February 2021 Medical Corner
Neural Network Modeling
This month the PNA Medical Corner spotlights an article co-authored by Dr. Martin Weiss, chairman of neurosurgery at USC and a member of the PNA. The study used neural network modeling to look at the factors that lead to negative outcomes, which include the presence of a tumor that has recurred after surgery and visual deficits that did not improve after surgery. The authors analyzed the outcomes for 341 patients with acromegaly, Cushings or a mammosomatotroph adenoma, 81 of whom had sub-optimal outcomes. Their modeling was able to predict with 87.1% accuracy which patients are more at risk for a poor outcome.
Neural network modeling for prediction of recurrence, progression, and hormonal non-remission in patients following resection of functional pituitary adenomas
Shane Shahrestani 1 2, Tyler Cardinal 3, Alexander Micko 3 4, Ben A Strickland 3, Dhiraj J Pangal 3, Guillaume Kugener 3, Martin H Weiss 3, John Carmichael 3, Gabriel Zada 3 Affiliations expand
• PMID: 33528731 DOI: 10.1007/s11102-021-01128-5
Functional pituitary adenomas (FPAs) cause severe neuro-endocrinopathies including Cushing's disease (CD) and acromegaly. While many are effectively cured following FPA resection, some encounter disease recurrence/progression or hormonal non-remission requiring adjuvant treatment. Identification of risk factors for suboptimal postoperative outcomes may guide initiation of adjuvant multimodal therapies.
Patients undergoing endonasal transsphenoidal resection for CD, acromegaly, and mammosomatotroph adenomas between 1992 and 2019 were identified. Good outcomes were defined as hormonal remission without imaging/biochemical evidence of disease recurrence/progression, while suboptimal outcomes were defined as hormonal non-remission or MRI evidence of recurrence/progression despite adjuvant treatment. Multivariate regression modeling and multilayered neural networks (NN) were implemented. The training sets randomly sampled 60% of all FPA patients, and validation/testing sets were 20% samples each.
348 patients with mean age of 41.7 years were identified. Eighty-one patients (23.3%) reported suboptimal outcomes. Variables predictive of suboptimal outcomes included: Requirement for additional surgery in patients who previously had surgery and continue to have functionally active tumor (p = 0.0069; OR = 1.51, 95%CI 1.12-2.04), Preoperative visual deficit not improved after surgery (p = 0.0033; OR = 1.12, 95%CI 1.04-1.20), Transient diabetes insipidus (p = 0.013; OR = 1.27, 95%CI 1.05-1.52), Higher MIB-1/Ki-67 labeling index (p = 0.038; OR = 1.08, 95%CI 1.01-1.15), and preoperative low cortisol axis (p = 0.040; OR = 2.72, 95%CI 1.06-7.01). The NN had overall accuracy of 87.1%, sensitivity of 89.5%, specificity of 76.9%, positive predictive value of 94.4%, and negative predictive value of 62.5%. NNs for all FPAs were more robust than for CD or acromegaly/mammosomatotroph alone.
We demonstrate capability of predicting suboptimal postoperative outcomes with high accuracy. NNs may aid in stratifying patients for risk of suboptimal outcomes, thereby guiding implementation of adjuvant treatment in high-risk patients.
Adenoma; Functional; Machine learning; Pituitary; Progression; Recurrence.