Machine Learning Prediction of Visual Outcome after Surgical Decompression of Sellar Region Tumors

Visual morbidity in macroprolactinoma: A retrospective cohort study

OBJECTIVE

The management of visual field damage in patients with macroprolactinomas is a major therapeutic challenge. We aimed to study the visual morbidity associated with macroprolactinoma and its outcomes following medical and surgical treatment. We aimed to identify predictors of visual recovery.

METHODS

We retrospectively reviewed patient's data including clinical presentation, serial pituitary magnetic resonance imaging, laboratory tests, visual symptoms and neuro-ophthalmologic examination, visual field tests and optical coherence tomography tests. The main outcome was complete visual field recovery. Descriptive analyses were conducted. Predictors of visual recovery were investigated.

PATIENTS

The study cohort included 150 patients with macroprolactinoma [median follow-up, 6.0 years (interquartile range (IQR) 2.9-10.6)].

RESULTS

At diagnosis, visual field defects were evident in 40 patients (26.7%). At the end of follow-up, 24 out of 39 available visual field tests (61.5%) exhibited complete recovery. Patients that achieved complete visual recovery had smaller macroadenomas at diagnosis [30.5 mm (15.0-80.0) vs. 42.0 mm (30.0-85.0), p < .01], lower baseline serum prolactin levels [1414 mcg/L (489-3586) vs. 4119 mcg/L (2715-6315), p < .01], lower rates of central hypogonadism (78.3% vs. 93.3%, p = .05) and central hypothyroidism (20.8% vs. 53.3%, p = .04), lower rates of compressive optic neuropathy (35.3% vs. 87.5%, p = .02) and a better visual acuity (better than 6/8 in both eyes, 93.7% vs. 28.6%, p < .01).

CONCLUSIONS

In our cohort of 150 patients with macroprolactinoma, 40 patients (26.7%) presented with visual field defects, of which 61.5% achieved complete visual recovery with treatment. Patients that achieved complete visual recovery presented with smaller macroadenomas, lower serum prolactin levels, lower rates of central hypogonadism and central hypothyroidism, lower rates of compressive optic neuropathy and better visual acuity.

Current status of artificial intelligence technologies in pituitary adenoma surgery: a scoping review

PURPOSE

Pituitary adenoma surgery is a complex procedure due to critical adjacent neurovascular structures, variations in size and extensions of the lesions, and potential hormonal imbalances. The integration of artificial intelligence (AI) and machine learning (ML) has demonstrated considerable potential in assisting neurosurgeons in decision-making, optimizing surgical outcomes, and providing real-time feedback. This scoping review comprehensively summarizes the current status of AI/ML technologies in pituitary adenoma surgery, highlighting their strengths and limitations.

METHODS

PubMed, Embase, Web of Science, and Scopus were searched following the PRISMA-ScR guidelines. Studies discussing the use of AI/ML in pituitary adenoma surgery were included. Eligible studies were grouped to analyze the different outcomes of interest of current AI/ML technologies.

RESULTS

Among the 2438 identified articles, 44 studies met the inclusion criteria, with a total of seventeen different algorithms utilized across all studies. Studies were divided into two groups based on their input type: clinicopathological and imaging input. The four main outcome variables evaluated in the studies included: outcome (remission, recurrence or progression, gross-total resection, vision improvement, and hormonal recovery), complications (CSF leak, readmission, hyponatremia, and hypopituitarism), cost, and adenoma-related factors (aggressiveness, consistency, and Ki-67 labeling) prediction. Three studies focusing on workflow analysis and real-time navigation were discussed separately.

CONCLUSION

AI/ML modeling holds promise for improving pituitary adenoma surgery by enhancing preoperative planning and optimizing surgical strategies. However, addressing challenges such as algorithm selection, performance evaluation, data heterogeneity, and ethics is essential to establish robust and reliable ML models that can revolutionize neurosurgical practice and benefit patients.

Severe hypernatremia during postoperative care in patients with craniopharyngioma

Purpose

We aimed to describe and predict the risk of severe hypernatremia after surgical resection of craniopharyngioma and to identify the association of water intake, urine output, and sodium level change in the patients.

Method

The outcome was postoperative severe hypernatremia. We identified risk factors associated with hypernatremia using multivariable regression. We trained machine learning models to predict the outcome. We compared serum sodium change, intravenous input, oral input, total input, urine output, and net fluid balance according to different nurse shifts.

Results

Among 234 included patients, 125 developed severe hypernatremia after surgery. The peak incidence occurred during day 0 and day 6 after surgery. The risk was increased in patients with gross total resection (odds ratio (OR) 2.41, P < 0.001), high Puget classification (OR 4.44, P = 0.026), preoperative adrenal insufficiency (OR 2.01, P = 0.040), and preoperative hypernatremia (OR 5.55, P < 0.001). The random forest algorithm had the highest area under the receiver operating characteristic curve (0.770, 95% CI, 0.727-0.813) in predicting the outcome and was validated in the prospective validation cohort. Overnight shifts were associated with the highest serum sodium increase (P = 0.010), less intravenous input (P < 0.001), and less desmopressin use (P < 0.001).

Conclusion

The overall incidence of severe hypernatremia after surgical resection of craniopharyngioma was significant, especially in patients with gross total resection, hypothalamus distortion, preoperative adrenal insufficiency, and preoperative severe hypernatremia. Less intravenous input and less desmopressin use were associated with serum sodium increases, especially during overnight shifts.

Predictive Modeling of Long-Term Glaucoma Progression Based on Initial Ophthalmic Data and Optic Nerve Head Characteristics

Purpose

The purpose of this study was to develop a model, based on initial optic nerve head (ONH) characteristics, predictive of long-term rapid retinal nerve fiber layer (RNFL) thinning in patients with open-angle glaucoma (OAG).

Methods

This study evaluated 712 eyes with OAG that had been followed up for >5 years with annual evaluation of RNFL thickness. Baseline ophthalmic features were incorporated into the machine learning models for prediction of faster RNFL thinning. The model was trained and tested using a random forest (RF) method, and was interpreted using Shapley additive explanations. Factors associated with faster rate of RNFL thinning were statistically evaluated using a decision tree.

Results

The RF model showed that greater lamina cribrosa (LC) curvature, higher intraocular pressure (IOP), visual field mean deviation converging towards −5 dB, and thinner peripapillary choroid at baseline were the four most significant features predicting faster RNFL thinning. Partial interaction between the features showed that larger LC curvature was a strong factor for faster RNFL thinning when it exceeded approximately 12.0. When the LC curvature was ≤12, higher initial IOP and thinner peripapillary choroid played a role in the rapid RNFL thinning. Based on the decision tree, higher IOP (>26.5 mm Hg), greater laminar curvature (>13.95), and thinner peripapillary choroid (≤117.5 µm) were the 3 most important determinants affecting the rate of RNFL thinning.

Conclusions

Baseline ophthalmic data and ONH characteristics of patients with OAG were predictive of eyes at risk of faster progression. Combinations of important characteristics, such as IOP, LC curvature, and choroidal thickness, could stratify eyes into groups with different rates of RNFL thinning.

Translational Relevance

This work lays the foundations for developing prediction models to estimate glaucoma prognosis based on initial ONH characteristics.