Paul Vincent Naser

Postoperative placement of patients into a regular ward, an intermediate-care unit (IMC), or an intensive care unit (ICU) is critical for balancing patient safety against resource constraints. Most existing models collapse this decision into a binary ICU versus non-ICU choice and lack a mechanism to tune risk thresholds to local staffing ratios or definitions of ICU‐level events. We developed Neuro-TACTIC, a cost-sensitive machine learning framework that stratifies postoperative neurosurgical patients into three monitoring levels: regular ward, intermediate care unit, and intensive care unit. An XGBoost-based classifier was trained on 27 demographic, intraoperative, and imaging-derived features from a retrospective cohort of 1072 patients undergoing elective craniotomy. A tunable parameter ζ integrates resource-related and harm-related costs to adjust the balance between over- and under-triage. Generalization was assessed in an independent cohort. Across repeated cross-validation and bootstrap analyses, the framework demonstrated stable behavior across cost settings. At the operating point ζ = 0.975, performance was AUCμ = 0.67 ± 0.03 and weighted F1 = 0.49 ± 0.03 in the development cohort, and AUCμ = 0.60 ± 0.04 and weighted F1 = 0.44 ± 0.06 in the independent evaluation cohort (n = 81). Feature importance analyses identified operative duration, tumor volume, surgical position, body mass index, and patient age as the most influential predictors. This study demonstrates the feasibility of cost-sensitive, three-tier postoperative triage modeling in neurosurgical patients. Neuro-TACTIC is a methodological proof-of-concept; prospective validation and multicenter evaluation are required before clinical deployment.

Background/Objectives: Routine postoperative ICU admission following brain tumor surgery may not benefit selected patients. The objective of this study was to develop a risk prediction instrument for early (within 24 h) postoperative adverse events using machine learning techniques. Methods: Retrospective cohort of 1000 consecutive adult patients undergoing elective brain tumor resection. Nine events/interventions (CPR, reintubation, return to OR, mechanical ventilation, vasopressors, impaired consciousness, intracranial hypertension, swallowing disorders, and death) were chosen as target variables. Potential prognostic features (n = 27) from five categories were chosen and a gradient boosting algorithm (XGBoost) was trained and cross-validated in a 5 × 5 fashion. Prognostic performance, potential clinical impact, and relative feature importance were analyzed. Results: Adverse events requiring ICU intervention occurred in 9.2% of cases. Other events not requiring ICU treatment were more frequent (35% of cases). The boosted decision trees yielded a cross-validated ROC-AUC of 0.81 ± 0.02 (mean ± CI95) when using pre- and post-op data. Using only pre-op data (scheduling decisions), ROC-AUC was 0.76 ± 0.02. PR-AUC was 0.38 ± 0.04 and 0.27 ± 0.03 for pre- and post-op data, respectively, compared to a baseline value (random classifier) of 0.092. Targeting a NPV of at least 95% would require ICU admission in just 15% (pre- and post-op data) or 30% (only pre-op data) of cases when using the prediction algorithm. Conclusions: Adoption of a risk prediction instrument based on boosted trees can support decision-makers to optimize ICU resource utilization while maintaining adequate patient safety. This may lead to a relevant reduction in ICU admissions for surveillance purposes.

BACKGROUND: Several individual predictors for outcomes in patients with cerebellar stroke (CS) have been previously identified. There is, however, no established clinical score for CS. Therefore, the aim of this study was to develop simple and accurate grading scales for patients with CS in an effort to better estimate mortality and outcomes. METHODS: This multicentric retrospective study included 531 patients with ischemic CS presenting to 5 different academic neurosurgical and neurological departments throughout Germany between 2008 and 2021. Logistic regression analysis was performed to determine independent predictors related to 30-day mortality and unfavorable outcome (modified Rankin Scale score of 4–6). By weighing each parameter via calculation of regression coefficients, an ischemic CS-score and CS-grading scale (CS-GS) were developed and internally validated. RESULTS: Independent predictors for 30-day mortality were aged ≥70 years (odds ratio, 5.2), Glasgow Coma Scale score 3 to 4 at admission (odds ratio, 2.6), stroke volume ≥25 cm ³ (odds ratio, 2.7), and involvement of the brain stem (odds ratio, 3.9). When integrating each parameter into the CS-score, age≥70 years and brain stem stroke were assigned 2 points, Glasgow Coma Scale score 3 to 4, and stroke volume≥25 cm ³ 1 point resulting in a score ranging from 0 to 6. CS-score of 0, 1, 2, 3, 4, 5, and 6 points resulted in 30-day mortality of 1%, 6%, 6%, 17%, 21%, 55%, and 67%, respectively. Independent predictors for 30-day unfavorable outcomes consisted of all components of the CS-score with an additional variable focused on comorbidities (CS-GS). Except for Glasgow Coma Scale score 3 to 4 at admission, which was assigned 3 points, all other parameters were assigned 1 point resulting in an overall score ranging from 0 to 7. CS-GS of 0, 1, 2, 3, 4, 5, 6, and 7 points resulted in 30-day unfavorable outcome of 1%, 17%, 33%, 40%, 50%, 80%, 77%, and 100%, respectively. Both 30-day mortality and unfavorable outcomes increased with increasing CS-score and CS-GS ( P <0.001). CONCLUSIONS: The CS-score and CS-GS are simple and accurate grading scales for the prediction of 30-day mortality and unfavorable outcome in patients with CS. While the score systems proposed here may not directly impact treatment decisions, it may help discuss mortality and outcome with patients and caregivers.

Purpose: Inflammatory and infectious diseases of the pituitary gland (IIPD) are rare lesions often misdiagnosed preoperatively. Immediate surgery is indicated especially in cases of neurological impairment. However, (chronic) inflammatory processes can mimic other pituitary tumors, such as adenomas, and data on the preoperative diagnostic criteria for IIPD are sparse. Methods: We retrospectively reviewed medical records of 1317 patients who underwent transsphenoidal surgery at our institution between March 2003 and January 2023. A total of 26 cases of histologically confirmed IIPD were identified. Patient records, laboratory parameters, and postoperative course were analyzed and compared with an age, sex, and tumor volume-matched control group of nonfunctioning pituitary adenomas. Results: Pathology confirmed septic infection in ten cases, most commonly caused by bacteria (3/10) and fungi (2/10). In the aseptic group, lymphocytic hypophysitis (8/26) and granulomatous inflammation (3/26) were most frequently observed. Patients with IIPD commonly presented with endocrine and/or neurological dysfunction. No surgical mortality occurred. Preoperative radiographic findings (cystic/solid tumor mass, contrast enhancement) did not significantly differ between IIPD and adenomas. At follow-up, 13 patients required permanent hormone substitution. Conclusion: In conclusion, correct preoperative diagnosis of IIPD remains challenging, as neither radiographic findings nor preoperative laboratory workup unequivocally identify these lesions. Surgical treatment facilitates decompression of supra- and parasellar structures. Furthermore, this low-morbidity procedure enables the identification of pathogens or inflammatory diseases requiring targeted medical treatment, which is crucial for these patients. Establishing a correct diagnosis through surgery and histopathological confirmation thus remains of utmost importance.

Background: This ex vivo experimental study sought to compare screw planning accuracy of a self-derived deep-learning-based (DL) and a commercial atlas-based (ATL) tool and to assess robustness towards pathologic spinal anatomy. Methods: From a consecutive registry, 50 cases (256 screws in L1-L5) were randomly selected for experimental planning. Reference screws were manually planned by two independent raters. Additional planning sets were created using the automatic DL and ATL tools. Using Python, automatic planning was compared to the reference in 3D space by calculating minimal absolute distances (MAD) for screw head and tip points (mm) and angular deviation (degree). Results were evaluated for interrater variability of reference screws. Robustness was evaluated in subgroups stratified for alteration of spinal anatomy. Results: Planning was successful in all 256 screws using DL and in 208/256 (81%) using ATL. MAD to the reference for head and tip points and angular deviation was 3.93 ± 2.08 mm, 3.49 ± 1.80 mm and 4.46 ± 2.86° for DL and 7.77 ± 3.65 mm, 7.81 ± 4.75 mm and 6.70 ± 3.53° for ATL, respectively. Corresponding interrater variance for reference screws was 4.89 ± 2.04 mm, 4.36 ± 2.25 mm and 5.27 ± 3.20°, respectively. Planning accuracy was comparable to the manual reference for DL, while ATL produced significantly inferior results (p < 0.0001). DL was robust to altered spinal anatomy while planning failure was pronounced for ATL in 28/82 screws (34%) in the subgroup with severely altered spinal anatomy and alignment (p < 0.0001). Conclusions: Deep learning appears to be a promising approach to reliable automated screw planning, coping well with anatomic variations of the spine that severely limit the accuracy of ATL systems.