Objective To explore the application value of artificial intelligence in medical research assistance, and analyze the key paths to achieve precise execution of model instructions, improvement of model interpretation completeness, and control of hallucinations. Methods Taking esophageal cancer research as the scenario, five types of literature including research articles, case reports, reviews, editorials, and guidelines were selected for model interpretation tests. The model performance was systematically evaluated from five dimensions: recognition accuracy, format accuracy, instruction execution accuracy, content reliability rate, and content completeness index. The performance differences of Ruibin Agent, GPT-4o, Claude 3.7 Sonnet, DeepSeek V3, and DouBao-pro models in medical literature interpretation tasks were compared. Results A total of 15 studies were included, with 3 studies of each type. The five models collectively conducted 1 875 tests. Due to the poor recognition accuracy of the editorial type, the overall recognition accuracy of Ruibin Agent was significantly lower than other models (92.0% vs. 100.0%, P＜0.001). In terms of format accuracy, Ruibin Agent was significantly better than Claude 3.7 Sonnet (98.7% vs. 92.0%, P=0.002) and GPT-4o (98.7% vs. 78.9%, P＜0.001). In terms of instruction execution accuracy, Ruibin Agent was better than GPT-4o (97.3% vs. 80.0%, P＜0.001). In terms of content reliability rate, Ruibin Agent was significantly lower than Claude 3.7 Sonnet (84.0% vs. 92.0%, P=0.010) and DeepSeek V3 (84.0% vs. 94.7%, P＜0.001). In terms of content completeness index, the median scores of Ruibin Agent, GPT-4o, Claude 3.7 Sonnet, DeepSeek V3, and DouBao-pro were 0.71, 0.60, 0.85, 0.74, and 0.77, respectively. Conclusion Ruibin Agent has significant advantages in terms of formatted interpretation of medical literature and instruction execution accuracy. In the future, it is necessary to focus on optimizing the recognition ability of editorial types, strengthening the coverage ability of core elements of various types of literature to improve interpretation completeness, and improving content reliability through optimizing the confidence mechanism to ensure the rigor of medical literature interpretation.

Objective:To construct a deep learning model based on YOLOV8-Seg algorithm to conduct automatic segmentation for the central gland(CG)and peripheral zone(PZ)of prostate,so as to provide a reliable basis for clinical diagnosis and treatment.Methods:The sequence data of T2-weighted imaging(T2WI)of horizontal relaxation time of 158 patients were selected from a public data set of magnetic resonance imaging(MRI)for prostate MRI,which was provided by the Charité University Hospital in Berlin,were selected.The all data were divided into a training set(109 cases),a validation set(16 cases),and a test set(33 cases)as the ratio of 7 to1 to 2.A lightweight asymmetric decoupled head(LADH)structure and the large kernel UniRepLKNetBlock module were integrated into the YOLOV8-Seg algorithm to enhance the capabilities of model's extraction feature,and the new model was named as YOLOV8-URLK.The assessment model with mean Average Precision(mAP),Dice Similarity Coefficient(DSC),95%Hausdorff Distance(HD95),and Average Surface Distance(ASD)was adopted to segment performance of the detection at prostate CG and PZ.Comparative experiments were conducted among that and YOLOV8-Seg,TransU-Net,and U-Net network,so as to validate the effectiveness of YOLOV8-URLK for detection and segmentation at prostate zone.Results:On the test set,the mAP@0.5(box)of YOLOV8-URLK model was 0.878,and the mean Dice coefficients,the mean HD95 values and the ASD values of that at CG and PZ were respectively(0.867,17.123 and 1.461)and(14.902,0.898 and 1.112).On the test set,the mAP@0.5(box)of YOLOV8-Seg model was 0.860,and the mean Dice coefficients of that at CG and PZ were 0.851 and 0.884,the mean HD95 values of that at them were 19.174 and 15.298,and ASD values of that at them were 1.781 and 1.219,respectively.On test set,the mean Dice coefficients of TransU-Net model at CG and PZ were 0.864 and 0.824,and the mean HD95 values of that at them were 18.134 and 19.402,and ASD values of that at them were 1.698 and 1.717,respectively.On the test set,the mean Dice coefficients of the U-Net model at CG and PZ were 0.857 and 0.690,and the mean HD95 values of that at them were 18.976 and 26.934,and ASD values of that at them were 1.753 and 2.135.The YOLOV8-URLK model can better reappear the segmentation trend of manual annotations.Conclusion:The YOLOV8-URLK model demonstrates higher precision in the detection and segmentation of MRI images of prostate,which were superior to YOLOV8-Seg,TransU-Net and U-Net.It can enhance the efficiency of the detection and segmentation.

Traditional development of small protein scaffolds has relied on display technologies and mutation-based engineering, which limit sequence and functional diversity, thereby constraining their therapeutic and application potential. Protein design tools have significantly advanced the creation of novel protein sequences, structures, and functions. However, further improvements in design strategies are still needed to more efficiently optimize the functional performance of protein-based drugs and enhance their druggability. Here, we extended an evolution-based design protocol to create a novel minibinder, BindHer, against the human epidermal growth factor receptor 2 (HER2). It not only exhibits super stability and binding selectivity but also demonstrates remarkable properties in tissue specificity. Radiolabeling experiments with ^99mTc, ⁶⁸Ga, and ¹⁸F revealed that BindHer efficiently targets tumors in HER2-positive breast cancer mouse models, with minimal nonspecific liver absorption, outperforming scaffolds designed through traditional engineering. These findings highlight a new rational approach to automated protein design, offering significant potential for large-scale applications in therapeutic mini-protein development.

The purpose of this investigation was to elucidate the clinical characteristics and genetic underpinnings of a pediatric patient with neurodevelopmental disorder with ataxic gait, absent speech, and decreased cortical white matter (NDAGSW, OMIM#617807). The affected individual, a 1-year-9-month-old male, displayed physical development retardation and distinctive facial features, notably periorbital puffiness, upward-gazing palpebral fissures, a shortened philtrum, a tented mouth, and conical-shaped digits. Clinically, the patient presented with profound global developmental retardation, marked language deficits, hypotonia, and an ataxic gait. Subtle, non-diagnostic alterations were identified in cranial magnetic resonance imaging and visual evoked potential assessments. The trio-whole exome sequencing analysis revealed a de novo heterozygous mutation, c.202G>A (p.A68T), within the RAB11B gene, a known pathogenic variant linked to NDAGSW. Neurodevelopmental disorders due to RAB11B gene variants are rare disorders with clinical manifestations of severe mental retardation, aphasia, motor retardation, gait abnormalities with peculiar phenotypical features, structural abnormalities of the brain, and reduced cerebral white matter, cerebellar hypoplasia, and hypoplasia of the corpus callosum as seen on cranial imaging. Based on the characteristics of the disease, the heterozygous missense mutation c.202G>A (p.Ala68Thr) in the RAB11B gene was identified as the genetic etiology of the child.

Objective To explore the value of radiomics and deep transfer learning(DTL)based on gadoxetic acid disodium-enhanced magnetic resonance imaging(MRI)for preoperative prediction of microvascular invasion(MVI)in hepatocellular carcinoma(HCC).Methods A retrospective analysis was conducted using the MRI and clinicopathological data of 369 HCC patients who underwent surgery and had pathologically confirmed MVI at the Affiliated Hospital of Qingdao University from January 2019 to September 2024.According to the negative and positive manifestations of MVI,these patients were divided into MVI-group(n=219)and MVI+group(n=150);and they were then randomly assigned into the training set(n=258)and the test set(n=111)in a ratio of 7:3.Based on the hepatobiliary phase images,the optimal features were extracted and screened from radiomics features,DTL features,and the fusion features of the two.Nine machine learning models were constructed using 3 algorithms(random forest,multi-layer perceptron,and support vector machine,separately)and trained on radiomics features,DTL features,and the fusion features of the two.The diagnostic efficacy of each model was evaluated using receiver operating characteristic curve,and the optimal model was identified as the output model.Results Among all the constructed models,those based on fused features outperformed models using individual features.The random forest classifier model in the training set had the best performance,with an AUC of 0.998(95%CI:0.996-1.000),and was therefore selected as the output model in this study.Conclusion Radiomics and DTL models based on gadoxetic acid disodium-enhanced MRI can effectively predict the MVI in HCC.Among these,the random forest classifier model utilizing fused features in the training set exhibits the best performance.

Objective To explore the value of radiomics and deep transfer learning(DTL)based on gadoxetic acid disodium-enhanced magnetic resonance imaging(MRI)for preoperative prediction of microvascular invasion(MVI)in hepatocellular carcinoma(HCC).Methods A retrospective analysis was conducted using the MRI and clinicopathological data of 369 HCC patients who underwent surgery and had pathologically confirmed MVI at the Affiliated Hospital of Qingdao University from January 2019 to September 2024.According to the negative and positive manifestations of MVI,these patients were divided into MVI-group(n=219)and MVI+group(n=150);and they were then randomly assigned into the training set(n=258)and the test set(n=111)in a ratio of 7:3.Based on the hepatobiliary phase images,the optimal features were extracted and screened from radiomics features,DTL features,and the fusion features of the two.Nine machine learning models were constructed using 3 algorithms(random forest,multi-layer perceptron,and support vector machine,separately)and trained on radiomics features,DTL features,and the fusion features of the two.The diagnostic efficacy of each model was evaluated using receiver operating characteristic curve,and the optimal model was identified as the output model.Results Among all the constructed models,those based on fused features outperformed models using individual features.The random forest classifier model in the training set had the best performance,with an AUC of 0.998(95%CI:0.996-1.000),and was therefore selected as the output model in this study.Conclusion Radiomics and DTL models based on gadoxetic acid disodium-enhanced MRI can effectively predict the MVI in HCC.Among these,the random forest classifier model utilizing fused features in the training set exhibits the best performance.

Objective:To construct a deep learning model based on YOLOV8-Seg algorithm to conduct automatic segmentation for the central gland(CG)and peripheral zone(PZ)of prostate,so as to provide a reliable basis for clinical diagnosis and treatment.Methods:The sequence data of T2-weighted imaging(T2WI)of horizontal relaxation time of 158 patients were selected from a public data set of magnetic resonance imaging(MRI)for prostate MRI,which was provided by the Charité University Hospital in Berlin,were selected.The all data were divided into a training set(109 cases),a validation set(16 cases),and a test set(33 cases)as the ratio of 7 to1 to 2.A lightweight asymmetric decoupled head(LADH)structure and the large kernel UniRepLKNetBlock module were integrated into the YOLOV8-Seg algorithm to enhance the capabilities of model's extraction feature,and the new model was named as YOLOV8-URLK.The assessment model with mean Average Precision(mAP),Dice Similarity Coefficient(DSC),95%Hausdorff Distance(HD95),and Average Surface Distance(ASD)was adopted to segment performance of the detection at prostate CG and PZ.Comparative experiments were conducted among that and YOLOV8-Seg,TransU-Net,and U-Net network,so as to validate the effectiveness of YOLOV8-URLK for detection and segmentation at prostate zone.Results:On the test set,the mAP@0.5(box)of YOLOV8-URLK model was 0.878,and the mean Dice coefficients,the mean HD95 values and the ASD values of that at CG and PZ were respectively(0.867,17.123 and 1.461)and(14.902,0.898 and 1.112).On the test set,the mAP@0.5(box)of YOLOV8-Seg model was 0.860,and the mean Dice coefficients of that at CG and PZ were 0.851 and 0.884,the mean HD95 values of that at them were 19.174 and 15.298,and ASD values of that at them were 1.781 and 1.219,respectively.On test set,the mean Dice coefficients of TransU-Net model at CG and PZ were 0.864 and 0.824,and the mean HD95 values of that at them were 18.134 and 19.402,and ASD values of that at them were 1.698 and 1.717,respectively.On the test set,the mean Dice coefficients of the U-Net model at CG and PZ were 0.857 and 0.690,and the mean HD95 values of that at them were 18.976 and 26.934,and ASD values of that at them were 1.753 and 2.135.The YOLOV8-URLK model can better reappear the segmentation trend of manual annotations.Conclusion:The YOLOV8-URLK model demonstrates higher precision in the detection and segmentation of MRI images of prostate,which were superior to YOLOV8-Seg,TransU-Net and U-Net.It can enhance the efficiency of the detection and segmentation.

The purpose of this investigation was to elucidate the clinical characteristics and genetic underpinnings of a pediatric patient with neurodevelopmental disorder with ataxic gait, absent speech, and decreased cortical white matter (NDAGSW, OMIM#617807). The affected individual, a 1-year-9-month-old male, displayed physical development retardation and distinctive facial features, notably periorbital puffiness, upward-gazing palpebral fissures, a shortened philtrum, a tented mouth, and conical-shaped digits. Clinically, the patient presented with profound global developmental retardation, marked language deficits, hypotonia, and an ataxic gait. Subtle, non-diagnostic alterations were identified in cranial magnetic resonance imaging and visual evoked potential assessments. The trio-whole exome sequencing analysis revealed a de novo heterozygous mutation, c.202G>A (p.A68T), within the RAB11B gene, a known pathogenic variant linked to NDAGSW. Neurodevelopmental disorders due to RAB11B gene variants are rare disorders with clinical manifestations of severe mental retardation, aphasia, motor retardation, gait abnormalities with peculiar phenotypical features, structural abnormalities of the brain, and reduced cerebral white matter, cerebellar hypoplasia, and hypoplasia of the corpus callosum as seen on cranial imaging. Based on the characteristics of the disease, the heterozygous missense mutation c.202G>A (p.Ala68Thr) in the RAB11B gene was identified as the genetic etiology of the child.

Objective To develop and evaluate the equivalence of the Mandarin test material for tracking of noise tolerance(TNT)test.Methods Six different speech materials were developed(themes including daily life,entertainment,family,festivals,outdoors,and school).Four-minute TNT tests were measured in 21 normal hear-ing subjects using six different test materials.For each session,the tolerable noise level(TNL)and TNT scores were acquired and calculated for 3 time windows(31～240 s,31～120 s,151～240 s).Results Statistic analysis showed significant differences in the TNL(F=43.611,P＜0.05)among the normal hearing listeners.There were statistically significant differences in standardize z-scored TNT scores of the six different materials in the three time windows(P＜0.05).Post-hoc comparisons revealed that all significant differences involved the family and daily life themes.Conclusion Entertainment,festival,outdoors and school themed test materials can serve as the materials of Mandarin tracking of noise tolerance test and can be appied in research and clinical testing.

Signal transduction and activator of transcription factor 1(STAT1), one of the important members of the STAT family, is a key cytoplasmic transcription factor and an important component of the JAK-STAT signaling pathway. Gain-of-function mutations in STAT1 (STAT1-GOF) impaired the dephosphorylation of STAT1 protein, mediated the enhancement of cell signaling pathways such as type Ⅰ, Ⅱ, and Ⅲ interferon(IFN) and interleukins-27 (IL-27), IL-6, IL-10, and IL-17, and inhibited Th17 cells. The clinical manifestations of STAT1-GOF are diverse, including chronic mucocutaneous candidiasis and autoimmune diseases. For the treatment of STAT1-GOF, such as targeted therapy with ruxolitinib for STAT1 hyperphosphorylation, immunomodulatory therapy and hematopoietic stem cell transplantation for different self-immune systems, certain curative effects can be obtained. With the understanding of disease mechanisms and the discovery of new clinical phenotypes, this review focuses on the diseases caused by gain-of-function mutations of STAT1, and introduces the clinical manifestations and treatment progress of STAT1-GOF to promote the understanding of such diseases and their future diagnosis, treatment and research works.