ABSTRACT
Introduction: Gross total resection (GTR), Biochemical Remission (BR) and restitution of a priorly disrupted hypothalamus pituitary axis (new improvement, IMP) are important factors in pituitary adenoma (PA) resection surgery. Prediction of these metrics using simple and preoperatively available data might help improve patient care and contribute to a more personalized medicine. Research question: This study aims to develop machine learning models predicting GTR, BR, and IMP in PA resection surgery, using preoperatively available data. Material and methods: With data from patients undergoing endoscopic transsphenoidal surgery for PAs machine learning models for prediction of GTR, BR and IMP were developed and externally validated. Development was carried out on a registry from Bologna, Italy while external validation was conducted using patient data from Zurich, Switzerland. Results: The model development cohort consisted of 1203 patients. GTR was achieved in 207 (17.2%, 945 (78.6%) missing), BR in 173 (14.4%, 992 (82.5%) missing) and IMP in 208 (17.3%, 167 (13.9%) missing) cases. In the external validation cohort 206 patients were included and GTR was achieved in 121 (58.7%, 32 (15.5%) missing), BR in 46 (22.3%, 145 (70.4%) missing) and IMP in 42 (20.4%, 7 (3.4%) missing) cases. The AUC at external validation amounted to 0.72 (95% CI: 0.63-0.80) for GTR, 0.69 (0.52-0.83) for BR, as well as 0.82 (0.76-0.89) for IMP. Discussion and conclusion: All models showed adequate generalizability, performing similarly in training and external validation, confirming the possible potentials of machine learning in helping to adapt surgical therapy to the individual patient.
ABSTRACT
OBJECTIVE: Newly diagnosed patients with a familial cavernous malformation (FCM) and their families are concerned about their future outlook, which is scarcely discussed in the literature. The authors studied a prospective contemporary cohort of patients with FCMs to assess demographics, mode of presentation, prospective risk of hemorrhage and seizures, need for surgery, and functional outcome over an extended interval. METHODS: A prospectively maintained database beginning January 1, 2015, of patients diagnosed with a cavernous malformation (CM) was queried. Data on demographics, radiological imaging, and symptoms at first diagnosis were collected in adult patients who gave their consent to prospective contact. Follow-up was done using questionnaires, in-person visits, and medical record review to assess for prospective symptomatic hemorrhage (i.e., the first hemorrhage after enrollment in the database), seizure, functional outcome measured by the modified Rankin Scale (mRS), and treatment. The prospective hemorrhage rate was calculated by the number of prospective hemorrhages divided by patient-years of follow-up censored at last follow-up, first prospective hemorrhage, or death. A Kaplan-Meier curve of survival free of hemorrhage was obtained comparing patients with versus without hemorrhage at the time of presentation and compared with a log-rank test for p < 0.05. RESULTS: A total of 75 patients with FCM were included, of whom 60% were female. The mean age at diagnosis was 41 ± 16 years. Most symptomatic or large lesions were located supratentorially. At first diagnosis, 27 patients had no symptoms, and the remaining were symptomatic. Over an average of 9.9 years, the rate of prospective hemorrhage was 4.0% per patient-year, and the rate of new seizure was 1.2% per patient-year, with 64% and 32% of patients experiencing at least one symptomatic hemorrhage and at least one seizure, respectively. Thirty-eight percent of the patients underwent at least 1 surgery and 5.3% underwent stereotactic radiosurgery. At the last follow-up, 83.0% of patients remained independent with an mRS score ≤ 2. CONCLUSIONS: The authors' findings provide clinically useful information on hemorrhage rate, seizure rate, the likelihood of surgery, and functional outcome. These findings can be helpful to practicing physicians when counseling patients with FCM and their families, who are often apprehensive about their future and well-being.
