Cochlear implantation is the most effective method to restore hearing in patients with severe and profound hearing impairment.There are individual differences in rehabilitation after cochlear implantation.In order to better understand the underlying factors of rehabilitation,machine learning has been gradually applied to the reha-bilitation prediction of cochlear implant patients.Since related literature is still in its infancy,many problems still remain unresolved,such as insufficient sample size and lack of diversification of data features.We suggest that fu-ture research may expand the sample size,optimize machine learning models,and fully explore the predictive factors affecting the rehabilitation of cochlear implantation,and make machine learning a better tool in the area of cochlear implantation.

Objective The application of 18F-PSMA-1007 PET/CT in the precise diagnosis and treatment of prostate cancer(PCa)is gradually increasing.This study aimed to explore the predictive value of 18F-PSMA-1007 PET/CT for positive surgical margins after radical prostatectomy(RP).Methods A total of 173 PCa patients who were pathologically confirmed and underwent RP in our hospital from July 2020 to August 2023 were retrospectively recruited.All patients underwent 18F-PSMA-1007 PET/CT whole-body imaging before surgery.According to the postoperative pathological results,they were divided into a negative surgical margin group with 83 cases and a positive surgical margin group with 90 cases.The differences in age,SUVmax,SUVmean,preoperative total prostate specific antigen(tPSA),prostate specific antigen density(PSAD),prostate volume,Gleason score,and clinical T staging between the groups were compared,and the risk factors were further analyzed by Logistic regression.Results The preoperative tPSA(Z=-3.252,P=0.001),SUVmax(Z=2.531,P=0.011),and clinical T staging(P=0.018)were all lower in the negative surgical margin group than in the positive surgical margin group.PSAD(OR=3.492,95％CI:1.095-11.133,P=0.035),SUVmax(OR=1.036,95％CI:1.003-1.070,P=0.034),and clinical T staging(OR=3.364,95％CI:1.117-10.133,P=0.045)were independent risk factors for positive surgical margins.Conclusion 18F-PSMA-1007 PET/CT has certain predictive value for positive surgical margins after RP in PCa patients.High PSAD,high SUVmax and high clinical T stage were independent risk factors for predicting positive margin after PR surgery,thus providing some reference for the clinical treatment strategy of PCa patients.

Objective To include patients with clinical data matched by propensity scores and to explore the value of 18F-fluorode-oxyglucose(18F-FDG)PET/CT metabolic parameters and radiomics in differentiating benign and malignant solitary pulmonary nod-ule(SPN).Methods A total of 54 patients with SPN(27 benign and 27 malignant)were retrospectively selected,all of them under-went 18F-FDG PET/CT scans.Then the metabolic parameters were analyzed,and the metabolic parameters model was established.After delineating the lesion,imaging features were selected through variance and correlation analysis.The logistic regression was used to build the model,and balance accuracy(bACC)was used to compare the performance of the models.The correlation between meta-bolic parameters and radiomics features was analyzed.Results The maximum standardized uptake value(SUVmax),total lesion uptake(TLU),and coefficient of variation(COV)of malignant were higher than those of benign(P＜0.05).SUVmax and COV had positive predictive value for malignant lesions[odds ratio(OR)＞1,P＜0.05].There was no statistical difference between the performance of the metabolic parameters model and the radiomics model(P＞0.05).There was a strong correlation between radiomics features and metabolic parameters.Conclusion After propensity score matching,metabolic parameters and radiomics show no statistical difference in differentiating benign from malignant SPN.

The number of patients with eye diseases in China is enormous,and the negative effects of these conditions,such as impaired visual function,psychological burdens,and restricted social participation,are becoming increasingly severe.Due to the limited and unevenly distributed ophthalmic resources,and the significant limitations of traditional diagnostic and therapeutic approaches in terms of accuracy and efficiency,there is an urgent need for more sensitive and efficient modalities.With the rapid advancement of artificial intelligence technology,ophthalmic diagnosis has entered a new stage of intelligent transformation.Facial photos,as a noninvasive and convenient medium,show unique advantages in eye disease diagnosis.Artificial intelligence systems based on facial photo analysis have been applied to the screening and diagnosis of conditions such as myopia,strabismus,ptosis,and thyroid eye disease,showing promising results.This review introduces the workflow of intelligent diagnosis for ocular diseases based on facial photographs,with a focus on recapitulating relevant research findings both domestically and internationally in recent years.It summarizes the innovative features and application advantages of intelligent diagnosis systems for eye diseases based on facial photos,analyzes the current technical bottlenecks and challenges in application,proposes corresponding countermeasures,and discusses future development directions,aiming to provide references and new insights for the intelligent screening and diagnosis of eye diseases.

Objective To analyze occupational exposure histories and clinical manifestations in three cases of occupational high altitude disease, and to identify key diagnostic points and prevention and treatment strategies. Methods The basic information, clinical characteristics, and occupational hazard exposure history of three patients with occupational high altitude disease were conducted using the retrospective analysis. Results The reason of these three pariticipants who visited high-altitude areas was work requirements. Case 1 experienced recurrent symptoms of altitude reactions during the prodromal stage and was clinically diagnosed with "high altitude sickness and cerebral edema". During transportation to a lower-altitude area, the patient passed through an area with a higher altitude (4 700 m), resulting in deterioration of the condition. Case 2 developed an upper respiratory tract infection and subsequently engaged in aerobic exercise, which aggravated the condition, eading to coughing up pink frothy sputum, followed by cerebral edema and bilateral pulmonary edema. Both cases developed acute cerebral edema and/or acute pulmonary edema due to severe hypobaric hypoxia and were diagnosed with occupational acute high altitude disease according to the GBZ 92-2008 Diagnostic Criteria of Occupational High Altitude Disease. Case 3 mainly presented with hearing loss, without clinical manifestations of high-altitude pulmonary edema or high-altitude cerebral edema, and thus could not be diagnosed with occupational acute high altitude disease. ConclusionThe key diagnostic criteria for occupational acute high altitude disease include a recent occupational history of working in high altitude environments and the presence of clinical manifestations of high altitude pulmonary edema or high altitude cerebral edema, with exclusion of other diseases presenting with similar symptoms. Preventive measures should be taken before workers enter high-altitude areas. Early symptoms of occupational high altitude disease are easily overlooked, so it is crucial to remain vigilant for warning signs and provide timely treatment.

This article presents a case study of a patient who visited the Geriatric Department of Peking Union Medical College Hospital due to "palpitations, shortness of breath for more than 2 years, limb weakness for 6 months, edema, and nocturnal dyspnea for 2 months". The patient exhibited decreased muscle strength in the limbs and involvement of swallowing and respiratory muscles, alongside complications of heart failure and various arrhythmias which were predominantly atrial. Laboratory tests revealed the presence of multiple autoantibodies and notably anti-mitochondrial antibodies. Following a comprehensive multidisciplinary evaluation, the patient was diagnosed with anti-mitochondrial antibody-associated inflammatory myopathy. Treatment involved a combination of glucocorticoids and immunosuppressants, along with resistance exercises for muscle strength and rehabilitation training for lung function, resulting in significant improvement of clinical symptoms. The case underscores the importance of collaborative multidisciplinary approaches in diagnosing and treating rare diseases in elderly patients, where careful consideration of clinical manifestations and subtle abnormal clinical data can lead to effective interventions.

ObjectiveTo explore the mechanism by which Zuoguiwan improves the pancreas development in the gestational diabetes mellitus （GDM） model by observing the effects of Zuoguiwan on the expression of key regulatory factors in different stages of pancreas development. MethodsPregnant Wistar rats were randomly assigned into blank， model， insulin detemir （20 U·kg^-1） and Zuoguiwan （1.89 g·kg^-1） groups （n=18）. GDM was induced by peritoneal injection of streptozotocin on day 6.5 （E6.5d） in the embryonic stage， and the blank group was given an equal volume of sodium citrate buffer. The modeling performance was assessed by measuring the blood glucose of pregnant rats. Except the blank group and model group， pregnant rats in other groups were administrated with corresponding drugs from E9.5d to delivery. The random blood glucose of pregnant rats was monitored， and the embryos and offspring rats were measured for the length and weighed on E12.5d， E18.5d and day 21 after birth （B21d）. The Lee's index of rats on B21d was calculated. Enzyme-linked immunosorbent assay （ELISA） was employed to measure the fasting insulin （FINS） levels of B22d rats and the Homeostasis Model Assessment for Insulin Resistance （HOMA-IR） was calculated. The serum levels of aspartate aminotransferase （AST）， alanine aminotransferase （ALT）， total bilirubin （TBIL）， total cholesterol （CHO）， triglyceride （TG）， high-density lipoprotein cholesterol （HDL）， and low-density lipoprotein cholesterol （LDL） in E18.5d pregnant rats and B22d offspring were determined. The pathological changes in the pancreas of E12.5d， E18.5d and B22d rats were observed by hematoxylin-eosin （HE） staining. Western blot was used to determine the protein levels of pancreatic duodenal homeobox 1 （Pdx1）， pancreas-specific transcription factor 1a （Ptf1a）， and sex-determining region Y-box protein 9 （Sox9） in the pancreas of E12.5d embryos， Pdx1， Nkx2 homeobox 2 （Nkx2.2）， and hairy and enhancer of split-1 （Hes1） in the pancreas of E18.5d embryos， and Pdx1， v-maf musculoaponeurotic fibrosarcoma oncogene homolog A （Mafa）， and NK transcription factor-related homeobox gene family 6 locus 1 （Nkx6.1） in the pancreas of B22d rats. ResultsCompared with the blank group， the model group showed elevated blood glucose levels in pregnant rats on B0d， E9.5d， E12.5d， E15.5d， and E18.5d （P<0.05， P<0.01）， decreased body weight and body length （P<0.01） and increased Lee's index in the offspring. In addition， the B22d offspring showed rising levels of FBG， FINS， HOMA-IR， AST， and TG （P<0.01）， a declined level of HDL （P<0.01）， and pancreatic acinous cells with edema and loose arrangement. The pregnant rats on E18.5d exhibited raised levels of ALT， AST， and TG （P<0.05， P<0.01） in the pancreas and a declined level of HDL （P<0.05）. The E12.5d embryos showed up-regulated protein levels of Pdx1， Sox9， and Ptf1a in the pancreas （P<0.01） and the E18.5d embryos exhibited down-regulated protein levels of Pdx1， Nkx2.2， and Hes1 in the pancreas （P<0.01）. The protein levels of Pdx1， Nkx6.1， and Mafa in the pancreas of B22d offspring were down-regulated （P<0.01）. Compared with the model group， the insulin group exhibited lowered blood glucose in pregnant rats on B0d， E15.5d， and E18.5d （P<0.05， P<0.01）. The offspring in all treatment groups showcased increased body weight and body length （P<0.01） and decreased Lee's index. The B22d offspring exhibited declined levels of FBG， FINS， and HOMA-IR in the insulin group （P<0.01） and lowered levels of FBG and HOMA-IR in the Zuoguiwan group （P<0.01）. The B22d offspring in all the treatment groups showed reduced levels of ALT， AST， TBIL， CHO， TG， and LDL， a raised level of HDL， and alleviated edema of pancreatic acinous cells. The pregnant rats on E18.5d demonstrated declined levels of TG and ALT （P<0.05， P<0.01） and an elevated level of HDL （P<0.05）. The pancreas of E12.5d embryos presented down-regulated protein levels of Pdx1 and Sox9 and an up-regulated protein level of Ptf1a in the insulin group （P<0.05）. The pancreas of E12.5d embryos in the Zuoguiwan group presented down-regulated protein levels of Pdx1， Sox9， and Ptf1a （P<0.01）. All the treatment groups showed up-regulated protein levels of Pdx1， Nkx2.2， and Hes1 in the pancreas of E18.5d embryos （P<0.01） and Pdx1， Nkx6.1， and Mafa in the pancreas of B22d embryos （P<0.05， P<0.01）. ConclusionZuoguiwan can promote the growth and development and ameliorate the pathological changes in the pancreas of the offspring of GDM model by regulating the expression of Pdx1 pathway-related regulatory factors in different stages of pancreas development.

Cochlear implantation is the most effective method to restore hearing in patients with severe and profound hearing impairment.There are individual differences in rehabilitation after cochlear implantation.In order to better understand the underlying factors of rehabilitation,machine learning has been gradually applied to the reha-bilitation prediction of cochlear implant patients.Since related literature is still in its infancy,many problems still remain unresolved,such as insufficient sample size and lack of diversification of data features.We suggest that fu-ture research may expand the sample size,optimize machine learning models,and fully explore the predictive factors affecting the rehabilitation of cochlear implantation,and make machine learning a better tool in the area of cochlear implantation.

Objective:To explore the differences in sociodemographic and clinical characteristics between pa-tients with unipolar depression bipolar depression and to establish a nomogram for identifying bipolar depression.Methods:Using data from the China Mental Disorders Cohort Study,the sociodemographic and clinical characteristics of 2 643 patients with unipolar depression and 250 patients with bipolar depression diagnosed accord-ing to the criteria of the Diagnostic and Statistical Manual of Mental Disorders,Fifth Edition(DSM-5)were includ-ed to compare their sociodemographic and clinical characteristics.These characteristics included general demograph-ic information,disease-related information,clinical examination results,and the severity of the disease assessed with the Global Assessment of Functioning(GAF)and Hamilton Depression Rating Scale.Logistic regression analysis was employed to identify factors influencing bipolar depression,and a nomogram was constructed for its identifica-tion.Results:The risk factors for bipolar depression included being male(OR=1.48),being employed(OR=1.38),having non-melancholic features during episodes(OR=2.33),a Body Mass Index ranging from normal to obese(OR=2.48,2.49,4.65),psychotic features(OR=2.14),mixed episode(OR=9.36),comorbid physical diseases(OR=2.47),four or more depressive episodes(OR=1.67),earlier age of onset(OR=0.95),longer ill-ness duration(OR=1.03),and higher GAF scores(OR=1.02).The nomogram model achieved an AUC of 0.81(95％CI:0.78-0.84).The Hosmer-Lemeshow test result was x2=6.96(P＞0.05),indicating good model fit.The calibration curve showed good performance.The decision curve analysis revealed that the nomogram pro-vides significant clinical benefit when the risk of bipolar depression was within the range of 0 to 0.9.Conclusion:The nomogram established based on the identified sociodemographic and clinical factors can accurately assess the risk of bipolar depression,providing a useful tool for early identification and intervention.

Objective:To evaluate the diagnostic efficacy of 18F-prostate specific membrane antigen (PSMA)-1007 PET/CT in patients with prostate imaging reporting and data system (PI-RADS) 1-3 lesions on multi-parametric MRI (mpMRI) and pathologically confirmed prostate cancer. Methods:Clinical, pathological, and imaging data of 59 patients (age (67.8±7.6) years) with PI-RADS 1-3 lesions on mpMRI in the First Affiliated Hospital of Xi′an Jiaotong University between December 2021 and March 2024 were retrospectively collected. Those patients also underwent 18F-PSMA-1007 PET/CT and prostate biopsy during the same period due to an elevated prostate specific antigen (PSA) level. The diagnostic performances of 18F-PSMA-1007 PET/CT for PI-RADS 1-3 prostate cancer and clinically significant prostate cancer were evaluated by using pathological results as the standard. Mann-Whitney U test was used to compare differences in clinical characteristics and PET parameters between PET-positive and PET-negative groups, and logistic regression analysis was performed to select independent influencing factors for the PET/CT diagnosis of prostate cancer. Results:Of the included 59 patients, 7, 27, and 25 had PI-RADS scores of 1, 2, and 3 respectively. Benign prostate hyperplasia was pathologically confirmed in 8 patients, and prostate cancer was confirmed in 51 patients, of which 37 had clinically significant prostate cancer. The sensitivity of 18F-PSMA-1007 PET/CT in diagnosing prostate cancer was 86.3%(44/51), the specificity was 2/8, the accuracy was 78.0%(46/59), the positive predictive value was 88.0%(44/50), and the negative predictive value was 2/9. For patients with clinically significant prostate cancer, the sensitivity, specificity, accuracy, positive predictive value, and negative predictive value were 91.9%(34/37), 27.3%(6/22), 67.8%(40/59), 68.0%(34/50), and 6/9, respectively. SUV max was significantly higher in the PET-positive group ( n=44) than that in the PET-negative group ( n=7; 12.8(9.1, 23.5) vs 5.1(5.0, 6.2); Z=-4.16, P=0.001). Logistic regression analysis showed that SUV max was an independent influencing factor for the diagnosis of prostate cancer by 18F-PSMA-1007 PET/CT (odds ratio ( OR)=6.01, 95% CI: 1.57-23.00, P=0.009). Conclusions:18F-PSMA-1007 PET/CT has a high sensitivity and positive predictive value in prostate cancer patients with PI-RADS 1-3 on mpMRI. It can be used as a supplementary modality to mpMRI to guide clinical decision for patients with PI-RADS 1-3 and clinically suspected prostate cancer lesions.