Objective To develop a deep learning model based on fundus retinal images to improve the detection rate of mild cognitive impairment(MCI)in patients with coronary heart disease,achieve early intervention and improve prognosis.Methods The study was a single-center cross-sectional study that retrospectively included patients diagnosed with coronary heart disease(CHD)by coronary angiography(≥50％ stenosis of at least one coronary vessel)from Beijing Anzhen Hospital between November 2021 and December 2022.The whole data set was randomly divided into the training set and the testing set according to the ratio of 8∶2 for model development.After that,the patient data of the same center from January 2023 to April 2023 were included in the time verification method to verify the model.The diagnostic criteria for MCI were MMSE＜27 or MoCA＜26.Four kinds of convolutional neural network(CNN)architectures were used to train fundus images,and a comprehensive vision model of MCI detection was established through model integration.The area under the curve(AUC),sensitivity and specificity of the receiver operating curve(ROC)were used to evaluate the performance of the AI model.Results We collected 5 880 eligible fundus images from 3 368 CHD patients.Based on the results of the MMSE scale,the algorithm was labeled,including 2 898 males and 527 MCI patients.The AUC of the deep learning model in the test group is 0.733(95％CI 0.688-0.778),and the sensitivity of the algorithm in the test group is 0.577(95％CI 0.528-0.625)by using the operating point with the maximum sum of sensitivity and specificity.With a specificity of 0.758(95％CI 0.714-0.802),corresponding to a validated AUC of 0.710(95％CI 0.601-0.818).Based on the results of the MoCA scale,the algorithm labels 2 437 males and 1 626 MCI patients.The AUC of the deep learning model in the test group was 0.702(95％CI 0.671-0.733).The operating point with the maximum sum of sensitivity and specificity was selected,and the sensitivity of the algorithm was 0.749(95％CI 0.719-0.778)and the specificity was 0.561(95％CI 0.527-0.595),corresponding to the AUC value of the verification group was 0.674(95％CI 0.622-0.726).Conclusions The deep learning algorithm model based on fundus images has good diagnostic performance,and may be used as a new non-invasive,convenient and rapid screening method for MCI in CHD population.

Objective To develop a deep learning model based on fundus retinal images to improve the detection rate of mild cognitive impairment(MCI)in patients with coronary heart disease,achieve early intervention and improve prognosis.Methods The study was a single-center cross-sectional study that retrospectively included patients diagnosed with coronary heart disease(CHD)by coronary angiography(≥50％ stenosis of at least one coronary vessel)from Beijing Anzhen Hospital between November 2021 and December 2022.The whole data set was randomly divided into the training set and the testing set according to the ratio of 8∶2 for model development.After that,the patient data of the same center from January 2023 to April 2023 were included in the time verification method to verify the model.The diagnostic criteria for MCI were MMSE＜27 or MoCA＜26.Four kinds of convolutional neural network(CNN)architectures were used to train fundus images,and a comprehensive vision model of MCI detection was established through model integration.The area under the curve(AUC),sensitivity and specificity of the receiver operating curve(ROC)were used to evaluate the performance of the AI model.Results We collected 5 880 eligible fundus images from 3 368 CHD patients.Based on the results of the MMSE scale,the algorithm was labeled,including 2 898 males and 527 MCI patients.The AUC of the deep learning model in the test group is 0.733(95％CI 0.688-0.778),and the sensitivity of the algorithm in the test group is 0.577(95％CI 0.528-0.625)by using the operating point with the maximum sum of sensitivity and specificity.With a specificity of 0.758(95％CI 0.714-0.802),corresponding to a validated AUC of 0.710(95％CI 0.601-0.818).Based on the results of the MoCA scale,the algorithm labels 2 437 males and 1 626 MCI patients.The AUC of the deep learning model in the test group was 0.702(95％CI 0.671-0.733).The operating point with the maximum sum of sensitivity and specificity was selected,and the sensitivity of the algorithm was 0.749(95％CI 0.719-0.778)and the specificity was 0.561(95％CI 0.527-0.595),corresponding to the AUC value of the verification group was 0.674(95％CI 0.622-0.726).Conclusions The deep learning algorithm model based on fundus images has good diagnostic performance,and may be used as a new non-invasive,convenient and rapid screening method for MCI in CHD population.

Objective To explore the application effect of dexmedetomidine combined with ropivacaine for quadratus lumborum block at the lateral supra-arcuate ligament(QLB-LSAL) in open hepatocellular carcinoma resection.Methods A prospective study was conducted in 60 patients who underwent elective open hepatocellular carcinoma resection at Jining First People's Hospital. The patients were randomly divided into the compound group and the control group,with 30 cases in each group. Patients in the compound group received QLB-LSAL combined general anesthesia,and patients in the control group received simple general anesthesia. All patients underwent patient controlled intravenous analgesia (PCIA)postoperatively. The mean arterial pressure (MAP),heart rate (HR) and visual analogue scale (VAS) scores during rest and coughing at different time points were observed and compared between the two groups. The number of postoperative PCIA compressions,the dosage of sufentanil,the first postoperative exhaust time,the first postoperative ambulation time,the hospital stay and the occurrence of adverse reactions of the two groups were recorded. Results In the compound group,the HR and MAP were significantly lower than those of the control group at the time of skin incision (T2) and at the end of surgery (T3);the VAS scores during rest and coughing were significantly lower than those of the control group at the time of exiting the anesthesia recovery room and 6 hours and 12 hours after surgery;and the PCIA compression times were significantly less than those of the control group;the dosage of sufentanil was significantly lower than that in the control group 0 to 24 hours after surgery,and the dosage of sufentanil was higher than that in the control group 25 to 48 hours after surgery;the first postoperative ambulation time and the first postoperative exhaust time were significantly earlier than those in the control group;and the above differences were statistically significant(P<0.05). There was no significant difference in the HR or MAP at 5 minutes into the operating room (T0) and 5 minutes before skin incision (T1),VAS scores during rest and coughing 24 hours and 48 hours after surgery,hospital stay and incidence of adverse reactions between the two groups (P>0.05).Conclusion For patients with open hepatocellular carcinoma resection,dexmedetomidine combined with ropivazine for QLB-LSAL can provide more ideal postoperative analgesia,reduce perioperative opioid consumption,and have less impact on circulatory system,which is conducive to rapid postoperative recovery.

Objective To explore the lung protective effect of pressure controlled ventilation-volume guaranteed(PCV-VG)combined with driving pressure(DP)guided lung protective ventilation strategy in patients undergoing thoracoscopic and laparoscopic radical esophagectomy.Methods 70 patients scheduled for elective thoracoscopic and laparoscopic radical esophagectomy were allocated into two groups using a random number table method:Conventional lung protective ventilation strategy group(group C)and DP guided lung protective ventilation strategy under PCV-VG mode group(group P),35 case in each group.Peak airway pressure(Ppeak),plateau pressure(Pplat),dynamic compliance(Cdyn)and DP were compared between the two groups at 5 minutes after intubation(T1),30 min after pneumoperitoneum established(T2),just prior to one lung ventilation(OLV)(T3),30 min after OLV(T4),60 min after OLV(T5)and 15 min from recovery of two lung ventilation(TLV)(T6).The blood pressure(BP),heart rate(HR),arterial partial pressure of oxygen(PaO2),partial pressure of carbon dioxide in arterial blood(PaCO2)and pH were recorded before anesthesia(T0),T2,T3,T4,T5 and T6 time points.The occurrence of postoperative pulmonary complications(PPCs)also recorded.Results Compared with group C,Ppeak in group P at T1,T2,T4,T5 and T6 time points was significantly decreased,and Cdyn was obviously increased,the differences were statistically significant(P＜0.05).At the T1,T4,T5 and T6 time points,the DP was lower in group P compared to group C,and Pplat at T6 time point was lower than that in group C,the differences were statistically significant(P＜0.05).At the time points of T4 and T5,the PaO2 in group P was higher than that in Group C,and the PaCO2 at T6 time point was also higher than that in group C,the differences were statistically significant(P＜0.05).The comparison of PaCO2 at T0,T2,T3,T4 and T5 time points of the two groups,the difference was not statistically significant(P＞0.05).Comparison of pH between the two groups,the difference was not statistically significant at all time points(P＞0.05).The systolic blood pressure(SBP)of group P was higher than that of group C at the T4 time point,and the diastolic blood pressure(DBP)was lower than that of group C at T6 time point,and the differences were statistically significant(P＜0.05);There were no significant differences in SBP and DBP at T0,T2,T3 and T5 time points,and HR at each time point between the two groups(P＞0.05).There was no statistically significant difference in the occurrence of PPCs within 7 d after operation between the two groups(P＞0.05).Conclusion DP guided lung protective ventilation strategy under PCV-VG mode can improve intraoperative respiratory mechanics,and increase oxygenation during OLV in patients undergoing thoracoscopic and laparoscopic radical esophagectomy,but it does not significantly affect the incidence of PPCs within 7 d after operation.It is worthy clinical significant.