BackgroundPregnancy and childbirth involve significant health challenges, including preventable maternal deaths, severe complications, and disparities tied to social determinants, emphasizing the need for improved maternal care. Pregnancy could benefit from a more comprehensive, continuous care model that captures dynamic changes and enhances maternal-fetal outcomes. ObjectiveThis large-scale, real-world, high-density study aims to use wearable data to investigate maternal biobehavioral trajectories for pregnancies leading to loss, preterm, and term births, exploring how demographic factors like age and body mass index (BMI) affect these trajectories. MethodsRetrospective observational analysis of pregnancies from a sample of 10,318 and 18- to 51-year-old female Oura Ring users (324 preterm births, 5039 term births, 4955 pregnancies ending in loss before 20 weeks of gestation). Oura biobehavioral data were analyzed across a 64-week window encompassing 8 weeks prepregnancy, through pregnancy, and post partum, via generalized estimating equation (GEE) statistical modeling. ResultsGestational age emerged as a significant factor across all domains among term pregnancies (P<.001). During the first trimester, participants experienced marked sleep changes, peaking around week 9 and characterized by more time in bed (+30 min), asleep (+15 min), and awake (+15 min) compared with prepregnancy. Metrics declined and stabilized in the second trimester; by the third trimester, time in bed returned to baseline, while sleep remained reduced and wakefulness elevated. At birth, time in bed and wakefulness peaked, and sleep duration reached its minimum, with nighttime wake exceeding 3 SDs above baseline. Temperature changes were more pronounced, sustained, and occurred earlier than sleep changes—becoming evident by week 4, peaking at +0.3 °C above baseline by week 9, and showing a steady decline until birth. A secondary, modest increase (+0.1 °C) was observed near birth, followed by a decline postpartum. Heart rate (HR) increased steadily, peaking at +10 bpm above baseline at week 32, while HR variability declined by >15 milliseconds in a mirrored pattern. Respiratory rate peaked around week 9 and declined thereafter. Step count declined in the first trimester, with a ≈2000-step reduction at around week 8. After a slight rebound midpregnancy, activity declined again, reaching its lowest point near birth, with >2500 fewer steps than prepregnancy. Age and BMI showed significant but modest interaction effects (all P<.01). In pregnancies ending in loss, deviations emerged up to 2 weeks prior. Time in bed decreased starting ≈2 weeks before loss (P<.001), followed by reductions in sleep duration (P<.001), temperature trends (P<.001), respiratory rate (P=.019), HR (P=.005), and awake time (P=.033). ConclusionsThese findings highlight the complex dynamics underlying changes in participants’ sleep, temperature trends, cardiorespiratory, and activity data throughout pregnancy, involving extensive adaptations. A deeper focus on normative changes can advance maternal-fetal medicine, improve clinical outcomes, and address scientific gaps.

Liver transplant recipients (LTRs) are at risk of graft injury, leading to cirrhosis and reduced survival. Liver biopsy, the diagnostic gold standard, is invasive and risky. We developed a hybrid multi-class neural network (NN) model, 'GraftIQ,' integrating clinician expertise for non-invasive graft pathology diagnosis. Biopsies from LTRs (1992-2020) were classified into six categories using demographic, clinical, and lab data from 30 days pre-biopsy. The dataset (5217 biopsies) was split 70/30 for training/testing, with external validation at Mayo Clinic, Hannover Medical School, and NUHS Singapore. Bayesian fusion was used to combine clinician-derived probabilities with NN predictions, improving performance. Here we show that GraftIQ (MulticlassNN+clinical insight) achieved an AUC of 0.902 (95% CI:0.884-0.919), up from 0.885 with NN alone. Internal and external validation demonstrated 10-16% higher AUC than conventional ML models. GraftIQ demonstrates high accuracy in identifying graft etiologies and offers a valuable clinical decision support tool for LTRs.

ABSTRACTBackground and AimsLiver transplant recipients (LTRs) are at risk of developing graft injury, leading to cirrhosis and reduced survival. Liver biopsy remains the gold standard method for the diagnosis of graft pathology but is invasive and risky. Our study aimed to develop a novel hybrid multi-class neural network (NN) model ‘GraftIQ’ integrating clinician expertise for non-invasive diagnosis of graft pathology.MethodsGraft injury diagnosis was based on liver biopsies from LTRs (1992-2020). Demographic, clinical, and laboratory data from the 30 days before biopsy were used to train a multi-class NN model to classify biopsies into six categories. The dataset was split into 70% training and 30% test sets, with external validation on additional biopsies from 2020-2024. To enhance predictive capabilities, clinician expertise was integrated with neural network predictions using Bayesian fusion to combine clinician-provided probabilities with data-driven outcomes.ResultsOur dataset comprises 5,217 biopsies categorized into six graft etiology groups. In response to findings from expert versus machine implementation analysis, Bayesian fusion of clinical expertise and NN predictions enhanced predictive performance. GraftIQ (MulticlassNN + clinical insight) achieved an overall AUC of 0.902 (95% CI: 0.884, 0.919), improving from an AUC of 0.885 using the NN alone. Robustness validated through 10-fold internal cross-validation and external validation, showed AUC improvements of 10-16% compared to conventional machine learning approaches.ConclusionOur multi-class neural network model demonstrates high accuracy in predicting common causes of graft pathology. Through the integration of clinician expertise, we observed an improvement in its performance, affirming the effectiveness of GraftIQ as a valuable clinical decision support tool.Availability of codehttps://github.com/divya031090/multiclassNN

BACKGROUND:Solitary hepatocellular carcinoma measuring ≤3 cm represents approximately 30% of hepatocellular carcinoma cases, yet treatment guidelines lack robust evidence. This study compares oncologic outcomes after ablation, liver resection, and liver transplantation for solitary, small hepatocellular carcinoma. METHODS:We systematically searched databases up to 7 February 2022, for studies including adults with solitary hepatocellular carcinoma ≤3 cm treated by any ablation, liver resection, or liver transplantation. We excluded non-hepatocellular carcinoma cancers, recurrent/metastatic diseases, and alternative therapies. A frequentist network meta-analysis assessed 5-year overall survival and recurrence-free survival using only adjusted effect estimates while accounting for bias risk. RESULTS:We identified 80 studies (4 randomized controlled trials, 72 retrospectives, and 4 prospective cohorts) with 28,211 patients. In the network meta-analysis for 5-year overall survival (26 studies), liver transplantation was associated with the lowest mortality hazard (hazard ratio, 0.47; 95% confidence interval, 0.31-0.73, referenced to liver resection), followed by liver resection (reference), whereas ablation had the greatest mortality hazard (hazard ratio, 1.32; 95% confidence interval, 1.16-1.49, referenced to liver resection). For 5-year recurrence-free survival (19 studies), liver transplantation had the best outcome (hazard ratio, 0.36; 95% confidence interval, 0.20-0.63, referenced to liver transplantation), followed by liver resection (reference), with ablation showing the least favorable outcome (hazard ratio, 1.67; 95% confidence interval, 1.45-1.93, referenced to liver resection). CONCLUSIONS:This network meta-analysis provides the evidence for comparing treatment modality outcomes for solitary, small (≤3 cm) hepatocellular carcinoma. LT emerges as the superior choice for achieving a better 5-year OS, followed by liver resection, then ablation. When feasible to preserve liver function, liver resection can be prioritized. Ablation with close surveillance should be reserved for individuals unfit for surgery.

The transition from pregnancy into parturition is physiologically directed by maternal, fetal and placental tissues. We hypothesize that these processes may be reflected in maternal physiological metrics. We enrolled pregnant participants in the third-trimester (n = 118) to study continuously worn smart ring devices monitoring heart rate, heart rate variability, skin temperature, sleep and physical activity from negative temperature coefficient, 3-D accelerometer and infrared photoplethysmography sensors. Weekly surveys assessed labor symptoms, pain, fatigue and mood. We estimated the association between each metric, gestational age, and the likelihood of a participant's labor beginning prior to (versus after) the clinical estimated delivery date (EDD) of 40.0 weeks with mixed effects regression. A boosted random forest was trained on the physiological metrics to predict pregnancies that naturally passed the EDD versus undergoing onset of labor prior to the EDD. Here we report that many raw sleep, activity, pain, fatigue and labor symptom metrics are correlated with gestational age. As gestational age advances, pregnant individuals have lower resting heart rate 0.357 beats/minute/week, 0.84 higher heart rate variability (milliseconds) and shorter durations of physical activity and sleep. Further, random forest predictions determine pregnancies that would pass the EDD with accuracy of 0.71 (area under the receiver operating curve). Self-reported symptoms of labor correlate with increased gestational age and not with the timing of labor (relative to EDD) or onset of spontaneous labor. The use of maternal smart ring-derived physiological data in the third-trimester may improve prediction of the natural duration of pregnancy relative to the EDD.

Psychological stress, both leading up to and during pregnancy, is associated with increased risk for negative pregnancy outcomes. Although the neuroendocrine circuits that link the stress response to reduced sexual motivation and mating are well-described, the specific pathways by which stress negatively impacts gestational outcomes remain unclear. Using a mouse model of chronic psychological stress during pregnancy, we investigated 1) how chronic exposure to stress during gestation impacts maternal reproductive neuroendocrine circuitry, and 2) whether stress alters developmental outcomes for the fetus or placenta by mid-pregnancy. Focusing on the stress-responsive neuropeptide RFRP-3, we identified novel contacts between RFRP-3-immunoreactive (RFRP-3-ir) cells and tuberoinfundibular dopaminergic neurons in the arcuate nucleus, thus providing a potential pathway linking the neuroendocrine stress response directly to pituitary prolactin production and release. However, neither of these cell populations nor circulating levels of pituitary hormones were affected by chronic stress. Conversely, circulating levels of steroid hormones relevant to gestational outcomes (progesterone and corticosterone) were altered in chronically-stressed dams across gestation, and those dams were qualitatively more likely to experience delays in fetal development. Together, these findings suggest that, up until at least mid-pregnancy, mothers appear to be relatively resilient to the effects of elevated glucocorticoids on reproductive neuroendocrine system function. We conclude that understanding how chronic psychological stress impacts reproductive outcomes will require understanding individual susceptibility and identifying reliable neuroendocrine changes resulting from gestational stress.

The menstrual cycle is characterized partially by fluctuations of the ovarian hormones estradiol (E2) and progesterone (P4), which are implicated in the regulation of cognition. Research on attention in the different stages of the menstrual cycle is sparse, and the three attentional networks (alerting, orienting and executive) and their interaction were not explored during the menstrual cycle. In the current study, we used the ANT-I (attentional network test – interactions) to examine two groups of women: naturally cycling (NC) – those with a regular menstrual cycle, and oral contraceptives (OC) – those using OC and characterized with low and steady ovarian hormone levels. We tested their performance at two time points that fit, in natural cycles, the early follicular phase and the early luteal phase. We found no differences in performance between NC and OC in low ovarian hormone states (Both phases for the OC group and early follicular phase for the NC group). However, the NC group in the early luteal phase exhibited the same pattern of responses for alerting and no-alerting conditions, resulting in a better conflict resolution (executive) when attention is oriented to the target. Results-driven exploratory regression analysis of E2 and P4 suggested that change in P4 from early follicular to early luteal phases was a mediator for the alerting effect found. In conclusion, the alerting state found with or without alertness manipulation suggests that there is a progesterone mediated activation of the alerting system during the mid-luteal phase.

Solid-organ transplantation is a life-saving treatment for end-stage organ disease in highly selected patients. Alongside the tremendous progress in the last several decades, new challenges have emerged. The growing disparity between organ demand and supply requires optimal patient/donor selection and matching. Improvements in long-term graft and patient survival require data-driven diagnosis and management of post-transplant complications. The growing abundance of clinical, genetic, radiologic, and metabolic data in transplantation has led to increasing interest in applying machine-learning (ML) tools that can uncover hidden patterns in large datasets. ML algorithms have been applied in predictive modeling of waitlist mortality, donor–recipient matching, survival prediction, post-transplant complications diagnosis, and prediction, aiming to optimize immunosuppression and management. In this review, we provide insight into the various applications of ML in transplant medicine, why these were used to evaluate a specific clinical question, and the potential of ML to transform the care of transplant recipients. 36 articles were selected after a comprehensive search of the following databases: Ovid MEDLINE; Ovid MEDLINE Epub Ahead of Print and In-Process & Other Non-Indexed Citations; Ovid Embase; Cochrane Database of Systematic Reviews (Ovid); and Cochrane Central Register of Controlled Trials (Ovid). In summary, these studies showed that ML techniques hold great potential to improve the outcome of transplant recipients. Future work is required to improve the interpretability of these algorithms, ensure generalizability through larger-scale external validation, and establishment of infrastructure to permit clinical integration.

Background Machine learning (ML) has been increasingly applied in the health-care and liver transplant setting. The demand for liver transplantation continues to expand on an international scale, and with advanced aging and complex comorbidities, many challenges throughout the transplantation decision-making process must be better addressed. There exist massive datasets with hidden, non-linear relationships between demographic, clinical, laboratory, genetic, and imaging parameters that conventional methods fail to capitalize on when reviewing their predictive potential. Pre-transplant challenges include addressing efficacies of liver segmentation, hepatic steatosis assessment, and graft allocation. Post-transplant applications include predicting patient survival, graft rejection and failure, and post-operative morbidity risk. Aim In this review, we describe a comprehensive summary of ML applications in liver transplantation including the clinical context and how to overcome challenges for clinical implementation. Methods Twenty-nine articles were identified from Ovid MEDLINE, MEDLINE Epub Ahead of Print and In-Process and Other Non-Indexed Citations, Embase, Cochrane Database of Systematic Reviews, and Cochrane Central Register of Controlled Trials. Conclusion ML is vastly interrogated in liver transplantation with promising applications in pre- and post-transplant settings. Although challenges exist including site-specific training requirements, the demand for more multi-center studies, and optimization hurdles for clinical interpretability, the powerful potential of ML merits further exploration to enhance patient care.

Background Nonalcoholic fatty liver disease (NAFLD) is the most prevalent liver disease worldwide. Cardiovascular disease (CVD) is the leading cause of mortality among patients with NAFLD. The aim of our study was to develop a machine learning algorithm integrating clinical, lifestyle, and genetic risk factors to identify CVD in patients with NAFLD. Methods and Results We created a cohort of patients with NAFLD from the UK Biobank, diagnosed according to proton density fat fraction from magnetic resonance imaging data sets. A total of 400 patients with NAFLD with subclinical atherosclerosis or clinical CVD, defined by disease codes, constituted cases and 446 NAFLD cases with no CVD constituted controls. We evaluated 7 different supervised machine learning approaches on clinical, lifestyle, and genetic variables for identifying CVD in patients with NAFLD. The most significant clinical and lifestyle variables observed by the predictive modeling were age (59 years [54.00–63.00 years]), hypertension (145 mm Hg [134.0–156.0 mm Hg] and 85 mm Hg [79.00–93.00 mm Hg]), waist circumference (98 cm [95.00–105.00 cm]), and sedentary lifestyle, defined as time spent watching TV >4 h/d. In the genetic data, single‐nucleotide polymorphisms in IL16 and ANKLE1 gene were most significant. Our proposed ensemble‐based integrative machine learning model achieved an area under the curve of 0.849 using the random forest modeling for CVD prediction. Conclusions We propose a machine learning algorithm that identifies CVD in patients with NAFLD through integration of significant clinical, lifestyle, and genetic risk factors. These patients with NAFLD at higher risk of CVD should be flagged for screening and aggressive treatment of their cardiometabolic risk factors to prevent cardiovascular morbidity and mortality.

Abstract Despite numerous findings detailing the negative impact of stress on female reproductive health, the means by which stress acts on the CNS and periphery to compromise reproductive success remains poorly understood. As a result, the current study sought to clarify the neuroendocrine mechanisms by which stress acts on the brain to deleteriously influence pregnancy outcomes. Reproduction is regulated by the hypothalamo-pituitary-gonadal (HPG) axis, with hypothalamic gonadotropin-releasing hormone (GnRH) neurons representing the final, common pathway of this axis. Cells expressing the inhibitory neuropeptide, RFamide-related peptide-3 (RFRP-3), lie upstream of the GnRH system and are markedly regulated by environmental and psychosocial factors, including stress. In the present study, we asked whether RFRP-3 neurons mediate the effects of stress on pregnancy outcomes through the regulation of prolactin secretion, as prolactin is critical for pregnancy maintenance. More specifically, because specialized hypothalamic dopaminergic neurons, namely tubero-infundibular dopaminergic (TIDA) neurons, are major regulators of prolactin secretion, we hypothesized that RFRP-3 neurons directly target TIDA cells to negatively influence fetal development. To test this possibility, we subjected pregnant mice to chronic restraint stress for the first half of pregnancy and performed a broad screen of hypothalamic neuroendocrine function compared to non-stressed controls. Stressed mice exhibited elevated baseline concentrations of corticosterone that remained high at least 6 days after the final exposure to stress. Whereas progesterone concentrations were reduced by stress early in pregnancy, stressed mice recovered typical progesterone secretion during late gestation. These early, stressful experiences resulted in persistent developmental delays, reduced embryo weight, and abnormal placental histology. Significantly, a small percentage of TIDA cells receive close contacts from RFRP-3 axons, providing a mechanism for the control of prolactin secretion by stress. However, contrary to expectation, the percentage of TIDA neurons receiving input from RFRP-3 cells was not impacted by stress. Together, these findings identify a potential pathway of control for the impact of stress on neuroendocrine factors critical to pregnancy success, although further work using more sensitive approaches is needed to examine the putative role of RFRP-3 on stress-induced pregnancy outcomes.

Hepatitis A virus (HAV) and hepatitis E virus (HEV) are the most common causes of acute hepatitis in humans worldwide.1–7 The genomic structure of these viruses is shown in the poster. Both enterically transmitted hepatotropic viruses show a similar but not identical epidemiologic pattern, mode of transmission and clinical course. However, there are also some distinct genetic differences within the genome of the individual viruses with an impact on epidemiology and transmission. Most HAV and HEV infections are acquired through contaminated water and food.

BACKGROUND & AIMS: Few patients with primary sclerosing cholangitis (PSC) and inflammatory bowel diseases (IBDs) are exposed to tumor necrosis factor (TNF) antagonists because of the often mild symptoms of IBD. We assessed the effects of anti-TNF agents on liver function in patients with PSC and IBD, and their efficacy in treatment of IBD. METHODS: We performed a retrospective analysis of 141 patients with PSC and IBD receiving treatment with anti-TNF agents (infliximab or adalimumab) at 20 sites (mostly tertiary-care centers) in Europe and North America. We collected data on the serum level of alkaline phosphatase (ALP). IBD response was defined as either endoscopic response or, if no endoscopic data were available, clinical response, as determined by the treating clinician or measurements of fecal calprotectin. Remission was defined more stringently as endoscopic mucosal healing. We used linear regression analysis to identify factors associated significantly with level of ALP during anti-TNF therapy. RESULTS: Anti-TNF treatment produced a response of IBD in 48% of patients and remission of IBD in 23%. There was no difference in PSC symptom frequency before or after drug exposure. The most common reasons for anti-TNF discontinuation were primary nonresponse of IBD (17%) and side effects (18%). At 3 months, infliximab-treated patients had a median reduction in serum level of ALP of 4% (interquartile range, reduction of 25% to increase of 19%) compared with a median 15% reduction in ALP in adalimumab-treated patients (interquartile range, reduction of 29% to reduction of 4%; P = .035). Factors associated with lower ALP were normal ALP at baseline (P < .01), treatment with adalimumab (P = .090), and treatment in Europe (P = .083). CONCLUSIONS: In a retrospective analysis of 141 patients with PSC and IBD, anti-TNF agents were moderately effective and were not associated with exacerbation of PSC symptoms or specific side effects. Prospective studies are needed to investigate the association between use of adalimumab and reduced serum levels of ALP further.

BACKGROUND Liver cirrhosis is a significant source of morbidity and mortality worldwide. The disease is usually indolent and asymptomatic early in its course while many cirrhotic patients are diagnosed late when severe complications occur. A major challenge is to diagnose advanced fibrosis as early as possible, using simple and non-invasive diagnostics tools. Thrombocytopenia represents advanced fibrosis and portal hypertension (HTN) and most non-invasive scores that predict liver fibrosis incorporate platelets as a strong risk factor. However, little is known about the association between longitudinal changes in platelet counts (PTC), when still within the normal range, and the risk of cirrhosis. AIM To explore whether platelet counts trajectories over time, can predict advanced liver fibrosis across the different etiologies of liver diseases. METHODS A nested case-control study utilizing a large computerized database. Cirrhosis cases (n = 5258) were compared to controls (n = 15744) matched for age and sex at a ratio of 1:3. All participants had multiple laboratory measurements prior to enrollment. We calculated the trends of PTC, liver enzymes, bilirubin, international normalized ratio, albumin and fibrosis scores (fibrosis-4 and aspartate transaminase-to-platelet ratio index) throughout the preceding 20 years prior to cirrhosis diagnosis compared to healthy controls. The association between PTC, cirrhosis complications and fibrosis scores prior to cirrhosis diagnosis was investigated. RESULTS The mean age in both groups was 56 (SD 15.8). Cirrhotic patients were more likely to be smokers, diabetic with chronic kidney disease and had a higher prevalence of HTN. The leading cirrhosis etiologies were viral, alcoholic and fatty liver disease. The mean PTC decreased from 240000/μL to 190000/μL up to 15 years prior to cirrhosis diagnosis compared to controls who’s PTC remained stable around the values of 240000/μL. This trend was consistent regardless of sex, cirrhosis etiology and was more pronounced in patients who developed varices and ascites. Compared to controls whose values remained in the normal range, in the cirrhosis group aspartate aminotransferase and alanine aminotransferase, increased from 40 U/L to 75 U/L and FIB-4 increased gradually from 1.3 to 3 prior to cirrhosis diagnosis. In multivariable regression analysis, a decrease of 50 units in PTC was associated with 1.3 times odds of cirrhosis (95%CI 1.25-1.35). CONCLUSION In the preceding years before the diagnosis of cirrhosis, there is a progressive decline in PTC, within the normal range, matched to a gradual increase in fibrosis scores.

Background. Mammalian target of rapamycin (mTOR) inhibitors following liver transplantation (LT) are used to minimize calcineurin inhibitor (CNI)-related nephrotoxicity. Data about metabolic effects of mTOR inhibitors are still limited. Aim. This study aims to determine the renal and metabolic effects of different mTOR inhibitor-based protocols in real-life LT patients. Methods. This is a retrospective cohort study of patients treated with mTOR inhibitors after LT. Demographics, treatment protocols, glomerular filtration rate (GFR), and metabolic parameters were collected over a period of 4 years. Initiation of blood pressure (BP), diabetes mellitus, and lipid medications was also noted. Results. Fifty-two LT recipients received mTOR inhibitors. GFR improved significantly (by 1.96 mL/min/year), with greater improvement in patients with baseline renal dysfunction (+13.3 mL/min vs +4.5 mL/min at 3 years). Conversion to an mTOR inhibitor during the first post-transplant year resulted in a more durable improvement in GFR (for 4 years vs only 1 year for later conversion).No significant weight gain or new-onset diabetes mellitus was observed. However, there was some increase in total cholesterol (+7 mg/dL) and blood pressure (+2 mm Hg during the third year and +8 mm Hg in the fourth years), followed by initiation of lipid-lowering and BP medications in 25% and 13% of patients, respectively. Conclusions. Treatment with an mTOR inhibitor following LT resulted in improved kidney functions without significant negative metabolic effects such as weight gain or newonset diabetes mellitus. This makes mTOR inhibitors a valuable immunosuppressive option in the face of the growing incidence of nonalcoholic steatohepatitis as a leading cause for LT.