A machine learning-based choledocholithiasis prediction tool to improve ERCP decision making: a proof-of-concept study.

BACKGROUND: Previous studies demonstrated limited accuracy of existing guidelines for predicting choledocholithiasis, leading to overutilization of endoscopic retrograde cholangiopancreatography (ERCP). More accurate stratification may improve patient selection for ERCP and allow use of lower-risk modalities. METHODS: A machine learning model was developed using patient information from two published cohort studies that evaluated performance of guidelines in predicting choledocholithiasis. Prediction models were developed using the gradient boosting model (GBM) machine learning method. GBM performance was evaluated using 10-fold cross-validation and area under the receiver operating characteristic curve (AUC). Important predictors of choledocholithiasis were identified based on relative importance in the GBM. RESULTS: 1378 patients (mean age 43.3 years; 61.2% female) were included in the GBM and 59.4% had choledocholithiasis. Eight variables were identified as predictors of choledocholithiasis. The GBM had accuracy of 71.5% (SD 2.5%) (AUC 0.79 [SD 0.06]) and performed better than the 2019 American Society for Gastrointestinal Endoscopy (ASGE) guidelines (accuracy 62.4% [SD 2.6%]; AUC 0.63 [SD 0.03]) and European Society of Gastrointestinal Endoscopy (ESGE) guidelines (accuracy 62.8% [SD 2.6%]; AUC 0.67 [SD 0.02]). The GBM correctly categorized 22% of patients directed to unnecessary ERCP by ASGE guidelines, and appropriately recommended as the next management step 48% of ERCPs incorrectly rejected by ESGE guidelines. CONCLUSIONS: A machine learning-based tool was created, providing real-time, personalized, objective probability of choledocholithiasis and ERCP recommendations. This more accurately directed ERCP use than existing ASGE and ESGE guidelines, and has the potential to reduce morbidity associated with ERCP or missed choledocholithiasis.

Multi-Site Observational Study to Assess Biomarkers for Susceptibility or Resilience to Chronic Pain: The Acute to Chronic Pain Signatures (A2CPS) Study Protocol.

Chronic pain has become a global health problem contributing to years lived with disability and reduced quality of life. Advances in the clinical management of chronic pain have been limited due to incomplete understanding of the multiple risk factors and molecular mechanisms that contribute to the development of chronic pain. The Acute to Chronic Pain Signatures (A2CPS) Program aims to characterize the predictive nature of biomarkers (brain imaging, high-throughput molecular screening techniques, or "omics," quantitative sensory testing, patient-reported outcome assessments and functional assessments) to identify individuals who will develop chronic pain following surgical intervention. The A2CPS is a multisite observational study investigating biomarkers and collective biosignatures (a combination of several individual biomarkers) that predict susceptibility or resilience to the development of chronic pain following knee arthroplasty and thoracic surgery. This manuscript provides an overview of data collection methods and procedures designed to standardize data collection across multiple clinical sites and institutions. Pain-related biomarkers are evaluated before surgery and up to 3 months after surgery for use as predictors of patient reported outcomes 6 months after surgery. The dataset from this prospective observational study will be available for researchers internal and external to the A2CPS Consortium to advance understanding of the transition from acute to chronic postsurgical pain.

Identification of the Somatomotor Network from Language Task-based fMRI Compared with Resting-State fMRI in Patients with Brain Lesions.

Background Resting-state functional MRI (rs-fMRI) is a potential alternative to task-based functional MRI (tb-fMRI) for somatomotor network (SMN) identification. Brain networks can also be generated from tb-fMRI by using independent component analysis (ICA). Purpose To investigate whether the SMN can be identified by using ICA from a language task without a motor component, the sentence completion functional MRI (sc-fMRI) task, compared with rs-fMRI. Materials and Methods The sc-fMRI and rs-fMRI scans in patients who underwent presurgical brain mapping between 2012 and 2016 were analyzed, using the same imaging parameters (other than scanning time) on a 3.0-T MRI scanner. ICA was performed on rs-fMRI and sc-fMRI scans with use of a tool to separate data sets into their spatial and temporal components. Two neuroradiologists independently determined the presence of the dorsal SMN (dSMN) and ventral SMN (vSMN) on each study. Groups were compared by using t tests, and logistic regression was performed to identify predictors of the presence of SMNs. Results One hundred patients (mean age, 40.9 years ± 14.8 [standard deviation]; 61 men) were evaluated. The dSMN and vSMN were identified in 86% (86 of 100) and 76% (76 of 100) of rs-fMRI scans and 85% (85 of 100) and 69% (69 of 100) of sc-fMRI scans, respectively. The concordance between rs-fMRI and sc-fMRI for presence of dSMN and vSMN was 75% (75 of 100 patients) and 53% (53 of 100 patients), respectively. In 10 of 14 patients (71%) where rs-fMRI did not show the dSMN, sc-fMRI demonstrated it. This rate was 67% for the vSMN (16 of 24 patients). Conclusion In the majority of patients, independent component analysis of sentence completion task functional MRI scans reliably demonstrated the somatomotor network compared with resting-state functional MRI scans. Identifying target networks with a single sentence completion scan could reduce overall functional MRI scanning times by eliminating the need for separate motor tasks. © RSNA, 2021 Online supplemental material is available for this article. See also the editorial by Field and Birn in this issue.

Long-term kidney function and survival in recipients of allografts from living kidney donors with hypertension: a national cohort study.

Allografts from living kidney donors with hypertension may carry subclinical kidney disease from the donor to the recipient and, thus, lead to adverse recipient outcomes. We examined eGFR trajectories and all-cause allograft failure in recipients from donors with versus without hypertension, using mixed-linear and Cox regression models stratified by donor age. We studied a US cohort from 1/1/2005 to 6/30/2017; 49 990 recipients of allografts from younger (<50 years old) donors including 597 with donor hypertension and 21 130 recipients of allografts from older (≥50 years old) donors including 1441 with donor hypertension. Donor hypertension was defined as documented predonation use of antihypertensive therapy. Among recipients from younger donors with versus without hypertension, the annual eGFR decline was -1.03 versus -0.53 ml/min/m2 (P = 0.002); 13-year allograft survival was 49.7% vs. 59.0% (adjusted allograft failure hazard ratio [aHR] 1.23; 95% CI 1.05-1.43; P = 0.009). Among recipients from older donors with versus without hypertension, the annual eGFR decline was -0.67 versus -0.66 ml/min/m2 (P = 0.9); 13-year allograft survival was 48.6% versus 52.6% (aHR 1.05; 95% CI 0.94-1.17; P = 0.4). In secondary analyses, our inferences remained similar for risk of death-censored allograft failure and mortality. Hypertension in younger, but not older, living kidney donors is associated with worse recipient outcomes.

Isoosmolar enemas demonstrate preferential gastrointestinal distribution, safety, and acceptability compared with hyperosmolar and hypoosmolar enemas as a potential delivery vehicle for rectal microbicides.

Rectally applied antiretroviral microbicides for preexposure prophylaxis (PrEP) of HIV infection are currently in development. Since enemas (rectal douches) are commonly used by men who have sex with men prior to receptive anal intercourse, a microbicide enema could enhance PrEP adherence by fitting seamlessly within the usual sexual practices. We assessed the distribution, safety, and acceptability of three enema types-hyperosmolar (Fleet), hypoosmolar (distilled water), and isoosmolar (Normosol-R)-in a crossover design. Nine men received each enema type in random order. Enemas were radiolabeled [(99m)Tc-diethylene triamine pentaacetic acid (DTPA)] to assess enema distribution in the colon using single photon emission computed tomography/computed tomography (SPECT/CT) imaging. Plasma (99m)Tc-DTPA indicated mucosal permeability. Sigmoidoscopic colon tissue biopsies were taken to assess injury as well as tissue penetration of the (99m)Tc-DTPA. Acceptability was assessed after each product use and at the end of the study. SPECT/CT imaging showed that the isoosmolar enema had greater proximal colonic distribution (up to the splenic flexure) and greater luminal and colon tissue concentrations of (99m)Tc-DTPA when compared to the other enemas (p<0.01). Colon biopsies also showed that only the hyperosmolar enema caused sloughing of the colonic epithelium (p<0.05). In permeability testing, the hypoosmolar enema had higher plasma (99m)Tc-DTPA 24-h area under the concentration-time curve and peak concentration compared to the hyperosmolar and isoosmolar enemas, respectively. Acceptability was generally good with no clear preferences among the three enema types. The isoosmolar enema was superior or similar to the other enemas in all categories and is a good candidate for further development as a rectal microbicide vehicle.

Quantification of the spatial distribution of rectally applied surrogates for microbicide and semen in colon with SPECT and magnetic resonance imaging.

AIMS: We sought to describe quantitatively the distribution of rectally administered gels and seminal fluid surrogates using novel concentration-distance parameters that could be repeated over time. These methods are needed to develop rationally rectal microbicides to target and prevent HIV infection. METHODS: Eight subjects were dosed rectally with radiolabelled and gadolinium-labelled gels to simulate microbicide gel and seminal fluid. Rectal doses were given with and without simulated receptive anal intercourse. Twenty-four hour distribution was assessed with indirect single photon emission computed tomography (SPECT)/computed tomography (CT) and magnetic resonance imaging (MRI), and direct assessment via sigmoidoscopic brushes. Concentration-distance curves were generated using an algorithm for fitting SPECT data in three dimensions. Three novel concentration-distance parameters were defined to describe quantitatively the distribution of radiolabels: maximal distance (D(max) ), distance at maximal concentration (D(Cmax) ) and mean residence distance (D(ave) ). RESULTS: The SPECT/CT distribution of microbicide and semen surrogates was similar. Between 1 h and 24 h post dose, the surrogates migrated retrograde in all three parameters (relative to coccygeal level; geometric mean [95% confidence interval]): maximal distance (D(max) ), 10 cm (8.6-12) to 18 cm (13-26), distance at maximal concentration (D(Cmax) ), 3.8 cm (2.7-5.3) to 4.2 cm (2.8-6.3) and mean residence distance (D(ave) ), 4.3 cm (3.5-5.1) to 7.6 cm (5.3-11). Sigmoidoscopy and MRI correlated only roughly with SPECT/CT. CONCLUSIONS: Rectal microbicide surrogates migrated retrograde during the 24 h following dosing. Spatial kinetic parameters estimated using three dimensional curve fitting of distribution data should prove useful for evaluating rectal formulations of drugs for HIV prevention and other indications.

A Bayesian hierarchical nonlinear mixture model in the presence of artifactual outliers in a population pharmacokinetic study.

The purpose of this study is to develop a statistical methodology to handle a large proportion of artifactual outliers in a population pharmacokinetic (PK) modeling. The motivating PK data were obtained from a population PK study to examine associations between PK parameters such as clearance of dexmedetomidine (DEX) and cytochrome P450 2A6 phenotypes. The blood samples were sparsely sampled from patients in intensive care units (ICUs) while different doses of DEX were continuously infused. Conventional population PK analysis of these data revealed several challenges and intricacies. Especially, there was strong evidence that some plasma drug concentrations were artifactually high and likely contaminated with the infused drug due to blood sampling processes that are sometimes unavoidable in an ICU setting. If not addressed, or if arbitrarily excluded, these outlying values could lead to biased estimates of PK parameters and miss important relationships between PK parameters and covariates due to increased variability. We propose a novel population PK model, a Bayesian hierarchical nonlinear mixture model, to accommodate the artifactual outliers using a finite mixture as the residual error model. Our results showed that the proposed model handles the outliers well. We also conducted simulation studies with a varying proportion of the outliers. These simulation results showed that the proposed model can accommodate the outliers well so that the estimated PK parameters are less biased.

Damage to the optic radiation in multiple sclerosis is associated with retinal injury and visual disability.

OBJECTIVE: To determine whether damage to the optic radiation (OR) in multiple sclerosis (MS) is associated with optic nerve injury and visual dysfunction. DESIGN: Case-control study. SETTING: Referral center. PARTICIPANTS: Ninety referred patients with MS and 29 healthy volunteers. MAIN OUTCOME MEASURES: Magnetic resonance imaging indices along the OR were reconstructed with diffusion tensor tractography. Retinal nerve fiber layer thickness and visual acuity at high and low contrast were measured in a subset of the MS group (n = 36). RESULTS: All tested magnetic resonance imaging indices (fractional anisotropy [FA]; mean, parallel, and perpendicular [lambda( perpendicular)] diffusivity; T2 relaxation time; and magnetization transfer ratio) were significantly abnormal in patients with MS. Mean retinal nerve fiber layer thickness was significantly correlated with FA (r = 0.55; P < .001) and lambda( perpendicular) (r = -0.37; P = .001). The retinal nerve fiber layer thickness in the nasal retinal quadrant was also specifically correlated with FA and lambda( perpendicular) in the synaptically connected contralateral OR. In individuals with less severely damaged optic nerves (mean retinal nerve fiber layer thickness >80 mum), letter acuity scores at 2.5% contrast were correlated with OR-specific FA (r = 0.55; P = .004), lambda( perpendicular) (r = -0.40; P = .04), and magnetization transfer ratio (r = 0.54; P = .01), as well as the fraction of OR volume made up of lesions (r = -0.69; P < .001). CONCLUSIONS: Fractional anisotropy and lambda( perpendicular) are potentially useful quantitative magnetic resonance imaging biomarkers of OR-specific damage in MS. Such damage is associated with retinal injury and visual disability.

Sleep-disordered breathing and mortality: a prospective cohort study.

BACKGROUND: Sleep-disordered breathing is a common condition associated with adverse health outcomes including hypertension and cardiovascular disease. The overall objective of this study was to determine whether sleep-disordered breathing and its sequelae of intermittent hypoxemia and recurrent arousals are associated with mortality in a community sample of adults aged 40 years or older. METHODS AND FINDINGS: We prospectively examined whether sleep-disordered breathing was associated with an increased risk of death from any cause in 6,441 men and women participating in the Sleep Heart Health Study. Sleep-disordered breathing was assessed with the apnea-hypopnea index (AHI) based on an in-home polysomnogram. Survival analysis and proportional hazards regression models were used to calculate hazard ratios for mortality after adjusting for age, sex, race, smoking status, body mass index, and prevalent medical conditions. The average follow-up period for the cohort was 8.2 y during which 1,047 participants (587 men and 460 women) died. Compared to those without sleep-disordered breathing (AHI: <5 events/h), the fully adjusted hazard ratios for all-cause mortality in those with mild (AHI: 5.0-14.9 events/h), moderate (AHI: 15.0-29.9 events/h), and severe (AHI: >or=30.0 events/h) sleep-disordered breathing were 0.93 (95% CI: 0.80-1.08), 1.17 (95% CI: 0.97-1.42), and 1.46 (95% CI: 1.14-1.86), respectively. Stratified analyses by sex and age showed that the increased risk of death associated with severe sleep-disordered breathing was statistically significant in men aged 40-70 y (hazard ratio: 2.09; 95% CI: 1.31-3.33). Measures of sleep-related intermittent hypoxemia, but not sleep fragmentation, were independently associated with all-cause mortality. Coronary artery disease-related mortality associated with sleep-disordered breathing showed a pattern of association similar to all-cause mortality. CONCLUSIONS: Sleep-disordered breathing is associated with all-cause mortality and specifically that due to coronary artery disease, particularly in men aged 40-70 y with severe sleep-disordered breathing. Please see later in the article for the Editors' Summary.