Surface coating by mechanofusion modulates bulk charging pathways and battery performance of Ni-rich layered cathodes.

Ni-rich layered oxides as high-capacity battery cathodes suffer from degradation at high voltages. We utilize a dry surface modification method, mechanofusion (MF), to achieve enhanced battery stability. The simplicity, high yield, and flexibility make it cost-effective and highly attractive for processing at the industrial scale. The underlying mechanisms responsible for performance improvement are unveiled by a systematic study combining multiple probes, e.g., 3D nano-tomography, spectroscopic imaging, in situ synchrotron diffraction, and finite element analysis (FEA). MF affects the bulk crystallography by introducing partially disordered structure, microstrain, and local lattice variation. Furthermore, the crack initiation and propagation pattern during delithiation are regulated and the overall mechanical fracture is reduced after such surface coating. We validate that MF can alter the bulk charging pathways. Such a synergic effect between surface modification and bulk charge distribution is fundamentally important for designing next-generation battery cathode materials.

Solvent-Mediated, Reversible Ternary Graphite Intercalation Compounds for Extreme-Condition Li-Ion Batteries.

Traditional Li-ion intercalation chemistry into graphite anodes exclusively utilizes the cointercalation-free or cointercalation mechanism. The latter mechanism is based on ternary graphite intercalation compounds (t-GICs), where glyme solvents were explored and proved to deliver unsatisfactory cyclability in LIBs. Herein, we report a novel intercalation mechanism, that is, in situ synthesis of t-GIC in the tetrahydrofuran (THF) electrolyte via a spontaneous, controllable reaction between binary-GIC (b-GIC) and free THF molecules during initial graphite lithiation. The spontaneous transformation from b-GIC to t-GIC, which is different from conventional cointercalation chemistry, is characterized and quantified via operando synchrotron X-ray and electrochemical analyses. The resulting t-GIC chemistry obviates the necessity for complete Li-ion desolvation, facilitating rapid kinetics and synchronous charge/discharge of graphite particles, even under high current densities. Consequently, the graphite anode demonstrates unprecedented fast charging (1 min), dendrite-free low-temperature performance, and ultralong lifetimes exceeding 10 000 cycles. Full cells coupled with a layered cathode display remarkable cycling stability upon a 15 min charging and excellent rate capability even at -40 °C. Furthermore, our chemical strategies are shown to extend beyond Li-ion batteries to encompass Na-ion and K-ion batteries, underscoring their broad applicability. Our work contributes to the advancement of graphite intercalation chemistry and presents a low-cost, adaptable approach for achieving fast-charging and low-temperature batteries.

Dual-Region Computed Tomography Radiomics-Based Machine Learning Predicts Subcarinal Lymph Node Metastasis in Patients with Non-small Cell Lung Cancer.

BACKGROUND: Noninvasively and accurately predicting subcarinal lymph node metastasis (SLNM) for patients with non-small cell lung cancer (NSCLC) remains challenging. This study was designed to develop and validate a tumor and subcarinal lymph nodes (tumor-SLNs) dual-region computed tomography (CT) radiomics model for predicting SLNM in NSCLC. METHODS: This retrospective study included NSCLC patients who underwent lung resection and SLNs dissection between January 2017 and December 2020. The radiomic features of the tumor and SLNs were extracted from preoperative CT, respectively. Ninety machine learning (ML) models were developed based on tumor region, SLNs region, and tumor-SLNs dual-region. The model performance was assessed by the area under the curve (AUC) and validated internally by fivefold cross-validation. RESULTS: In total, 202 patients were included in this study. ML models based on dual-region radiomics showed good performance for SLNM prediction, with a median AUC of 0.794 (range, 0.686-0.880), which was superior to those of models based on tumor region (median AUC, 0.746; range, 0.630-0.811) and SLNs region (median AUC, 0.700; range, 0.610-0.842). The ML model, which is developed by using the naive Bayes algorithm and dual-region features, had the highest AUC of 0.880 (range of cross-validation, 0.825-0.937) among all ML models. The optimal logistic regression model was inferior to the optimal ML model for predicting SLNM, with an AUC of 0.727. CONCLUSIONS: The CT radiomics showed the potential for accurately predicting SLNM in NSCLC patients. The ML model with dual-region radiomic features has better performance than the logistic regression or single-region models.

Multi-Parameter Estimation Method and Closed-Form Solution Study for k-µ Channel Model.

This paper proposes a novel multi-parameter estimation algorithm for the k-µ fading channel model to analyze wireless transmission performance in complex time-varying and non-line-of-sight communication scenarios involving moving targets. The proposed estimator offers a mathematically tractable theoretical framework for the application of the k-µ fading channel model in realistic scenarios. Specifically, the algorithm obtains expressions for the moment-generating function of the k-µ fading distribution and eliminates the gamma function using the even-order moment value comparison method. It then obtains two sets of solution models for the moment-generating function at different orders, which enable the estimation of the k and µ parameters using three sets of closed-form solutions. The k and µ parameters are estimated based on received channel data samples generated using the Monte Carlo method to restore the distribution envelope of the received signal. Simulation results show strong agreement between theoretical and estimated values for the closed-form estimated solutions. Additionally, the differences in complexity, accuracy exhibited under different parameter settings, and robustness under decreasing SNR may make the estimators suitable for different practical application scenarios.

Sacubitril/Valsartan Cannot Improve Cardiac Function Compared with Valsartan in Patients Suffering Nonvalvular Atrial Fibrillation without Systolic Heart Failure.

This study investigates the effect of sacubitril/valsartan (Sac/Val) in patients diagnosed with nonvalvular atrial fibrillation (AF) without systolic heart failure (SHF).Nonvalvular AF patients without SHF admitted to the People's Hospital of Bortala Mongol Autonomous Prefecture from December 2020 to December 2021 were enrolled and randomly divided into Sac/Val treatment group (group T) and valsartan treatment group (group C, control). For subgroup analysis, patients were divided into subgroups with and without diastolic heart failure (DHF). After 1-month adaptive phase and subsequent 3-month treatment period, patients were followed up in the cardiology clinic. Plasma levels of biochemical markers and echocardiographic parameters before and after treatment were evaluated, and DHF scores were computed to assess diastolic function.Of 61 enrolled patients, 46 patients completed follow-up. Sac/Val treatment did not increase the percentage of sinus rhythm. Although N-terminal pro-B-type natriuretic peptide (NT-proBNP) expression tended to be reduced in both groups after 3 months of treatment, the differences compared with respective baseline levels and between groups were not significant. According to subgroup analysis, although NT-proBNP expression in the subgroup with DHF was lower at follow-up compared to baseline, the difference was not statistically significant. Similarly, no marked differences in echocardiographic parameters or tissue Doppler parameters related to DHF were detected between the groups (P > 0.05). Additionally, a subgroup analysis found no significant variations in the echocardiographic measures (P > 0.05).Sac/Val is not superior to valsartan for the short-term treatment of patients suffering with AF without SHF in improving NT-proBNP level and cardiac function.

Use of local wound infiltration in open hepatectomy to reduce wound pain: A systematic review and meta-analysis.

The aim of this study was to assess the effects of local wound infiltration anaesthesia on postoperative wound pain in patients undergoing open liver resection. The Cochrane Library, PubMed, EMBASE, China National Knowledge Infrastructure (CNKI), Chinese Biomedical Literature Database (CBM) and Wanfang databases were searched. The search period spanned from database creation to December 2022. All relevant studies on local wound infiltration anaesthesia for analgesia after hepatectomy were included. Two investigators independently screened the literature, extracted data and evaluated the quality of each study. Review Manager (RevMan) 5.4 software (Cochrane Collaboration) was used for the meta-analysis, in which 12 studies with 986 patients were included. The results show that local wound infiltration anaesthesia effectively reduced surgical site wound pain at 4 h (mean difference [MD]: -1.26, 95% confidence intervals [CIs]: -2.15 to -0.37, P = .005), 12 h (MD: -0.84, 95% CIs: -1.26 to -0.42, P < .001), 24 h (MD: -0.57, 95% CIs: -1.01 to -0.14, P = .009) and 48 h (MD: -0.54, 95% CIs: -0.81 to -0.26, P < .001) postoperatively; however, there was no significant difference in analgesia at 72 h postoperatively (MD: -0.10, 95% CIs: -0.80 to 0.59, P = .77). These findings suggest that local wound infiltration anaesthesia administered to patients undergoing open liver resection provides good postoperative wound analgesia at the surgical site.

Rigid registration algorithm based on the minimization of the total variation of the difference map.

Image registration is broadly used in various scenarios in which similar scenes in different images are to be aligned. However, image registration becomes challenging when the contrasts and backgrounds in the images are vastly different. This work proposes using the total variation of the difference map between two images (TVDM) as a dissimilarity metric in rigid registration. A method based on TVDM minimization is implemented for image rigid registration. The method is tested with both synthesized and real experimental data that have various noise and background conditions. The performance of the proposed method is compared with the results of other rigid registration methods. It is demonstrated that the proposed method is highly accurate and robust and outperforms other methods in all of the tests. The new algorithm provides a robust option for image registrations that are critical to many nano-scale X-ray imaging and microscopy applications.

Bi-allelic SPATA22 variants cause premature ovarian insufficiency and nonobstructive azoospermia due to meiotic arrest.

The genetic causes of idiopathic premature ovarian insufficiency (POI) and nonobstructive azoospermia (NOA) remain unclear. We performed whole-exome sequencing (WES) in members of a consanguineous family with two POI and two NOA patients to screen for potential pathogenic variants for familial POI and NOA. And a homozygous variant in SPATA22 (c.400C>T:p.R134X) was identified. Histological analysis and spermatocyte spreading assay demonstrated that the spermatogenesis was arrested at a zygotene-like stage in the proband with NOA. The candidate gene was further screened in the in-house WES database of idiopathic POI-affected patients. One additional compound heterozygous variant in SPATA22 (c.900+1G>A and c.31C>T:p.R11X) was found in one patient with sporadic POI and validated by minigene assay. Thus, this is the first report identifying SPATA22 as the causative gene for human POI. Combined with the observations in the familial patient with NOA, our findings highlighted the essential role of meiotic HR genes in gametogenesis and gonadal function maintenance.

Exploring the Agrobacterium-mediated transformation with CRISPR/Cas9 in cucumber (Cucumis sativus L.).

BACKGROUNDS: The narrow genetic basis of cucumber makes breeding of this species difficult. CRISPR/Cas9 system is  characteristic of  simple design, low cost and  high efficiency, which has opened a new path for cucumber functional genetics and the development of cucumber mocular breeding. However, the immature genetic transformation system is the main limiting factor for applying this technology in cucumber. METHODS AND RESULTS: In this study, a Histochemical ß-glucuronidase (GUS) assay was used to analyze the effect of various parameters, including slight scratch of explants, pre-culture time, acetosyringone (AS) concentration, infection time in Agrobacterium solution, and co-culture period on the transformation efficiency. The results showed that the explants slightly scratched after cutting, pre-cultured for 1 day, Agrobacterium bacterial solution containing AS, and 20 min length of infection could significantly increase the GUS staining rate of explants. On this basis, two sequences with high specificity (sgRNA-1 and sgRNA-2) targeted different loci of gene CsGCN5 were designed. The corresponding vectors Cas9-sgRNA-1 and Cas9-sgRNA-2 were constructed and transformed using the above-optimized cucumber genetic transformation system, and three and two PCR positive lines were obtained from 210 and 207 explants, respectively. No sequence mutation at target loci of CsGCN5 was detected in the Cas9-sgRNA-1 transformed three PCR positive lines. However, one mutant line with targeted homozygous change was recognized from the Cas9-sgRNA-2 transformed two PCR positive lines. CONCLUSION: In this study, 2.4‰ of total explants had directed mutation in the CsGCN5 gene. The results in the present study would be beneficial to further optimize and improve the efficiency of the genetic transformation of cucumber.

Effect of urinary catheter removal on different time after hysterectomy: a network meta-analysis.

INTRODUCTION AND HYPOTHESIS: The optimal timing for removing urinary catheters is controversial for patients undergoing total hysterectomy. This study aimed to evaluate the optimal time for removing urinary catheters post-hysterectomy. METHODS: We searched multiple databases from inception till December 31, 2020, for all randomized trials evaluating the timing of catheter removal following hysterectomy. All studies were evaluated by two investigators independently depending on inclusion and exclusion criteria. Network meta-analysis (NMA) was conducted on the data using Stata 14.0 software. RESULTS: A total of 12 articles involving 1814 patients were ultimately included. This study showed removing urinary catheters 12.1 to 24 h (pooled OR = 2.67; 95% CI, 1.53­4.67) and 36.1 to 48 h (pooled OR = 8.11;95% CI, 3.78­17.36) post-hysterectomy increased the risk of urinary tract infection (UTI) compared with immediate catheter removal. Timing of catheter removal in other groups following hysterectomy accompanied a reduced risk of urinary retention (UR) versus immediate catheter removal (P < 0.05). Removal of the urinary catheter from 36.1 to 48 h was most likely to lead to UTI. The maximum SUCRA value of immediate catheter removal after hysterectomy was 99.3% for UR. Catheter removal 24.1 to 36 h after hysterectomy was the best time for preventing UR. CONCLUSION: Removal of the catheter immediately after hysterectomy may be the optimal time for preventing UTI with increased risk of UR, whereas removal time of the urinary catheters within 6 h post-hysterectomy combined with postoperative urination monitoring might be more beneficial than other removal times following hysterectomy.

Effect of WeChat Messaging on Improving the Quality of Bowel Preparation for Outpatient Colonoscopy: A Randomized Controlled Study.

With the most active users of any social media platform in China, WeChat has become the preferred platform for public announcements and is widely used in the fields of medicine and nursing (Hong, Zhou, Fang, & Shi, 2017; Zeng, Deng, Wang, & Liu, 2016). The aim of this study was to evaluate the effect of WeChat messaging on bowel preparation for outpatient colonoscopy. A total of 150 outpatients scheduled for colonoscopy in a Grade III level A hospital were randomly assigned to the experimental group (n = 73) or the control group (n = 72). Both groups received routine guidance from the day of the scheduling appointment through the day of colonoscopy. In addition, the experimental group received colonoscopy-related information and individualized guidance daily through WeChat from the day of the appointment. After the colonoscopy, the diet and medication compliance, satisfaction, anxiety, and bowel cleanliness were compared. Post-intervention, there were significant differences in bowel cleanliness, satisfaction, diet and medication compliance, and anxiety between the two groups. WeChat messaging can help improve diet and medication compliance, patient satisfaction, and the success rate and thoroughness of colonoscopy, as well as alleviate the anxiety of patients scheduled for outpatient colonoscopy.

Polyphenylene Sulfide-Based Solid-State Separator for Limited Li Metal Battery.

The urgent need for high energy batteries is pushing the battery studies toward the Li metal and solid-state direction, and the most central question is finding proper solid-state electrolyte (SSE). So far, the recently studied electrolytes have obvious advantages and fatal weaknesses, resulting in indecisive plans for industrial production. In this work, a thin and dense lithiated polyphenylene sulfide-based solid state separator (PPS-SSS) prepared by a solvent-free process in pilot stage is proposed. Moreover, the PPS surface is functionalized to immobilize the anions, increasing the Li+ transference number to 0.8-0.9, and widening the electrochemical potential window (EPW > 5.1 V). At 25 °C, the PPS-SSS exhibits high intrinsic Li+ diffusion coefficient and ionic conductivity (>10-4 S cm-1 ), and Li+ transport rectifying effect, resulting in homogenous Li-plating on Cu at 2 mA cm-2 density. Based on the limited Li-plated Cu anode or anode-free Cu, high loadings cathode and high voltage, the Li-metal batteries (LMBs) with polyethylene (PE) protected PPS-SSSs deliver high energy and power densities (>1000 Wh L-1 and 900 W L-1 ) with >200 cycling life and high safety, exceeding those of state-of-the-art Li-ion batteries. The results promote the Li metal battery toward practicality.

Highly stable multiple-access underwater frequency transfer with terminal phase compensation.

A multiple-access underwater frequency transfer scheme using terminal phase compensation is demonstrated. With this scheme, a highly stable 100 MHz frequency signal was disseminated over a 3 m underwater link for 5000 s. The timing fluctuation and fractional frequency instability were both measured and analyzed. The experimental results show that with the phase compensation technique, the total root-mean-square (RMS) timing fluctuation is about 3 ps, and the fractional frequency instabilities are on the order of 5.9×10-13 at 1 s and 5.3×10-15 at 1000 s. The experiment results indicate that the proposed frequency transfer technique has a potential application of disseminating an atomic clock to multiple terminals.

Laser-based underwater frequency transfer with sub-picosecond timing fluctuation using optical phase compensation.

We demonstrated a sub-picosecond laser-based underwater frequency transfer with an optical phase compensation. With this transfer technique, a highly-stable 500 MHz radio-frequency (RF) signal was disseminated over a 5-m underwater link for 5000 s, and the characteristic of the timing fluctuation and instability for the transfer was analyzed and measured. The experimental results show the total root-mean-square (RMS) timing fluctuation of the transferred RF signal with compensation is about 162 fs with a fractional frequency instability on the order of 2.8 × 10-13 at 1 s and 2.7 × 10-16 at 1000 s. The laser-based underwater frequency transfer proposed in this paper has a potential application of transferring atomic clock in water environment as its instability is less than the currently-used commercial Cs or H-master clocks.

Long-term follow-up of persistent pulmonary pure ground-glass nodules with deep learning-assisted nodule segmentation.

OBJECTIVE: To investigate the natural history of persistent pulmonary pure ground-glass nodules (pGGNs) with deep learning-assisted nodule segmentation. METHODS: Between January 2007 and October 2018, 110 pGGNs from 110 patients with 573 follow-up CT scans were included in this retrospective study. pGGN automatic segmentation was performed on initial and all follow-up CT scans using the Dr. Wise system based on convolution neural networks. Subsequently, pGGN diameter, density, volume, mass, volume doubling time (VDT), and mass doubling time (MDT) were calculated automatically. Enrolled pGGNs were categorized into growth, 52 (47.3%), and non-growth, 58 (52.7%), groups according to volume growth. Kaplan-Meier analyses with the log-rank test and Cox proportional hazards regression analysis were conducted to analyze the cumulative percentages of pGGN growth and identify risk factors for growth. RESULTS: The mean follow-up period of the enrolled pGGNs was 48.7 ± 23.8 months. The median VDT of the 52 pGGNs having grown was 1448 (range, 339-8640) days, and their median MDT was 1332 (range, 290-38,912) days. The 12-month, 24.7-month, and 60.8-month cumulative percentages of pGGN growth were 10%, 25.5%, and 51.1%, respectively, and they significantly differed among the initial diameter, volume, and mass subgroups (all p < 0.001). The growth pattern of pGGNs may conform to the exponential model. Lobulated sign (p = 0.044), initial mean diameter (p < 0.001), volume (p = 0.003), and mass (p = 0.023) predicted pGGN growth. CONCLUSIONS: Persistent pGGNs showed an indolent course. Deep learning can assist in accurately elucidating the natural history of pGGNs. pGGNs with lobulated sign and larger initial diameter, volume, and mass are more likely to grow. KEY POINTS: • The pure ground-glass nodule (pGGN) segmentation accuracy of the Dr. Wise system based on convolution neural networks (CNNs) was 96.5% (573/594). • The median volume doubling time (VDT) of 52 pure ground-glass nodules (pGGNs) having grown was 1448 days (range, 339-8640 days), and their median mass doubling time (MDT) was 1332 days (range, 290-38,912 days). The mean time to growth in volume was 854 ± 675 days (range, 116-2856 days). • The 12-month, 24.7-month, and 60.8-month cumulative percentages of pGGN growth were 10%, 25.5%, and 51.1%, respectively, and they significantly differed among the initial diameter, volume, and mass subgroups (all p values < 0.001). The growth pattern of pure ground-glass nodules may conform to exponential model.

[Value of body fat mass measured by bioelectrical impedance analysis in predicting abnormal blood pressure and abnormal glucose metabolism in children].

OBJECTIVE: To study the value of body fat mass measured by bioelectrical impedance analysis (BIA) in predicting abnormal blood pressure and abnormal glucose metabolism in children. METHODS: Stratified cluster sampling was used to select the students aged 6-16 years, and a questionnaire survey and physical examination were performed. The BIA apparatus was used to measure body fat mass. Body mass index (BMI), body fat mass index (FMI), and fat mass percentage (FMP) were calculated. Fasting blood glucose level were measured. RESULTS: A total of 14 293 children were enrolled, among whom boys accounted for 49.89%. In boys and girls, the percentile values (P60, P65, P70, P75, P80, P85, P90, P95) of FMI and FMP fitted by the LMS method were taken as the cut-off values. Based on the receiver operating characteristic curve analysis, the P70 values with a better value in predicting abnormal blood pressure and blood glucose metabolism were selected as the cut-off values for excessive body fat. When FMI or FMP was controlled below P70, the incidence of abnormal blood pressure or abnormal glucose metabolism may be decreased in 8.25%-43.24% of the children. CONCLUSIONS: The evaluation of obesity based on FMI and FMP has a certain value in screening for hypertension and hyperglycemia in children, which can be further verified in the future prevention and treatment of obesity and related chronic diseases in children.

Improvement of bandwidth of phase-locked loop for mode-locked laser with multiple-differentials-based loop filter.

A scheme for improving the bandwidth of a phase-locked loop (PLL) for mode-locked laser is proposed. In the proposed scheme, a modified PLL with a multiple-differentials-based loop filter can be used to increases the upper limit bandwidth of the laser-based PLL. The mechanism of the bandwidth improvement is explained in detail, and the experimental results of a laser-based PLL with the proposed scheme show that the upper-limit bandwidth of the PLL has been increased about by one order at offset frequency from 3 kHz to 30 kHz. This scheme with the simple multiple-differential-based loop filter configuration can be easily used in another laser's phase locking system whose bandwidth should be improved.

Timing jitter reduction through relative intensity noise suppression in high-repetition-rate mode-locked fiber lasers.

We reported the timing jitter reduction of an 882 MHz mode-locked NPE Yb:fiber lasers through active relative intensity noise suppression. The timing jitter spectra measurements based on balanced optical cross-correlation (BOC) technique show a reduction of ~10 dB in the Fourier frequency range from ~3 kHz to ~30 kHz with a unity-gain crossing point of 80 kHz. The results verify the theoretical prediction that the relative intensity noise (RIN) induced timing jitter by self-steepening effect dominates the jitter performance below ~100 kHz. Further comparison with the analytic model shows that the effect of RIN decays below ~3 kHz. Thus, the timing jitter reduction is not obvious at low frequency. To the best of our knowledge, this is the first experimental report on the timing jitter reduction through active RIN suppression in high-repetition-rate mode-locked fiber lasers.

A mutation in class III homeodomain-leucine zipper (HD-ZIP III) transcription factor results in curly leaf (cul) in cucumber (Cucumis sativus L.).

KEY MESSAGE: We identified two curly-leaf (cul) mutants in cucumber. Map-based cloning revealed that both mutants are due to allelic mutations in the CsPHB gene, a homolog of the Arabidopsis PHABULOSA which encodes a class III homeodomain-leucine zipper (HD-ZIP III) transcription factor. Leaf rolling is an important agronomic trait in crop breeding. Moderate leaf rolling minimizes shadowing between leaves, leading to improved photosynthetic efficiency. Although a number of genes controlling rolled leaf have been identified from rice and other plant species, none have been mapped or cloned in cucurbit crops. In this study, we identified and characterized two curly leaf (cul) mutants, cul-1 and cul-2 in cucumber. With map-based cloning, we show that cul-1 and cul-2 are allelic mutations and CsPHB (Csa6G525430) was the candidate gene for both mutants. The CsPHB gene encoded a class III homeodomain-leucine zipper (HD-ZIP III) transcription factor. A single non-synonymous mutation in the fourth and fifth exons of the CsPHB was responsible for the cul-1 and cul-2 mutant phenotypes, respectively. The single-nucleotide substitutions in cul-1 and cul-2 were both located in cs-miRNA165/166 complementary sites of CsPHB. The expression level of CsPHB gene in multiple organs of cul-1 and cul-2 mutants was higher than that in the wild type, while the expression of cs-miRNA165/166 in the two genotypes showed the opposite trend. We speculate that disruption of the binding between the mutant allele of CsPHB and cs-miRNA165/166 leads to the curly-leaf phenotype. This is the first report to clone and characterize the CsPHB gene in the family Cucurbitaceae. Taken together, these results support CsPHB as an important player in the modulation of leaf shape development in cucumber.

Radiomics model of contrast-enhanced computed tomography for predicting the recurrence of acute pancreatitis.

OBJECTIVES: To predict the recurrence of acute pancreatitis (AP) by constructing a radiomics model of contrast-enhanced computed tomography (CECT) at AP first attack. METHODS: We retrospectively enrolled 389 first-attack AP patients (271 in the primary cohort and 118 in the validation cohort) from three tertiary referral centers; 126 and 55 patients endured recurrent attacks in each cohort. Four hundred twelve radiomics features were extracted from arterial and venous phase CECT images, and clinical characteristics were gathered to develop a clinical model. An optimal radiomics signature was chosen using a multivariable logistic regression or support vector machine. The radiomics model was developed and validated by incorporating the optimal radiomics signature and clinical characteristics. The performance of the radiomics model was assessed based on its calibration and classification metrics. RESULTS: The optimal radiomics signature was developed based on a multivariable logistic regression with 10 radiomics features. The classification accuracy of the radiomics model well predicted the recurrence of AP for both the primary and validation cohorts (87.1% and 89.0%, respectively). The area under the receiver operating characteristic curve (AUC) of the radiomics model was significantly better than that of the clinical model for both the primary (0.941 vs. 0.712, p = 0.000) and validation (0.929 vs. 0.671, p = 0.000) cohorts. Good calibration was observed for all the models (p > 0.05). CONCLUSIONS: The radiomics model based on CECT performed well in predicting AP recurrence. As a quantitative method, radiomics exhibits promising performance in terms of alerting recurrent patients to potential precautions. KEY POINTS: • The incidence of recurrence after an initial episode of acute pancreatitis is high, and quantitative methods for predicting recurrence are lacking. • The radiomics model based on contrast-enhanced computed tomography performed well in predicting the recurrence of acute pancreatitis. • As a quantitative method, radiomics exhibits promising performance in terms of alerting recurrent patients to the potential need to take precautions.