potential applications to the medical and urology field. Recent findings Multiple works are published on the use of machine learning in urology, with performance demonstrated to be noninferior to human experts on multiple occasions. However, the major part of the machine learning publications in urology applications are concentrated on diagnosis and/or prognosis. Advanced machine learning algorithms based on agentic artificial intelligence, able to perform decisions and causality-based treatment optimization, are rarely put to use in urology. The democratization of advanced machine learning technologies in the medical fields can accelerate the adoption of these techniques, and potentially improve the patient care through relevant suggestive decision making. Summary This work aims to demystify the machine learning tools for medical applications, facilitate decision making and adoption of the correct tools for the correct applications, and places a roadmap for the future of machine learning in the enhancement of patient care in urology.

Abstract Objectives/Background This study was undertaken to review the published literature and provide a position statement from the American Headache Society regarding the safety, efficacy, and impact on access to care of telemedicine for the clinical management of patients with headache disorders. Access to specialized care in headache medicine is severely limited in the United States and worldwide. Telemedicine has been used as an approach to care delivery in headache medicine for more than a decade, with accelerated adoption during the COVID‐19 pandemic. There is now uncertainty regarding the extent to which telemedicine will be accepted by health systems and reimbursed by payers moving forward. The purpose of this position statement is to summarize evidence and clinical experience supporting the utility of telemedicine in headache medicine. Methods Evidence regarding the safety and efficacy of telemedicine, and patient and clinician satisfaction with the use of telemedicine for headache specialty care, was gathered from a variety of sources, including PubMed, Google Scholar, and ClinicalTrials.gov . The results and conclusions based upon these results were reviewed and discussed by the authors and the Board of Directors of the American Headache Society to confirm consistency with clinical experience and to achieve consensus. Results Several randomized clinical trials and observational studies have been performed to compare telemedicine with in‐person visits in the management of patients with headache disorders. These studies showed consistently that telemedicine is noninferior to in‐person care based upon multiple outcome measures, including disability measures, patient satisfaction, and clinician satisfaction. In addition, these studies found that telemedicine rarely leads to a missed diagnosis of secondary headache or mismanagement of primary headache. Telemedicine has substantial advantages for patients, including improved access to care and reduced costs associated with obtaining care. Studies evaluating health care utilization indicate no significant differences between patients evaluated and treated virtually versus in person. Obvious limitations of telemedicine include the inability to perform an in‐person physical exam or to perform injections. For a substantial number of patients, however, these limitations are outweighed by its advantages. The experience with telemedicine reported in the literature is consistent with the experience of the Board of Directors of the American Headache Society, who endorse its use for patients when feasible and appropriate. Conclusion Telemedicine has significantly advanced the care of patients with headache disorders. Its further development and deployment should be supported and reimbursed.

Abstract Objective The objective of this study was to summarize the available evidence regarding the clinical value and trend over time of lumbar cerebrospinal fluid (CSF) opening pressure utilization to diagnose spontaneous intracranial hypotension (SIH). Background CSF opening pressure obtained via lumbar puncture is one of the diagnostic criteria for SIH based on the International Criteria for Headache Disorders, 3rd Edition (ICHD‐3), but it has questionable utility as an initial investigation for diagnosing SIH. Methods The authors performed a systematic literature review and meta‐analysis. PubMed/MEDLINE, Scopus, and Cochrane Library were searched from inception to October 2022. Original studies and case series in English reporting three or more patients with suspected or known SIH and CSF pressure measurement were included. Meta‐analyses and meta‐regression were used to calculate pooled estimates and examine the impact of age, sex, and publication year on outcomes, including CSF pressure < 60 mm CSF, orthostatic headache, and positive findings on brain magnetic resonance imaging (MRI), spinal imaging, and radionuclide studies. Results For every 1‐year increase in the year of publication, the odds of reporting low CSF pressure decreased by 6.20% (adjusted odds ratio [aOR] = 0.94, aOR 95% confidence interval [CI] = [0.90, 0.97], p = 0.001), the odds of reporting a positive brain MRI increased by 4.67% (aOR = 1.05, aOR 95% CI = [1.01, 1.09], p = 0.026), and the odds of reporting orthostatic headache increased by 9.13% (aOR = 1.09, aOR 95% CI = [1.03, 1.15], p = 0.002). Each 1% increase in the percentage of patients with orthostatic headache was associated with a 3.13% increase in the odds of low CSF pressure (aOR = 1.03, aOR 95% CI = [1.01, 1.05], p = 0.003). Similarly, as the percentage of patients with low CSF pressure increased by 1%, there was a 2.53% increase in the odds of orthostatic headache (aOR = 1.03, aOR 95% CI = [1.01, 1.04], p = 0.005). It was estimated that 31.9% of patients with SIH had normal opening pressure (95% CI = [24.0%, 40.8%], prediction interval = [5.0%, 80.5%]). Every 1% increase in the percentage of patients with positive brain MRI was associated with a 5.25% increase in the odds of positive spinal imaging (aOR = 1.05, aOR 95% CI = [1.00, 1.11], p = 0.047). Age and positive radionuclide study did not significantly impact the outcomes measured. The corresponding I 2 for each outcome was reduced by controlling for study‐wide covariates believed to impact the prevalence of each outcome. Sensitivity analyses did not reveal discrepancies in results when studies requiring outcomes of interest were removed. Conclusion Our analysis found that recent studies indicate a reduced reliance on opening pressure for diagnosing SIH. Rather, results suggest an increasing reliance on contrast‐enhanced brain MRI, spine imaging, and clinical features for SIH diagnosis.

Background: Increasing maternal body mass index (BMI) represents a risk factor for Gestational Diabetes Mellitus (GDM) and adverse obstetrical and perinatal outcomes. Objective: To stratify clinical outcomes for pregnancies affected by GDM according to maternal BMI. Methods: Retrospective cohort study including individuals ≥18 years of age who were diagnosed with GDM from 2018 to 2022. Universal GDM screening was employed with a 50 g oral glucose challenge test ± a 100 g oral glucose tolerance test. Maternal demographics, preexisting medical conditions, and selected obstetric and neonatal morbidities were evaluated. Results: A total of 2193 pregnancies in 2110 women affected by GDM were identified. This included 506 (23.0%) with normal baseline maternal BMI, 596 (27.2%) with overweight, and 1091 (49.7%) with obese BMI. Adverse maternal outcomes were more frequent in the obese compared to overweight or normal BMI categories (cesarean delivery: normal 26.9% vs. overweight 28.5% vs. obese 40.9%; p < 0.001; hypertensive disorders of pregnancy: normal 8.7% vs. overweight 12.1% vs. obese 16.8%; p < 0.001). Postpartum glucose intolerance was higher in women with obesity (normal 7.3% vs. overweight 5.9% vs. obese 14.9%; p < 0.001). Infants born to mothers with obesity had higher birthweights (normal 3.3 kg vs. overweight 3.4 kg vs. obese 3.5 kg; p < 0.001), were more likely to have neonatal hypoglycemia (normal 29.4% vs. overweight 24.3% vs. obese 41.9%; p < 0.001) and require intensive care unit admission (normal 8.1% vs. overweight 5.9% vs. obese 11.9%; p < 0.001). Conclusions: Patients with GDM and baseline BMI in the obese range experienced the highest rate of adverse outcomes, while those with overweight BMI had similar outcomes to individuals who had normal BMI at baseline.

The clinical benefit of blood transfusion is undeniable, and yet reliance on donated blood products has several shortcomings. These include risks of supply shortages due to reliance on volunteer donors, short storage life, and potential infectious disease transmission. Immune response complications to donated blood cannot be completely avoided, despite significant advances in testing. Many of these limitations are exacerbated in low-income countries. For decades, cell-free hemoglobin-based blood substitutes have been developed and tested as potential substitutes for red blood cell transfusions. Early studies found that purified, native hemoglobin exhibited significant safety risks, such as hypertension from excessive vasoconstriction and evidence of multiple organ toxicities. These effects are likely in part due to the reactive heme center, which will scavenge nitric oxide, generate reactive oxygen species, and may drive sterile inflammation. Numerous strategies have been explored to further modify hemoglobin in the hope of creating a safe and well-tolerated blood substitute. Despite some promising results in preliminary studies, large-scale clinical trials have continued to show elevated rates of adverse events and/or a failure to meet specified clinical endpoints. As a result, no hemoglobin-based oxygen carrier (HBOC) has obtained US Food and Drug Administration approval for clinical use. This review focuses on the history of HBOC development, the lessons that have been learned from prior failures of HBOC programs, and the status of ongoing artificial oxygen carrier development efforts.

Background/Objectives: Dutch newborn screening is an important public health program designed to detect conditions early in life, enabling timely interventions that can prevent mortality, morbidity, and long-term disabilities. However, the program also faces certain challenges. One such issue is obtaining and maintaining a high positive predictive value (PPV); another is that newborn screening (NBS) in the Netherlands is intended for all newborn babies until the age of six months. This means comparing infants at different ages may introduce variability that complicates data interpretation. To support the optimization of the program, we systematically analyzed population-level tandem mass spectrometry (MS/MS) data to explore postnatal metabolic changes. Methods: We evaluated the impact of covariates—including birth weight, gestational age, age at blood collection, and biological sex—on metabolite profiles using retrospective newborn screening (NBS) data. Special emphasis was placed on the combined effects of these covariates. The analysis was based on data from 985,629 newborns collected between 2018 and 2024. Results: Specifically, (extremely) preterm infants exhibit altered levels of several amino acids and acylcarnitines. Moreover, we observed multiplicative effects of gestational age and birth weight on several metabolic markers. Biological sex however, does not have an impact. The largest impact of the age of sampling was observed on the C0/C16+C18 ratio, which may impact screening performance for CPT1 deficiency. Conclusions: Covariate-adjusted reference values could improve the performance of the Dutch newborn screening.

Abstract Small cell carcinoma of the ovary, hypercalcemic type (SCCOHT) is a rare, deadly form of ovarian cancer that uniformly harbors mutations in SMARCA4, a member of the SWI/SNF chromatin remodeling complex. SWI/SNF impacts RNA splicing, and dysregulation of splicing can generate immunogenic tumor antigens. Here, we explored the relationship between SMARCA4 loss and RNA splicing dysregulation. SCCOHT primary tumors harbored tumor-associated outlier splicing events compared to normal tissues. Many of the tumor events were retained introns encoding novel peptides predicted to bind to MHC-I complexes. Immune cells were observed in primary SCCOHT tumors, suggesting a potentially immune reactive tumor microenvironment. Mutations in several SWI/SNF subunits were associated with higher rates of outlier retained introns across tumor types in TCGA data. Interestingly, RNA sequencing of isogenic SCCOHT cell lines demonstrated a role for SMARCA4 in intron retention. Distinct protein-protein interactions between splicing factors identified in SCCOHT cell lines supported a role for SMARCA4 in splicing regulation. Further, SWI/SNF localized to genes which were differentially spliced. Mass spectrometry analyses confirmed expression of some of these novel peptides and a subset of these are predicted to bind to MHC-I complexes. A pool of these novel peptides derived from retained introns in SCCOHT triggered proliferation and expression of TNFa and INFb in primary human T cells. Together, these data suggest that SMARCA4 loss in SCCOHT leads to intron retention. Furthermore, T cell activation by novel peptides encoded by these tumor-specific splicing events suggests intron retention could be a source of tumor-associated antigens in SCCOHT. Citation Format: Elizabeth Raupach, Apurva Hegde, Krystine Garcia-Masnfield, Marice Alcantara, David Rose, Rebecca Halperin, Krystal Orlando, Jessica Lang, Ritin Sharma, Victoria David-Dirgo, Salvatore Facista, Rayvon Moore, Rochelle Kofman, Zoe Jensen, Victoria Zismann, Anthony Karnezis, Yemin Wang, Lynda Bennett, Timothy Whitsett, Marcin Kortylewski, William Hendricks, David Huntsman, Lorna Rodriguez-Rodriguez, Bernard Weissman, Jeffrey Trent, Patrick Pirrotte. Loss of SMARCA4 leads to intron retention and generation of tumor-associated antigens in small cell carcinoma of the ovary, hypercalcemic type [abstract]. In: Proceedings of the AACR Special Conference in Cancer Research: Advances in Ovarian Cancer Research; 2025 Sep 19-21; Denver, CO. Philadelphia (PA): AACR; Cancer Res 2025;85(18_Suppl):Abstract nr B065.