BACKGROUND: Postoperative pulmonary complications (PPCs) are major adverse events in neurosurgical patients. This study aimed to develop and validate machine learning models predicting PPCs after neurosurgery. METHODS: PPCs were defined according to the European Perioperative Clinical Outcome standards as occurring within 7 postoperative days. Data of cases meeting inclusion/exclusion criteria were extracted from the anesthesia information management system to create three datasets: The development (data of Huashan Hospital, Fudan University from 2018 to 2020), temporal validation (data of Huashan Hospital, Fudan University in 2021) and external validation (data of other three hospitals in 2023) datasets. Machine learning models of six algorithms were trained using either 35 retrievable and plausible features or the 11 features selected by Lasso regression. Temporal validation was conducted for all models and the 11-feature models were also externally validated. Independent risk factors were identified and feature importance in top models was analyzed. RESULTS: PPCs occurred in 712 of 7533 (9.5%), 258 of 2824 (9.1%), and 207 of 2300 (9.0%) patients in the development, temporal validation and external validation datasets, respectively. During cross-validation training, all models except Bayes demonstrated good discrimination with an area under the receiver operating characteristic curve (AUC) of 0.840. In temporal validation of full-feature models, deep neural network (DNN) performed the best with an AUC of 0.835 (95% confidence interval [CI]: 0.805-0.858) and a Brier score of 0.069, followed by Logistic regression (LR), random forest and XGBoost. The 11-feature models performed comparable to full-feature models with very close but statistically significantly lower AUCs, with the top models of DNN and LR in temporal and external validations. An 11-feature nomogram was drawn based on the LR algorithm and it outperformed the minimally modified Assess respiratory RIsk in Surgical patients in CATalonia (ARISCAT) and Laparoscopic Surgery Video Educational Guidelines (LAS VEGAS) scores with a higher AUC (LR: 0.824, ARISCAT: 0.672, LAS: 0.663). Independent risk factors based on multivariate LR mostly overlapped with Lasso-selected features, but lacked consistency with the important features using the Shapley additive explanation (SHAP) method of the LR model. CONCLUSIONS: The developed models, especially the DNN model and the nomogram, had good discrimination and calibration, and could be used for predicting PPCs in neurosurgical patients. The establishment of machine learning models and the ascertainment of risk factors might assist clinical decision support for improving surgical outcomes. TRIAL REGISTRATION ChiCTR 2100047474; https://www.chictr.org.cn/showproj.html?proj=128279 .
Adult ; Aged ; Female ; Humans ; Male ; Middle Aged ; Algorithms ; Lung Diseases/etiology* ; Machine Learning ; Neurosurgical Procedures/adverse effects* ; Postoperative Complications/diagnosis* ; Risk Factors ; ROC Curve

OBJECTIVE: To precise classify sacral meningeal cysts, effective guide minimally invasive neurosurgery and postoperative personalized rehabilitation by multiple dimensions radiographic reconstruction MRI. METHODS: From March to December 2021, based on the original 3D-fast imaging employing steadystate acquisition (FIESTA) scanning sequence, 92 patients with sacral meningeal cysts were pre-operatively evaluated by multiple dimensional reconstruction MRI. The shape of nerve root and the leakage of cyst were reconstructed according to the direction of nerve root or leakage track showed on original MRI scans. Sacral canal cysts were accurately classified as including nerve root and without nerve root, so as to accurately design the incision of skin and formulate corresponding open range of the posterior wall of the sacral canal. Under the microscope intraoperation, the shape of the nerve roots inside cysts or leakage track of the cysts without nerve roots were verified and explored. After the reinforcement and shaping operation, several reexaminations of multiple dimensional reconstruction MRI were performed to understand the deformation of the nerve root and hydrops in the operation cavity, so as to formulate a persona-lized rehabilitation plan for the patients. RESULTS: Among the 92 patients with sacral mengingeal cyst, 58 (63.0%) cysts with nerve root cyst, 29 (31.5%) cysts without nerve root cyst, and 5 (5.4%) cysts with mixed sacral canal cyst. In 58 patients with nerve root cysts, the accuracy of preoperative clinical classification on MRI image reached 96.6% (56/58) through confirmation by operating microscope. Only 2 cases of large single cyst with nerve root on the head of cyst were mistaken for without nerve root type. In 29 patients with sacral cyst without nerve root, the accuracy of preoperative image reached 100% through confirmation by operating microscope. The accuracy of judging the internal nerve root and leakage of 12 cases with recurrent sacral cyst was also 100%. Two cases of delayed postoperative hydrops were found one month after operation. After rehabilitation treatment by moxibustion and bathing, the hydrops disappeared 4-6 months after operation. CONCLUSION Multiple dimensional reconstruction MRI can precisely make clinical classification of sacral meningeal cysts before operation, guide minimally invasive neurosurgery effectively, and improve the rehabilitation effect.
Humans ; Magnetic Resonance Imaging/methods* ; Male ; Female ; Sacrum/surgery* ; Adult ; Middle Aged ; Imaging, Three-Dimensional/methods* ; Cysts/rehabilitation* ; Aged ; Adolescent ; Young Adult ; Spinal Nerve Roots/diagnostic imaging* ; Minimally Invasive Surgical Procedures ; Neurosurgical Procedures/methods*

With the continuous progress of medical technology, the application of stereotactic surgical robots in the field of neurosurgical operations has become increasingly extensive and important. This paper focuses on the registration principle of ultra-wideband positioning technology in stereotactic surgical robots during neurosurgical operations. It elaborates in detail on the processes of positioning and navigation, and illustrates different registration algorithms with examples. In addition, this paper looks ahead to the future development directions of ultra-wideband positioning technology in surgical robots, aiming to provide references for further development of surgical robots.
Neurosurgical Procedures/instrumentation* ; Robotic Surgical Procedures/methods* ; Algorithms ; Robotics/methods*

Objective To investigate the effect of health failure mode and effect analysis(HFMEA)in optimizing the management process of postoperative diabetes insipidus in children undergoing neurosurgery.Methods Based on HFMEA,a management flowchart for postoperative diabetes insipidus in children undergoing neurosurgery was created.Brainstorming was adopted to identify failure modes in the workflow,analyze risk factors,and develop improvement measures,thereby refining the management flowchart.The amelioration and prognosis of diabetes insipidus in these children before(October 2022 to November 2023)and after(January 2024 to February 2025)implementation of the management flowchart were compared.Results The HFMEA-based management process for postoperative diabetes insipidus in children undergoing neurosurgery alleviated the symptoms of diabetes insipidus regarding the number of diabetes insipidus in the pediatric intensive care unit(P=0.006),the average daily urine output in the pediatric intensive care unit(P=0.001),the proportion of electrolyte abnormalities at discharge/transfer(P=0.037),the duration of mechanical ventilation(P=0.007),and the length of stay in the intensive care unit(P=0.001).Conclusion The HFMEA-based management process for postoperative diabetes insipidus in children undergoing neurosurgery is beneficial to the optimization of the management process,the alleviation of postoperative diabetes insipidus,and the improvement of prognosis in these children.
Humans ; Diabetes Insipidus/etiology* ; Neurosurgical Procedures/adverse effects* ; Child ; Postoperative Complications/therapy* ; Healthcare Failure Mode and Effect Analysis ; Intensive Care Units, Pediatric ; Risk Factors

Humans ; Skull Base/surgery* ; Endoscopy/methods* ; Neurosurgical Procedures/methods*

Humans ; Endoscopy ; Neurosurgical Procedures ; Skull Base/surgery*

Selective dorsal neurotomy (SDN) is a surgical treatment for primary premature ejaculation (PE), but there is still no standard surgical procedure for selecting the branches of the dorsal penile nerves to be removed. We performed this study to explore the value of intraoperative neurophysiological monitoring (IONM) of the penile sensory-evoked potential (PSEP) for standard surgical procedures in SDN. One hundred and twenty primary PE patients undergoing SDN were selected as the PE group and 120 non-PE patients were selected as the normal group. The PSEP was monitored and compared between the two groups under both natural and general anesthesia (GA) states. In addition, patients in the PE group were randomly divided into the IONM group and the non-IONM group. During SDN surgery, PSEP parameters of the IONM group were recorded and analyzed. The differences in PE-related outcome measurements between the perioperative period and 3 months' postoperation were compared for the PE patients, and the differences in effectiveness and complications between the IONM group and the non-IONM group were compared. The results showed that the average latency of the PSEP in the PE group was shorter than that in the normal group under both natural and GA states (P < 0.001). Three months after surgery, the significant effective rates in the IONM and non-IONM groups were 63.6% and 34.0%, respectively (P < 0.01), and the difference in complications between the two groups was significant (P < 0.05). IONM might be useful in improving the short-term therapeutic effectiveness and reducing the complications of SDN.
Male ; Humans ; Premature Ejaculation/surgery* ; Intraoperative Neurophysiological Monitoring/methods* ; Prospective Studies ; Neurosurgical Procedures/methods* ; Penis/surgery* ; Retrospective Studies

OBJECTIVE: To evaluate the value of high-resolution ultrasound the diagnosis and prognosis of cubital tunnel syndrome. METHODS: From January 2018 to June 2019, 47 patients with cubital tunnel syndrome were treated with ulnar nerve release and anterior subcutaneous transposition. There were 41 males and 6 females, aged from 27 to 73 years old. There were 31 cases on the right, 15 cases on the left, and 1 case on both sides. The diameter of ulnar nerve was measured by high-resolution ultrasound pre-and post-operatively, and measured directly during the operation. The recovery status of the patients was evaluated by the trial standard of ulnar nerve function assessment, and the satisfaction of the patients was assessed. RESULTS: All the 47 cases were followed up for an average of 12 months and the incisions healed well. The diameter of ulnar nerve at the compression level was (0.16±0.04) cm pre-operatively, and the diameter of ulnar nerve was (0.23±0.04) cm post-operatively. The evaluation of ulnar nerve function:excellent in 16 cases, good in 18 cases and fair in 13 cases. Twelve months post-operatively, 28 patients were satisfied, 10 patients were general and 9 patients were dissatisfied. CONCLUSION The preoperative examination of ulnar nerve by high-resolution ultrasound is consistent with the intuitive measurement during operation, and the result of postoperative examination of ulnar nerve by high-resolution ultrasound is consistent with follow-up results. High-resolution ultrasound is an effective auxiliary method for the diagnosis and treatment of cubital tunnel syndrome.
Male ; Female ; Humans ; Adult ; Middle Aged ; Aged ; Cubital Tunnel Syndrome/surgery* ; Ulnar Nerve/surgery* ; Neurosurgical Procedures/methods* ; Decompression, Surgical/methods* ; Prognosis

Neurosurgery is a highly specialized field: it often involves surgical manipulation of noble structures and cerebral retraction is frequently necessary to reach deep-seated brain lesions. There are still no reliable methods preventing possible retraction complications. The objective of this study was to design work chambers well suited for transcranial endoscopic surgery while providing safe retraction of the surrounding brain tissue. The chamber is designed to be inserted close to the intracranial point of interest; once it is best placed it can be opened. This should guarantee an appreciable workspace similar to that of current neurosurgical procedures. The experimental aspect of this study involved the use of a force sensor to evaluate the pressures exerted on the brain tissue during the retraction phase. Following pterional craniotomy, pressure measurements were made during retraction with the use of a conventional metal spatula with different inclinations. Note that, although the force values necessary for retraction and exerted on the spatula by the neurosurgeon are the same, the local pressure exerted on the parenchyma at the edge of the spatula at different inclinations varied greatly. A new method of cerebral retraction using a chamber retractor (CR) has been designed to avoid any type of complication due to spatula edge overpressures and to maintain acceptable pressure values exerted on the parenchyma.
Humans ; Brain/surgery* ; Neurosurgical Procedures/methods* ; Neurosurgery ; Brain Neoplasms ; Endoscopy

OBJECTIVE: To review targeted muscle reinnervation (TMR) surgery for the construction of intelligent prosthetic human-machine interface, thus providing a new clinical intervention paradigm for the functional reconstruction of residual limbs in amputees. METHODS: Extensively consulted relevant literature domestically and abroad and systematically expounded the surgical requirements of intelligent prosthetics, TMR operation plan, target population, prognosis, as well as the development and future of TMR. RESULTS: TMR facilitates intuitive control of intelligent prostheses in amputees by reconstructing the "brain-spinal cord-peripheral nerve-skeletal muscle" neurotransmission pathway and increasing the surface electromyographic signals required for pattern recognition. TMR surgery for different purposes is suitable for different target populations. CONCLUSION TMR surgery has been certified abroad as a transformative technology for improving prosthetic manipulation, and is expected to become a new clinical paradigm for 2 million amputees in China.
Humans ; Artificial Limbs ; Muscle, Skeletal ; Neurosurgical Procedures ; Plastic Surgery Procedures ; Prosthesis Implantation