Auto interpretable depth learning model to analyze the hemodynamic changes and pulmonary complications in laparoscopic gynecologic tumor surgery with nalmefene hydrochloride combined with general anesthesia.

OBJECTIVE

In this work, based on intelligent computing, the biological signals of patients were analyzed to investigate the hemodynamic changes and pulmonary complications of Nalmefene Hcl combined with general anesthesia (GA) in laparoscopic gynecological tumor surgery (GTS).

PATIENTS AND METHODS

Eighty computer-aided GTS patients were randomly divided into a control group (n = 40) and an observation group (n = 40). Biomedical electrocardiogram (ECG) signals were detected by wavelet neural network in all patients undergoing laparoscopic gynecological tumor surgery and were computerized according to the android interface definition language model (AIDL). GA was used during surgery. The observation group was injected intravenously with 0.2 μg/kg naproxenacin hydrochloride after operation. The control group was given 1 mL 0.9% sodium chloride solution after operation. Mean arterial pressure (MAP), heart rate (HR), respiratory rate (RR), pulse oxygen saturation (SPO), coma score, and adverse reactions (AR) were compared between the two groups at 10, 20, and 30 minutes after wakefulness. The hemodynamic parameters between the two groups were compared. Serum urocholine (URO) and creatinine (Cre) levels were analyzed in patients without complications.

RESULTS

ECG waveform based on wavelet neural network has a high recognition rate and strong generalization ability. 37 patients in the observation group recovered within 10 minutes after surgery, and the recovery rate at 30 minutes was 95%. 30 patients in the control group awoke 10 minutes after the operation, and the recovery rate at 30 minutes m-AR was 75%. The average abstract windows toolkit (AWT) of the observation group and control group was 11.87 ± 5.78 min and 16.46 ± 5.32 min, respectively, and the difference was significant (p < 0.05). There were significant differences in HR, systolic blood pressure (SBP), and diastolic blood pressure (DBP) between the observation group and the control group during the extubation (p < 0.05). Blood gas indexes PaO2, PvO2, PaCO2, and PvCO2 in the observation group were significantly different from those in the control group half an hour after the operation and half an hour after pneumoperitoneum (p > 0.05).

CONCLUSIONS

Intelligent computational biological signal detection was beneficial to the development of surgery. Nalmefene Hcl combined with GA on the basis of the AIDL model has a significant effect on the awakening of GTS patients and can shorten sleep time. Patients with underlying cardiac disease were more likely to develop postoperative lung complications.