Synthesis of Acylation Polycyclic Derivatives via Regioselective Acylation/Cyclization of 1,7-Dienes with Acyl Oxime Esters.

A visible-light-induced radical cascade regioselective acylation/cyclization of 1,7-dienes with acyl oxime esters for the preparation of acylation polycyclic compounds via NCR-mediated C-C σ-bond cleavage is established. The transformation involves the cleavage of the C-C σ-bond in acyl oxime esters and selective addition of the electron neutral C═C bonds in 1,7-dienes for the synthesis of acyl polycyclic quinolinone derivatives, not the traditional seven-membered ring products. The strategy offers several advantages, including broad substrate tolerance, no need for bases, hyperstoichiometric radical initiators, and other auxiliaries.

Oxidant-Assisted Sulfonylation/Cyclization Cascade Synthesis of Alkylsulfonylated Oxindoles via the Insertion of SO2.

An oxidant-assisted tandem sulfonylation/cyclization of electron-deficient alkenes with 4-alkyl-substituted Hantzsch esters and Na2S2O5 for the preparation of 3-alkylsulfonylated oxindoles under mild conditions in the absence of a photocatalyst and transition metal catalyst is established. The mechanism studies show that the alkyl radicals, which come from the cleavage of the C-C bond in 4-substituted Hantzsch esters under oxidant conditions, subsequently undergo the in situ insertion of sulfur dioxide to generate the crucial alkylsulfonyl radical intermediates. This three-component reaction provides an efficient and facile route for the construction of alkylsulfonylated oxindoles and avoids the use of highly toxic alkylsulfonyl chlorides or alkylsulfonyl hydrazines as alkylsulfonyl sources.

Photoredox Ring Opening 1,2-Alkylarylation of Alkenes with Sulfonium Salts Toward Thioether-Substituted Oxindoles.

A novel strategy for the difunctionalization of electron-deficient alkenes with aryl sulfonium salts to access remote sulfur-containing oxindole derivatives by using in situ-formed copper(I)-based complexes as a photoredox catalyst is presented. This method enables the generation of the C(sp3)-centered radicals through site selective cleavage of the C-S bond of aryl sulfonium salts under mild conditions. Moreover, the oxidation reactions of desired products provide a new strategy for the preparation of sulfoxide or sulfone-containing compounds. Importantly, this approach can be easily applied to late-stage modification of pharmaceuticals molecules.

Skeletal Muscle Area on CT: Determination of an Optimal Height Scaling Power and Testing for Mortality Risk Prediction.

BACKGROUND. Sarcopenia is commonly assessed on CT by use of the skeletal muscle index (SMI), which is calculated as the skeletal muscle area (SMA) at L3 divided by patient height squared (i.e., a height scaling power of 2). OBJECTIVE. The purpose of this study was to determine the optimal height scaling power for SMA measurements on CT and to test the influence of the derived optimal scaling power on the utility of SMI in predicting all-cause mortality. METHODS. This retrospective study included 16,575 patients (6985 men, 9590 women; mean age, 56.4 years) who underwent abdominal CT from December 2012 through October 2018. The SMA at L3 was determined using automated software. The sample was stratified into two groups: 5459 patients without major medical conditions (based on ICD-9 and ICD-10 codes) who were included in the analysis for determining the optimal height scaling power and 11,116 patients with major medical conditions who were included for the purpose of testing this power. The optimal scaling power was determined by allometric analysis (whereby regression coefficients were fitted to log-linear sex-specific models relating height to SMA) and by analysis of statistical independence of SMI from height across scaling powers. Cox proportional hazards models were used to test the influence of the derived optimal scaling power on the utility of SMI in predicting all-cause mortality. RESULTS. In allometric analysis, the regression coefficient of log(height) in patients 40 years old and younger was 1.02 in men and 1.08 in women, and in patients older than 40 years old, it was 1.07 in men and 1.10 in women (all p < .05 vs regression coefficient of 2). In analyses for statistical independence of SMI from height, the optimal height scaling power (i.e., those yielding correlations closest to 0) was, in patients 40 years old and younger, 0.97 in men and 1.08 in women, whereas in patients older than 40 years old, it was 1.03 in men and 1.09 in women. In the Cox model used for testing, SMI predicted all-cause mortality with a higher concordance index using of a height scaling power of 1 rather than 2 in men (0.675 vs 0.663, p < .001) and in women (0.664 vs 0.653, p < .001). CONCLUSION. The findings support a height scaling power of 1, rather than a conventional power of 2, for SMI computation. CLINICAL IMPACT. A revised height scaling power for SMI could impact the utility of CT-based sarcopenia diagnoses in risk assessment.

Electro-oxidative three-component cascade coupling of isocyanides with elemental sulfur and amines for the synthesis of 2-aminobenzothiazoles.

2-Aminobenzothiazoles are commonly encountered in various functional compounds. Herein, we disclose an electro-oxidative three-component reaction for the effective synthesis of 2-aminobenzothiazoles under mild conditions, utilizing non-toxic and abundant elemental sulfur as the sulfur source. Both aliphatic amines and aryl amines demonstrate good compatibility at room temperature, highlighting the broad functional group tolerance of this approach. Additionally, elemental selenium demonstrated reactivities comparable to those of elemental sulfur.

Strength training is more effective than aerobic exercise for improving glycaemic control and body composition in people with normal-weight type 2 diabetes: a randomised controlled trial.

AIMS/HYPOTHESIS: Type 2 diabetes in people in the healthy weight BMI category (<25 kg/m2), herein defined as 'normal-weight type 2 diabetes', is associated with sarcopenia (low muscle mass). Given this unique body composition, the optimal exercise regimen for this population is unknown. METHODS: We conducted a parallel-group RCT in individuals with type 2 diabetes (age 18-80 years, HbA1c 47.5-118.56 mmol/mol [6.5-13.0%]) and BMI <25 kg/m2). Participants were recruited in outpatient clinics or through advertisements and randomly assigned to a 9 month exercise programme of strength training alone (ST), aerobic training alone (AER) or both interventions combined (COMB). We used stratified block randomisation with a randomly selected block size. Researchers and caregivers were blinded to participants' treatment group; however, participants themselves were not. Exercise interventions were conducted at community-based fitness centres. The primary outcome was absolute change in HbA1c level within and across the three groups at 3, 6 and 9 months. Secondary outcomes included changes in body composition at 9 months. Per adherence to recommended exercise protocol (PP) analysis included participants who completed at least 50% of the sessions. RESULTS: Among 186 individuals (ST, n=63; AER, n=58; COMB, n=65) analysed, the median (IQR) age was 59 (53-66) years, 60% were men and 83% were Asian. The mean (SD) HbA1c level at baseline was 59.6 (13.1) mmol/mol (7.6% [1.2%]). In intention-to-treat analysis, the ST group showed a significant decrease in HbA1c levels (mean [95% CI] -0.44 percentage points [-0.78, -0.12], p=0.002), while no significant change was observed in either the COMB group (-0.35 percentage points, p=0.13) or the AER group (-0.24 percentage points, p=0.10). The ST group had a greater improvement in HbA1c levels than the AER group (p=0.01). Appendicular lean mass relative to fat mass increased only in the ST group (p=0.0008), which was an independent predictor of HbA1c change (beta coefficient -7.16, p=0.01). Similar results were observed in PP analysis. Only one adverse event, in the COMB group, was considered to be possibly associated with the exercise intervention. CONCLUSIONS/INTERPRETATION: In normal-weight type 2 diabetes, strength training was superior to aerobic training alone, while no significant difference was observed between strength training and combination training for HbA1c reduction. Increased lean mass relative to decreased fat mass was an independent predictor of reduction in HbA1c level. TRIAL REGISTRATION: ClinicalTrials.gov NCT02448498. FUNDING: This study was funded by the National Institutes of Health (NIH; R01DK081371).

Design and rationale of re-energize fontan: Randomized exercise intervention designed to maximize fitness in fontan patients.

In this manuscript, we describe the design and rationale of a randomized controlled trial in pediatric Fontan patients to test the hypothesis that a live-video-supervised exercise (aerobic+resistance) intervention will improve cardiac and physical capacity; muscle mass, strength, and function; and endothelial function. Survival of children with single ventricles beyond the neonatal period has increased dramatically with the staged Fontan palliation. Yet, long-term morbidity remains high. By age 40, 50% of Fontan patients will have died or undergone heart transplantation. Factors that contribute to onset and progression of heart failure in Fontan patients remain incompletely understood. However, it is established that Fontan patients have poor exercise capacity which is associated with a greater risk of morbidity and mortality. Furthermore, decreased muscle mass, abnormal muscle function, and endothelial dysfunction in this patient population is known to contribute to disease progression. In adult patients with 2 ventricles and heart failure, reduced exercise capacity, muscle mass, and muscle strength are powerful predictors of poor outcomes, and exercise interventions can not only improve exercise capacity and muscle mass, but also reverse endothelial dysfunction. Despite these known benefits of exercise, pediatric Fontan patients do not exercise routinely due to their chronic condition, perceived restrictions to exercise, and parental overprotection. Limited exercise interventions in children with congenital heart disease have demonstrated that exercise is safe and effective; however, these studies have been conducted in small, heterogeneous groups, and most had few Fontan patients. Critically, adherence is a major limitation in pediatric exercise interventions delivered on-site, with adherence rates as low as 10%, due to distance from site, transportation difficulties, and missed school or workdays. To overcome these challenges, we utilize live-video conferencing to deliver the supervised exercise sessions. Our multidisciplinary team of experts will assess the effectiveness of a live-video-supervised exercise intervention, rigorously designed to maximize adherence, and improve key and novel measures of health in pediatric Fontan patients associated with poor long-term outcomes. Our ultimate goal is the translation of this model to clinical application as an "exercise prescription" to intervene early in pediatric Fontan patients and decrease long-term morbidity and mortality.

Visible-Light-Promoted Decarboxylative Alkylation/Cyclization of Vinylcycloalkanes.

An efficient strategy for visible-light-promoted decarboxylative alkylation of vinylcyclopropanes with alkyl N-(acyloxy)phthalimide esters through the dual C-C bond and single N-O bond cleavage, employing triphenylphosphine and lithium iodide as the photoredox system to synthesize 2-alkylated 3,4-dihydronaphthalenes, has been established. This alkylation/cyclization involves a radical process and undergoes a sequence of N-(acyloxy)phthalimide ester single-electron reduction, N-O bond cleavage, decarboxylative, alkyl radical addition, C-C bond cleavage, and intramolecular cyclization. Moreover, using the photocatalyst Na2-Eosin Y instead of triphenylphosphine and lithium iodide, the vinyl transfer products are acquired when vinylcyclobutanes or vinylcyclopentanes are utilized as alkyl radical receptors.

Recent advances in ring-opening of cyclobutanone oximes for capturing SO2, CO or O2via a radical process.

Cyclobutanone oximes and their derivatives are pivotal core structural motifs in organic chemistry. Iminyl-radical-triggered C-C bond cleavage of cyclobutanone oximes delivers an efficient strategy to produce stable distal cyano-substituted alkyl radicals, which can capture SO2, CO or O2 to form cyanoalkylsulfonyl radicals, cyanoalkylcarbonyl radicals or cyanoalkoxyl radicals under mild conditions. In the past several years, cyanoalkylsulfonylation/cyanoalkylcarbonyaltion/cyanoalkoxylation has attracted a lot of interest. In this updated report, the strategies for trapping SO2, CO or O2via iminyl-radical-triggered ring-opening of cyclobutanone oximes are summarized.

Conceptual framework and documentation standards of cystoscopic media content for artificial intelligence.

BACKGROUND: The clinical documentation of cystoscopy includes visual and textual materials. However, the secondary use of visual cystoscopic data for educational and research purposes remains limited due to inefficient data management in routine clinical practice. METHODS: A conceptual framework was designed to document cystoscopy in a standardized manner with three major sections: data management, annotation management, and utilization management. A Swiss-cheese model was proposed for quality control and root cause analyses. We defined the infrastructure required to implement the framework with respect to FAIR (findable, accessible, interoperable, reusable) principles. We applied two scenarios exemplifying data sharing for research and educational projects to ensure compliance with FAIR principles. RESULTS: The framework was successfully implemented while following FAIR principles. The cystoscopy atlas produced from the framework could be presented in an educational web portal; a total of 68 full-length qualitative videos and corresponding annotation data were sharable for artificial intelligence projects covering frame classification and segmentation problems at case, lesion, and frame levels. CONCLUSION: Our study shows that the proposed framework facilitates the storage of visual documentation in a standardized manner and enables FAIR data for education and artificial intelligence research.

Efficient resolution of 4-chlormandelic acid enantiomers using lipase@UiO-67(Zr) zirconium-organic frameworks in organic solvent.

A new biocatalyst PCL@UiO-67(Zr) was successfully synthesized by immobilized lipases on metal-organic frameworks (MOFs) materials. Compare with free lipases, zirconium foundation organic framework material UiO-67(Zr) modification on immobilized lipases Pseudomonas cepacia lipase (PCL) great boosts their enantioselectivity in the kinetic resolution racemic 4-chloro-mandelic acid (4-ClMA) on the organic solvent. The acquired bio-composite PCL@UiO-67(Zr) was fully characterized by powder X-ray diffraction (PXRD), Fourier transform infrared (FT-IR) spectroscopy, N2 adsorption-desorption isotherm and aperture distribution map, and scanning electron microscopy (SEM). The catalytic performance of PCL@UiO-67(Zr), such as temperature, reaction time, and lipase quantity, were deeply explored. The experiment results showed resolution racemic 4-ClMA optimum conditions that 20 mmol/L of (R, S)-4-chloromandelic acid, 120 mmol/L vinyl acetate, 30-mg immobilized lipases PCL@UiO-67(Zr), 2 mL of MTBE, 500 rpm, and under the 55°C reaction 18 h. In this optimum conditions, c and eep could reach up to 47.6% and 98.7%, respectively.

Cystatin C and Creatinine Concentrations Are Uninformative Biomarkers of Sarcopenia: A Cross-Sectional NHANES Study.

OBJECTIVES: Differences in creatinine and cystatin C-based estimates of glomerular filtration rate (eGFRDiff = eGFRCr - eGFRCysC) may reflect differences in muscle mass. We sought to determine if eGFRDiff (1) reflects lean mass, (2) identifies sarcopenic individuals beyond estimates based on age, body mass index (BMI), and sex; and (3) demonstrates associations differently in those with and without chronic kidney disease (CKD). DESIGN AND METHODS: This cross-sectional study included 3,754 participants, ages 20-85 years, with creatinine and cystatin C concentration levels, and dual-energy X-ray absorptiometry scans from National Health and Nutrition Examination Survey data (1999-2006). Dual-energy X-ray absorptiometry-derived appendicular lean mass index (ALMI) estimated muscle mass. Non-race-based CKD Epidemiology Collaboration equations estimated glomerular filtration rate using eGFRCr, eGFRCysC, and both biomarkers (eGFRCysC&Cr). CKD was defined as eGFRCysC&Cr <60 mL/minute/1.73 m2. ALMI sex-specific T-scores (compared with young adult) < -2.0 defined sarcopenia. In estimating ALMI, we compared the coefficient of determination (R2) values from: 1) eGFRDiff, 2) clinical characteristics (age, BMI, and sex), and 3) clinical characteristics plus eGFRDiff. Using logistic regression, we evaluated each model's C-statistic to diagnose sarcopenia. RESULTS: eGFRDiff was negatively and weakly associated with ALMI (No CKD: R2 = 0.006, p-value 0.002; CKD: R2 = 0.001, P value .9). Clinical characteristics explained most of the variation in ALMI (No CKD: R2 = 0.851, CKD: R2 = 0.828), and provided strong discrimination of sarcopenia (No CKD C-statistic: 0.950; CKD C-statistic: 0.943). Adding eGFRDiff improved the R2 by 0.025, and the C-statistic by 0.003. Tests for interaction between eGFRDiff and CKD were not significant (all P values > .05). CONCLUSIONS: Although eGFRDiff has statistically significant associations with ALMI and sarcopenia in univariate analyses, multivariate analyses demonstrate that eGFRDiff does not capture more information beyond routine clinical characteristics (age, BMI, and sex).

Intermolecular 1,2-Difunctionalization of Alkenes Enabled by Fluoroamide-Directed Remote Benzyl C(sp3)-H Functionalization.

A copper-catalyzed remote benzylic C-H functionalization strategy enabling 1,2-difunctionalization of alkenes with 2-methylbenzeneamides and nucleophiles, including alcohols, indoles, pyrroles, and the intrinsic amino groups, is reported, which is characterized by its redox-neutral conditions, exquisite site-selectivity, broad substrate scope, and wide utilizations of late-stage modifying bioactive molecules. This reaction proceeds through nitrogen-centered radical generation, hydrogen atom transfer, benzylic radical addition across the alkenes, single-electron oxidation, and carbocation electrophilic course cascades. While using external nucleophiles manipulates three-component alkene alkylalkoxylation and alkyl-heteroarylation with 2-methylbenzeneamides to access dialkyl ethers, 3-alkylindoles, and 3-alkylpyrroles, omitting the external nucleophiles results in two-component alkylamidation ([5+2] annulation) of alkenes with 2-methylbenzeneamides to benzo-[f][1,2]thiazepine 1,1-dioxides.

Gemcitabine and Cisplatin Induction Chemotherapy in Nasopharyngeal Carcinoma.

BACKGROUND: Platinum-based concurrent chemoradiotherapy is the standard of care for patients with locoregionally advanced nasopharyngeal carcinoma. Additional gemcitabine and cisplatin induction chemotherapy has shown promising efficacy in phase 2 trials. METHODS: In a parallel-group, multicenter, randomized, controlled, phase 3 trial, we compared gemcitabine and cisplatin as induction chemotherapy plus concurrent chemoradiotherapy with concurrent chemoradiotherapy alone. Patients with locoregionally advanced nasopharyngeal carcinoma were randomly assigned in a 1:1 ratio to receive gemcitabine (at a dose of 1 g per square meter of body-surface area on days 1 and 8) plus cisplatin (80 mg per square meter on day 1), administered every 3 weeks for three cycles, plus chemoradiotherapy (concurrent cisplatin at a dose of 100 mg per square meter every 3 weeks for three cycles plus intensity-modulated radiotherapy) or chemoradiotherapy alone. The primary end point was recurrence-free survival (i.e., freedom from disease recurrence [distant metastasis or locoregional recurrence] or death from any cause) in the intention-to-treat population. Secondary end points included overall survival, treatment adherence, and safety. RESULTS: A total of 480 patients were included in the trial (242 patients in the induction chemotherapy group and 238 in the standard-therapy group). At a median follow-up of 42.7 months, the 3-year recurrence-free survival was 85.3% in the induction chemotherapy group and 76.5% in the standard-therapy group (stratified hazard ratio for recurrence or death, 0.51; 95% confidence interval [CI], 0.34 to 0.77; P = 0.001). Overall survival at 3 years was 94.6% and 90.3%, respectively (stratified hazard ratio for death, 0.43; 95% CI, 0.24 to 0.77). A total of 96.7% of the patients completed three cycles of induction chemotherapy. The incidence of acute adverse events of grade 3 or 4 was 75.7% in the induction chemotherapy group and 55.7% in the standard-therapy group, with a higher incidence of neutropenia, thrombocytopenia, anemia, nausea, and vomiting in the induction chemotherapy group. The incidence of grade 3 or 4 late toxic effects was 9.2% in the induction chemotherapy group and 11.4% in the standard-therapy group. CONCLUSIONS: Induction chemotherapy added to chemoradiotherapy significantly improved recurrence-free survival and overall survival, as compared with chemoradiotherapy alone, among patients with locoregionally advanced nasopharyngeal carcinoma. (Funded by the Innovation Team Development Plan of the Ministry of Education and others; ClinicalTrials.gov number, NCT01872962.).

Sarcopenic obesity in rheumatoid arthritis: prevalence and impact on physical functioning.

OBJECTIVE: We determined the prevalence of sarcopenic obesity in patients with RA using multiple methods and assessed associations with physical functioning. METHODS: This study evaluated data from three RA cohorts. Whole-body dual-energy absorptiometry (DXA) measures of appendicular lean mass index (ALMI, kg/m2) and fat mass index (FMI) were converted to age, sex and race-specific Z-Scores and categorized using a recently validated method and compared it to a widely-used existing method. The prevalence of body composition abnormalities in RA was compared with two reference populations. In the RA cohorts, associations between body composition and change in the HAQ and the Short Physical Performance Battery (SPPB) in follow-up were assessed using linear and logistic regression, adjusting for age, sex, race and study. RESULTS: The prevalence of low lean mass and sarcopenic obesity was higher in patients with RA (14.2; 12.6%, respectively) compared with the reference population cohorts (7-10%; 4-4.5%, respectively, all P <0.05). There was only moderate agreement among methods of sarcopenic obesity categorization (Kappa 0.45). The recently validated method categorized fewer subjects as obese, and many of these were categorized as low lean mass only. Low lean mass, obesity and sarcopenic obesity were each associated with higher HAQ and lower SPPB at baseline and numerically greater worsening. CONCLUSION: RA patients had higher rates of low lean mass and sarcopenic obesity than the general population. The recently validated methods characterized body composition changes differently from traditional methods and were more strongly associated with physical function.

Revealing the Effect of Surface Composition on Multiwalled Carbon Nanotubes Supported Pt-Fe Alloy Electrocatalysts for Methanol Oxidation Performance.

The designs of efficient and inexpensive Pt-based catalysts for methanol oxidation reaction (MOR) are essential to boost the commercialization of direct methanol fuel cells. Here, the highly catalytic performance PtFe alloys supported on multiwalled carbon nanotubes (MWCNTs) decorating nitrogen-doped carbon (NC) have been successfully prepared via co-engineering of the surface composition and electronic structure. The Pt1 Fe3 @NC/MWCNTs catalyst with moderate Fe3+ feeding content (0.86 mA/mgPt ) exhibits 2.26-fold enhancement in MOR mass activity compared to pristine Pt/C catalyst (0.38 mA/mgPt ). Furthermore, the CO oxidation initial potential of Pt1 Fe3 @NC/MWCNTs catalyst is lower relative to Pt/C catalyst (0.71 V and 0.80 V). Benefited from the optimal surface compositions, the anti-corrosion ability of MWCNT, strong electron interaction between PtFe alloys and MWCNTs and the N-doped carbon (NC) layer, the Pt1 Fe3 @NC/MWCNTs catalyst presents an improved MOR performance and anti-CO poisoning ability. This study would open up new perspective for designing efficient electrocatalysts for the DMFCs field.

Tracking the Stepwise Formation of a Water-Soluble Fluorescent Tb12 Cluster for Efficient Doxorubicin Detection.

Doxorubicin (DOX) is an anthraquinone drug used for the efficient treatment of a variety of tumors in human beings. Unfortunately, its poor biodegradability causes incomplete metabolism in the body. Therefore, it is of great significance to synthesize a sensitive and selective material for DOX detection. In this paper, we report a water-soluble Tb12 cluster and track its step-by-step formation (L → Tb1L1 → Tb2L1 → Tb2L2 → Tb3L2 → Tb4L2 → Tb12L6). Tb12 can be used to determine the presence of DOX, which quenches the luminescence of the Tb12 aqueous solution, and the detection limit can reach 13 nM (KSV = 8.7 × 105 M-1). Tb12 has advantages of high sensitivity and high selectivity for the detection of DOX in a simulated environment of human urine and serum.

Visible-light-promoted radical cascade alkylation/cyclization: access to alkylated indolo/benzoimidazo[2,1-a]isoquinolin-6(5H)-ones.

A new protocol is herein described for the direct generation of alkylated indolo/benzoimidazo[2,1-a]isoquinolin-6(5H)-one derivatives by using Hantzsch esters as alkylation radical precursors using a photoredox/K2S2O8 system. This oxidative alkylation of active alkenes involves a radical cascade cyclization process and a sequence of Hantzsch ester single electron oxidation, C-C bond cleavage, alkylation, arylation and oxidative deprotonation.

Deep learning model for the prediction of microsatellite instability in colorectal cancer: a diagnostic study.

BACKGROUND: Detecting microsatellite instability (MSI) in colorectal cancer is crucial for clinical decision making, as it identifies patients with differential treatment response and prognosis. Universal MSI testing is recommended, but many patients remain untested. A critical need exists for broadly accessible, cost-efficient tools to aid patient selection for testing. Here, we investigate the potential of a deep learning-based system for automated MSI prediction directly from haematoxylin and eosin (H&E)-stained whole-slide images (WSIs). METHODS: Our deep learning model (MSINet) was developed using 100 H&E-stained WSIs (50 with microsatellite stability [MSS] and 50 with MSI) scanned at 40× magnification, each from a patient randomly selected in a class-balanced manner from the pool of 343 patients who underwent primary colorectal cancer resection at Stanford University Medical Center (Stanford, CA, USA; internal dataset) between Jan 1, 2015, and Dec 31, 2017. We internally validated the model on a holdout test set (15 H&E-stained WSIs from 15 patients; seven cases with MSS and eight with MSI) and externally validated the model on 484 H&E-stained WSIs (402 cases with MSS and 77 with MSI; 479 patients) from The Cancer Genome Atlas, containing WSIs scanned at 40× and 20× magnification. Performance was primarily evaluated using the sensitivity, specificity, negative predictive value (NPV), and area under the receiver operating characteristic curve (AUROC). We compared the model's performance with that of five gastrointestinal pathologists on a class-balanced, randomly selected subset of 40× magnification WSIs from the external dataset (20 with MSS and 20 with MSI). FINDINGS: The MSINet model achieved an AUROC of 0·931 (95% CI 0·771-1·000) on the holdout test set from the internal dataset and 0·779 (0·720-0·838) on the external dataset. On the external dataset, using a sensitivity-weighted operating point, the model achieved an NPV of 93·7% (95% CI 90·3-96·2), sensitivity of 76·0% (64·8-85·1), and specificity of 66·6% (61·8-71·2). On the reader experiment (40 cases), the model achieved an AUROC of 0·865 (95% CI 0·735-0·995). The mean AUROC performance of the five pathologists was 0·605 (95% CI 0·453-0·757). INTERPRETATION: Our deep learning model exceeded the performance of experienced gastrointestinal pathologists at predicting MSI on H&E-stained WSIs. Within the current universal MSI testing paradigm, such a model might contribute value as an automated screening tool to triage patients for confirmatory testing, potentially reducing the number of tested patients, thereby resulting in substantial test-related labour and cost savings. FUNDING: Stanford Cancer Institute and Stanford Departments of Pathology and Biomedical Data Science.

Artificial Intelligence Algorithm Improves Radiologist Performance in Skeletal Age Assessment: A Prospective Multicenter Randomized Controlled Trial.

Background Previous studies suggest that use of artificial intelligence (AI) algorithms as diagnostic aids may improve the quality of skeletal age assessment, though these studies lack evidence from clinical practice. Purpose To compare the accuracy and interpretation time of skeletal age assessment on hand radiograph examinations with and without the use of an AI algorithm as a diagnostic aid. Materials and Methods In this prospective randomized controlled trial, the accuracy of skeletal age assessment on hand radiograph examinations was performed with (n = 792) and without (n = 739) the AI algorithm as a diagnostic aid. For examinations with the AI algorithm, the radiologist was shown the AI interpretation as part of their routine clinical work and was permitted to accept or modify it. Hand radiographs were interpreted by 93 radiologists from six centers. The primary efficacy outcome was the mean absolute difference between the skeletal age dictated into the radiologists' signed report and the average interpretation of a panel of four radiologists not using a diagnostic aid. The secondary outcome was the interpretation time. A linear mixed-effects regression model with random center- and radiologist-level effects was used to compare the two experimental groups. Results Overall mean absolute difference was lower when radiologists used the AI algorithm compared with when they did not (5.36 months vs 5.95 months; P = .04). The proportions at which the absolute difference exceeded 12 months (9.3% vs 13.0%, P = .02) and 24 months (0.5% vs 1.8%, P = .02) were lower with the AI algorithm than without it. Median radiologist interpretation time was lower with the AI algorithm than without it (102 seconds vs 142 seconds, P = .001). Conclusion Use of an artificial intelligence algorithm improved skeletal age assessment accuracy and reduced interpretation times for radiologists, although differences were observed between centers. Clinical trial registration no. NCT03530098 © RSNA, 2021 Online supplemental material is available for this article. See also the editorial by Rubin in this issue.