Objective To explore the risk factors for urinary tract infection(UTI)after benign prostatic hyperpla-sia(BPH)surgery,and construct a high-efficiency risk-prediction model based on machine learning algorithms(MLA).Methods This retrospective study included 200 cases of BPH surgically treated in Xinyu Hospital of Traditional Chinese Medicine from May 2020 to April 2023.Twenty-three cases were included in the UTI group,and 177 were enrolled into the non-UTI group.The relevant data were collected and analyzed for the statistically significant factors by univariate logistic analysis by using the SPSS software,MLA-based logistic regression,back-propagation(BP)neural networks and decision classification and regression tree(CRT).And the predictive values of the models established via different algorithms using the area under the receiver operating characteristic curve(AUC)were compared.We assessed the prediction accuracy of the models and identified one with the best prediction efficiency based on the mean absolute error(MAE).Results Univariate analysis indicated statisti-cally significant differences between the UTI and non-UTI groups in age,comorbid diabetes mellitus(DM),urinary catheter-in-dwelling time,prostate volume,preoperative catheterization,preoperative IPSS(P＜0.05).The independent predictive varia-bles for UTI after BPH surgery were shown to be age,IPSS,comorbid DM and prostate volume by the method of multivariate lo-gistic regression model(P＜0.05).Age,urinary catheter-indwelling time,prostate volume and IPSS were assessed as the influ-ence factors by the CRT model(P＜0.05),and prostate volume,IPSS,age and urinary catheter-indwelling time were assessed as the influence factors by the BP neural network model(P＜0.05).Among the 3 risk-prediction models,the one constructed with the BP neural networks exhibited the best prediction efficiency(AUC:0.992,the optimal truncation value:0.912,corre-sponding sensitivity and specificity:0.957 and 0.955).Conclusion The risk-prediction model constructed by MLA and BP neural networks based on the characteristic factors of age,preoperative urinary retention catheterization,urinary catheter-indwell-ing time,IPSS and comorbid DM has a high predictive value for UTI after BPH surgery which can be applied to the identification and management of such high-risk population.

Objective To explore the risk factors for urinary tract infection(UTI)after benign prostatic hyperpla-sia(BPH)surgery,and construct a high-efficiency risk-prediction model based on machine learning algorithms(MLA).Methods This retrospective study included 200 cases of BPH surgically treated in Xinyu Hospital of Traditional Chinese Medicine from May 2020 to April 2023.Twenty-three cases were included in the UTI group,and 177 were enrolled into the non-UTI group.The relevant data were collected and analyzed for the statistically significant factors by univariate logistic analysis by using the SPSS software,MLA-based logistic regression,back-propagation(BP)neural networks and decision classification and regression tree(CRT).And the predictive values of the models established via different algorithms using the area under the receiver operating characteristic curve(AUC)were compared.We assessed the prediction accuracy of the models and identified one with the best prediction efficiency based on the mean absolute error(MAE).Results Univariate analysis indicated statisti-cally significant differences between the UTI and non-UTI groups in age,comorbid diabetes mellitus(DM),urinary catheter-in-dwelling time,prostate volume,preoperative catheterization,preoperative IPSS(P＜0.05).The independent predictive varia-bles for UTI after BPH surgery were shown to be age,IPSS,comorbid DM and prostate volume by the method of multivariate lo-gistic regression model(P＜0.05).Age,urinary catheter-indwelling time,prostate volume and IPSS were assessed as the influ-ence factors by the CRT model(P＜0.05),and prostate volume,IPSS,age and urinary catheter-indwelling time were assessed as the influence factors by the BP neural network model(P＜0.05).Among the 3 risk-prediction models,the one constructed with the BP neural networks exhibited the best prediction efficiency(AUC:0.992,the optimal truncation value:0.912,corre-sponding sensitivity and specificity:0.957 and 0.955).Conclusion The risk-prediction model constructed by MLA and BP neural networks based on the characteristic factors of age,preoperative urinary retention catheterization,urinary catheter-indwell-ing time,IPSS and comorbid DM has a high predictive value for UTI after BPH surgery which can be applied to the identification and management of such high-risk population.

Objective:To review the risk factors for early and medium-term complications of fenestration-branch endovascular thoracic aortic repair (F/B-TEVAR) in patients with complex aortic arch disease.Methods:The clinical and follow-up data of 202 patients undergoing F/B-TEVAR treatment from Feb 2019 to Sep 2023 in these centers were retrospectively analyzed .Results:There were 46 cases suffering from postoperative complications (22.8%). The risk factors with statistical significance included aortic atherosclerotic plaque [ OR=2.843; 95% CI (1.4-5.6); P<0.01], aortic intramural thrombosis [ OR=2.358; 95% CI (1.2-4.6), P=0.011], the aortic dilatation [ OR=4.219; 95% CI (1.6-11.3), P<0.01], the history of stroke [ OR=2.088; 95% CI (1.1-4.1), P=0.032], smoking history [ OR=2.680; 95% CI: (1.3-5.5); P<0.01], duration of surgery [ OR=1.9; 95% CI: (1.2-2.9); P=0.042].While the application of 3D printing assistive technology [ OR=0.392; 95% CI: (0.2-0.9); P=0.048] was in a negative correlation with postoperative complication. Conclusions:The independent risk factors for complications after F/B-TVAR included aortic atherosclerotic plaque, aortic intramural thrombosis, the aortic dilatation, the history of stroke, smoking history,duration of surgery.The application of 3D printing technology can effectively reduce the complication rate.

AIM: To evaluate clinical efficacy and safety of ultrasound cycloplasty(UCP)in the treatment of refractory glaucoma.METHODS:From June 2021 to October 2022, a total of 17 patients(17 eyes)with refractory glaucoma were enrolled in this prospective study, and they all underwent UCP. The patients underwent 6 mo followed-up post-treatment, and the intraocular pressure(IOP), pain grade score, IOP lowering drugs, success rate and occurrence of complications were documented.RESULTS:The IOP was significantly decreased from 51.98±7.80 mmHg before UCP to 32.54±13.21 mmHg at 1 d, 22.38±11.98 mmHg at 1 wk, 22.63±10.78 mmHg at 1 mo, 26.05±9.17 mmHg at 3 mo, and 23.73±9.60 mmHg at 6 mo postoperatively(all P<0.01). The percentage of IOP reduction after treatment was 36.25%, 57.10%, 56.35%, 49.16% and 54.09% at 1 d, 1 wk, 1, 3, and 6 mo, respectively. The pain grade scores were decreased(P<0.01). There was a statistically significant reduction in the use of IOP lowering medications(P=0.008). At 6 mo postoperatively, 2 eyes(12%)were complete success, 11 eyes(65%)were qualified success, and 4 eyes(24%)were failure. The main complication observed was anterior chamber inflammation in 1 eye(6%), foreign body sensation in 2 eyes(12%), subconjunctival hemorrhage in 2 eyes(12%), and conjunctival congestion in 6 eyes(35%). All symptoms spontaneously resolved within 1 wk without requiring any specific treatment. One case of choroidal detachment(6%)occurred on 10 d postoperatively, but recovered after orally treated by prednisone acetate for 1 mo. No other serious complications, such as hyphema, corectopia, synechia or macular edema were reported.CONCLUSION:UCP is safe and efficacious in treating refractory glaucoma, reducing IOP and alleviating ocular pain symptoms, while maintaining a favorable safety profile.

AIM: To observe the changes of nerve fiber thickness and vessel density in macula and optic disc following femtosecond laser-assisted and conventional phacoemulsification cataract surgery through optical coherence tomography angiography(OCTA).METHODS: A total of 65 cases(85 eyes)that diagnosed with age-related cataract and received surgery in Aier Eye Hospital(East of Chengdu)were included in this prospective nonrandomized controlled study. The patients were divided into two groups according to the surgery choice, with 23 cases(30 eyes)in femtosecond laser assisted group, and 42 cases(55 eyes)in traditional phacoemulsification group. OCTA was used to compare the changes in central macular thickness, thickness of nerve fiber layer in optic disc, vessel density and blood perfusion preoperatively, and at 1 d and 1 mo postoperatively.RESULTS: BCVA of patients in the two groups was significantly improved and IOP was significantly reduced at 1 mo postoperatively(all P<0.01). The macular nerve fiber layer thickness of the femtosecond laser-assisted group was increased at 1 d and 1 mo postoperatively(all P<0.05), while there was no statistical difference in the traditional phacoemulsification group before and after surgery(all P>0.05); there were significant differences in nerve fiber layer thickness in optic disc, vessel density and blood perfusion in both macula and optic disc of the traditional phacoemulsification group(all P<0.05), but there were no differences in the femtosecond laser assisted group(all P>0.05). Furthermore, there were no significant differences in foveal avascular zone area in the two groups of patients(all P>0.05).CONCLUSION: Femtosecond laser-assisted cataract surgery had less impact on retinal vessels.

Objective:To analyze the impact of global budget on the medical flow treatment and fund allocation in a non-compact medical community based on the symbiosis theory, so as to provide references for relevant authorities to formulate policies for the medical community.Methods:Data on outpatient and emergency visits, discharges, and medical insurance fund usage of the leading hospital and primary medical and health institutions in a non-compact medical community were collected from the health information system of a certain city. The time range of the data spanned from January 2017 to December 2019. The total budget was implemented in April 2018. The symbiotic system of the non-compact medical community was analyzed based on the theory of symbiosis. Descriptive analysis and intermittent time series segmented regression model were used to analyze the changes in indexes related to the flow of medical treatment and fund allocation between the leading hospital and primary institutions under the global budget.Results:The non-compact medical community′s symbiotic system had developed a continuous symbiotic model in organization and an asymmetric reciprocal symbiotic model in behavior. From the perspective of medical treatment flow, the number of outpatient and emergency visits of leading hospital and primary institutions in the medical community showed an upward trend, with little change in the number of discharged patients from 2017 to 2019; The number of patients transferred by the leading hospital increased from 32 in 2017 to 87 in 2019. According to the analysis of the intermittent time series segmented regression model, after the implementation of global budget, the proportion of outpatient and emergency visits in leading hospital was decreased ( β3=-0.43, P<0.05), the proportion of outpatient and emergency visits in primary institutions was on the rise ( β3= 0.02, P<0.05). In terms of fund allocation, the share of health insurance fund of the leading hospital increased from 45.98% in 2017 to 46.51% in 2019, and the primary medical and health institutions decreased from 23.44% to 18.06%, as well as the ratio of per capita income of primary medical and health institutions to that of leading hospitals was decreased from 72.62% to 60.79%. Conclusions:Under the global budget, the outpatient and emergency medical treatment flow in a non-compact medical community had been optimized. However, there was an uneven distribution of funds among medical institutions at all levels. Thus it was recommended to continue to give full play to the positive incentive effect of the global budget, establish a scientific mechanism for distributing benefits, and strengthen supervision and management.

Objective:To understand the incentive effect and influencing factors of the current economic incentive policy for medical alliances in Longhua District of Shenzhen(the alliance for short) on doctors′ willingness to work at primary medical institutions(the primary for short) from the perspective of mental account, and to explore the economic incentive effect of different economic incentive distribution methods on doctors′ willingness to work at the primary.Methods:The questionnaire was designed based on mental account theory. Random sampling was made in November 2019 for a questionnaire survey among doctors in two district-level medical institutions of the alliance in Longhua District of Shenzhen. The purpose was to analyze their inclination to work at the primary and their selection preferences for economic incentive distribution methods under the current economic incentive policy. The data were analyzed by descriptive analysis, and the influencing factors of doctors′ willingness to work at the primary were analyzed by χ2 test and binary logistic regression. Results:A total of 254 valid questionnaires were collected with an effective recovery rate of 90.7%. Among the respondents, 189(74.4%) were willing to work at the primary, 168(66.1%) chose to receive the economic incentives specifically for working at the primary, and 148 people(58.3%) hoped to receive such economic incentives immediately. Education background, self-rated economic income level of doctors and different payment methods of economic incentive for working at the primary had significant effects on their willingness to work at the primary( P<0.05). Conclusions:The current economic incentive policy of the alliance can meet the demands for economic incentives in terms of doctors′ material accounts, and doctors′ overall inclination to work at the primary was strong. If the amount of economic incentives is constant, doctors preferred to receive the economic incentives specifically, mainly affected by income accounts and additional income accounts. In addition, education and self-assessment of economic income level were important factors affecting the willingness of doctors to work at the primary, which may be affected by mental accounts other than material accounts.

A 69-year-old male patient with peripheral T-cell lymphoma received chemotherapy with intravenous doxorubicin liposome. In the first chemotherapy cycle, no obvious adverse reactions appeared. In the second chemotherapy cycle, the patient developed transient muscle soreness during the IV infusion of doxorubicin liposome. In the third chemotherapy cycle, dexamethasone and chlorphenamine were given to prevent anaphylaxis before doxorubicin liposome treatment and the infusion rate was controlled in a standardized way. However, at about 20 minutes of infusion, the patient developed nausea and vomiting. The infusion of doxorubicin was stopped immediately and replaced by IV infusion of 0.9% sodium chloride injection 250 ml. Then the patient developed facial numbness, laryngeal pain, neck discomfort, and multiple parts of skin rash with pruritus. The electrocardiogram monitoring showed heart rate 130 times/min, blood pressure 80/50 mmHg, and oxygen saturation 0.98. The patient was given oxygen inhalation and in half-lying position following the doctor′s advice, but the patient developed dyspnea, hoarseness, and slurred speech 20 minutes later. Physical examination showed the patient′s tongue was hypertrophic, his neck was swollen and thickened. Acute laryngeal edema induced by doxorubicin liposome was considered. Intravenous injection of dexamethasone 10 mg, IV infusion of 10% calcium gluconate, and aerosol inhalation of budesonide inhalation aerosol were given immediately and about 3 hours later, the symptoms gradually improved. Two days later, the allergic symptoms disappeared.

A 69-year-old male patient with peripheral T-cell lymphoma received chemotherapy with intravenous doxorubicin liposome. In the first chemotherapy cycle, no obvious adverse reactions appeared. In the second chemotherapy cycle, the patient developed transient muscle soreness during the IV infusion of doxorubicin liposome. In the third chemotherapy cycle, dexamethasone and chlorphenamine were given to prevent anaphylaxis before doxorubicin liposome treatment and the infusion rate was controlled in a standardized way. However, at about 20 minutes of infusion, the patient developed nausea and vomiting. The infusion of doxorubicin was stopped immediately and replaced by IV infusion of 0.9% sodium chloride injection 250 ml. Then the patient developed facial numbness, laryngeal pain, neck discomfort, and multiple parts of skin rash with pruritus. The electrocardiogram monitoring showed heart rate 130 times/min, blood pressure 80/50 mmHg, and oxygen saturation 0.98. The patient was given oxygen inhalation and in half-lying position following the doctor′s advice, but the patient developed dyspnea, hoarseness, and slurred speech 20 minutes later. Physical examination showed the patient′s tongue was hypertrophic, his neck was swollen and thickened. Acute laryngeal edema induced by doxorubicin liposome was considered. Intravenous injection of dexamethasone 10 mg, IV infusion of 10% calcium gluconate, and aerosol inhalation of budesonide inhalation aerosol were given immediately and about 3 hours later, the symptoms gradually improved. Two days later, the allergic symptoms disappeared.

Objective: To investigate the clinical significance of high definition (HD) MRI rectal lymph node aided diagnostic system based on deep neural network. Methods: The research selected 301 patients with rectal cancer who underwent pelvic HD MRI and reported pelvic lymph node metastasis from July 2016 to December 2017 in Affiliated Hospital of Qingdao University. According to the chronological order, the first 201 cases were used as learning group. The remaining 100 cases were used as verification group. There were 149 males (74.1%) and 52 females in the study group, with an average age of 58.8 years. There were 76 males (76.0%) and 24 females in the validation group, with an average age of 60.2 years. Firstly, Using deep learning technique, researchers trained the 12 060 HD MRI lymph nodes images data of learning group with convolution neural network to simulate the judgment process of radiologists, and established an artificial intelligence automatic recognition system for metastatic lymph nodes of rectal cancer. Then, 6 030 images of the validation group were clinically validated. Artificial intelligence and radiologists simultaneously diagnosed all cases of HD MRI images and made the diagnosis results of metastatic lymph node. Receiver operating characteristic (ROC) curve and area under curve (AUC) were used to compare the diagnostic level of them. Results: After continuous iteration training of the learning group data, the loss function value of artificial intelligence decreased continuously, and the diagnostic error decreased continuously. Among the 6 030 images of verification group, 912 images were considered to exist metastatic lymph nodes in radiologists′ diagnosis and 987 in artificial intelligence diagnosis. There were 772 images having identical diagnostic results of lymph node location and number of metastases with the two methods. Compared with manual diagnosis, the AUC of the intelligent platform was 0.886 2, the diagnostic time of a single case was 10 s, but the average diagnostic time of doctors was 600 s. Conclusion The HD MRI lymph node automatic recognition system based on deep neural network has high accuracy and high efficiency, and has the clinical significance of auxiliary diagnosis.