Machine Learning in Preoperative Prediction of Postoperative Immediate Remission of Histology-Positive Cushing's Disease

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.

Predicting delayed remission in Cushing's disease using radiomics models: a multi-center study

Purpose

No multi-center radiomics models have been built to predict delayed remission (DR) after transsphenoidal surgery (TSS) in Cushing's disease (CD). The present study aims to build clinical and radiomics models based on data from three centers to predict DR after TSS in CD.

Methods

A total of 122 CD patients from Peking Union Medical College Hospital, Xuanwu Hospital, and Fuzhou General Hospital were enrolled between January 2000 and January 2019. The T1-weighted gadolinium-enhanced MRI images and clinical data were used as inputs to build clinical and radiomics models. The regions of interest (ROI) of MRI images were automatically defined by a deep learning algorithm developed by our team. The area under the curve (AUC) of receiver operating characteristic (ROC) curves was used to evaluate the performance of the models. In total, 10 machine learning algorithms were used to construct models.

Results

The overall DR rate is 44.3% (54/122). According to multivariate Logistic regression analysis, patients with higher BMI and lower postoperative cortisol levels are more likely to achieve a higher rate of delayed remission. Among the 10 models, XGBoost achieved the best performance among all models in both clinical and radiomics models with AUC values of 0.767 and 0.819 respectively. The results from SHAP value and LIME algorithms revealed that postoperative cortisol level (PoC) and BMI were the most important features associated with DR.

Conclusion

Radiomics models can be built as an effective noninvasive method to predict DR and might be useful in assisting neurosurgeons in making therapeutic plans after TSS for CD patients. These results are preliminary and further validation in a larger patient sample is needed.

The State of Machine Learning in Outcomes Prediction of Transsphenoidal Surgery: A Systematic Review

The purpose of this analysis is to assess the use of machine learning (ML) algorithms in the prediction of postoperative outcomes, including complications, recurrence, and death in transsphenoidal surgery. Following Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, we systematically reviewed all papers that used at least one ML algorithm to predict outcomes after transsphenoidal surgery. We searched Scopus, PubMed, and Web of Science databases for studies published prior to May 12, 2021. We identified 13 studies enrolling 5,048 patients. We extracted the general characteristics of each study; the sensitivity, specificity, area under the curve (AUC) of the ML models developed as well as the features identified as important by the ML models. We identified 12 studies with 5,048 patients that included ML algorithms for adenomas, three with 1807 patients specifically for acromegaly, and five with 2105 patients specifically for Cushing's disease. Nearly all were single-institution studies. The studies used a heterogeneous mix of ML algorithms and features to build predictive models. All papers reported an AUC greater than 0.7, which indicates clinical utility. ML algorithms have the potential to predict postoperative outcomes of transsphenoidal surgery and can improve patient care. Ensemble algorithms and neural networks were often top performers when compared with other ML algorithms. Biochemical and preoperative features were most likely to be selected as important by ML models. Inexplicability remains a challenge, but algorithms such as local interpretable model-agnostic explanation or Shapley value can increase explainability of ML algorithms. Our analysis shows that ML algorithms have the potential to greatly assist surgeons in clinical decision making.

An Integrated Clinical Score to Predict Remission in Cushing's Disease

Objective

To derive a clinical score from parameters that favor remission of Cushing's disease (CD) after pituitary surgery.

Methods

This is an analysis of 11 clinical, hormonal, and post-operative parameters that each favored remission in a cohort of 145 patients with CD treated by trans-sphenoidal surgery (TSS). Each parameter was designated as a categorical variable (presence/absence), and several favorable parameters present for each patient were calculated. From this, a median parameter score (clinical score) of the entire cohort was derived, which was then compared to the event of remission/persistence of CD.

Results

The median number of favorable parameters present in the entire cohort was 3 (0-7). The significant count of patients in remission increased with the increasing number of parameters. The receiver-operator characteristic curve showed that the presence of ≥3 parameters was associated with remission in CD with a sensitivity of 84.2% and a specificity of 80%. Patients with a clinical score ≥3 had significantly higher remission rates (88.9%) than those who had persistent disease (27.3%; P = 0.001).

Conclusion

A clinical score of ≥3 predicts remission in CD treated by TSS; however, it requires validation in other large cohorts. Rather than assessing individual parameters to predict remission in CD, an integrated clinical score is a better tool for follow-up and patient counseling.

Recurrent Cushing's Disease in Adults: Predictors and Long-Term Follow-Up

Cushing's disease (CD) is characterized by endogenous hypercortisolism that is associated with increased mortality and morbidity. Due to high recurrence rates in CD, the determination of high-risk patients is of paramount importance. In this study, we aimed to determine recurrence rates and clinical, laboratory, and histological predictors of recurrence in a high volume single-center. This retrospective study included 273 CD patients operated in a single pituitary center between 1997 and 2020. The patients with early postoperative remission were further grouped according to recurrence status (recurrent and sustained remission groups). Demographic, radiologic, laboratory, pathologic, and follow-up clinical data of the patients were analyzed and compared between groups. The recurrence rate was 9.6% in the first 5 years; however, the overall recurrence rate was 14.2% in this study. Higher preoperative basal ACTH levels were significantly correlated with CD recurrence even with ACTH levels adjusted for tumor size, Ki-67 levels, and tumoral invasion. Recurrence rates were significantly higher in patients with ACTH levels higher than 55 pg/ml, tumor diameter>9.5 mm, and if adrenal axis recovery was before 6 months. The severity of hypercortisolism, morbidities, and demographic factors except age were not predictive factors of recurrence. Based on our study data, younger age at diagnosis, a diagnosis of osteoporosis, higher preoperative ACTH levels, larger tumor size, invasive behavior, higher Ki 67 index, and early recovery of the adrenal axis during the postoperative period attracted attention as potential predictors of recurrent disease.

Emerging diagnostic methods and imaging modalities in cushing's syndrome

Endogenous Cushing's syndrome (CS) is a rare disease characterized by prolonged glucocorticoid excess. Timely diagnosis is critical to allow prompt treatment and limit long-term disease morbidity and risk for mortality. Traditional biochemical diagnostic modalities each have limitations and sensitivities and specificities that vary significantly with diagnostic cutoff values. Biochemical evaluation is particularly complex in patients whose hypercortisolemia fluctuates daily, often requiring repetition of tests to confirm or exclude disease, and when delineating CS from physiologic, nonneoplastic states of hypercortisolism. Lastly, traditional pituitary MRI may be negative in up to 60% of patients with adrenocorticotropic hormone (ACTH)-secreting pituitary adenomas (termed "Cushing's disease" [CD]) whereas false positive pituitary MRI findings may exist in patients with ectopic ACTH secretion. Thus, differentiating CD from ectopic ACTH secretion may necessitate dynamic testing or even invasive procedures such as bilateral inferior petrosal sinus sampling. Newer methods may relieve some of the diagnostic uncertainty in CS, providing a more definitive diagnosis prior to subjecting patients to additional imaging or invasive procedures. For example, a novel method of cortisol measurement in patients with CS is scalp hair analysis, a non-invasive method yielding cortisol and cortisone values representing long-term glucocorticoid exposure of the past months. Hair cortisol and cortisone have both shown to differentiate between CS patients and controls with a high sensitivity and specificity. Moreover, advances in imaging techniques may enhance detection of ACTH-secreting pituitary adenomas. While conventional pituitary MRI may fail to identify microadenomas in patients with CD, high-resolution 3T-MRI with 3D-spoiled gradient-echo sequence has thinner sections and superior soft-tissue contrast that can detect adenomas as small as 2 mm. Similarly, functional imaging may improve the identification of ACTH-secreting adenomas noninvasively; Gallium-68-tagged corticotropin-releasing hormone (CRH) combined with PET-CT can be used to detect CRH receptors, which are upregulated on corticotroph adenomas. This technique can delineate functionality of adenomas in patients with CD from patients with ectopic ACTH secretion and false positive pituitary lesions on MRI. Here, we review emerging methods and imaging modalities for the diagnosis of CS, discussing their diagnostic accuracy, strengths and limitations, and applicability to clinical practice.

Machine learning models for differential diagnosis of Cushing's disease and ectopic ACTH secretion syndrome

BACKGROUND

Using machine learning (ML) to explore the noninvasive differential diagnosis of Cushing's disease (CD) and ectopic corticotropin (ACTH) secretion (EAS) model is the next hot research topic. This study was to develop and evaluate ML models for differentially diagnosing CD and EAS in ACTH-dependent Cushing's syndrome (CS).

METHODS

Two hundred sixty-four CD and forty-seven EAS were randomly divided into training and validation and test datasets. We applied 8 ML algorithms to select the most suitable model. The diagnostic performance of the optimal model and bilateral petrosal sinus sampling (BIPSS) were compared in the same cohort.

RESULTS

Eleven adopted variables included age, gender, BMI, duration of disease, morning cortisol, serum ACTH, 24-h UFC, serum potassium, HDDST, LDDST, and MRI. After model selection, the Random Forest (RF) model had the most extraordinary diagnostic performance, with a ROC AUC of 0.976 ± 0.03, a sensitivity of 98.9% ± 4.4%, and a specificity of 87.9% ± 3.0%. The serum potassium, MRI, and serum ACTH were the top three most important features in the RF model. In the validation dataset, the RF model had an AUC of 0.932, a sensitivity of 95.0%, and a specificity of 71.4%. In the complete dataset, the ROC AUC of the RF model was 0.984 (95% CI 0.950-0.993), which was significantly higher than HDDST and LDDST (both p < 0.001). There was no significant statistical difference in the comparison of ROC AUC between the RF model and BIPSS (baseline ROC AUC 0.988 95% CI 0.983-1.000, after stimulation ROC AUC 0.992 95% CI 0.983-1.000). This diagnostic model was shared as an open-access website.

CONCLUSIONS

A machine learning-based model could be a practical noninvasive approach to distinguishing CD and EAS. The diagnostic performance might be close to BIPSS.

Machine Learning Models to Forecast Outcomes of Pituitary Surgery: A Systematic Review in Quality of Reporting and Current Evidence

Background: The complex nature and heterogeneity involving pituitary surgery results have increased interest in machine learning (ML) applications for prediction of outcomes over the last decade. This study aims to systematically review the characteristics of ML models involving pituitary surgery outcome prediction and assess their reporting quality. Methods: We searched the PubMed, Scopus, and Web of Knowledge databases for publications on the use of ML to predict pituitary surgery outcomes. We used the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) to assess report quality. Our search strategy was based on the terms “artificial intelligence”, “machine learning”, and “pituitary”. Results: 20 studies were included in this review. The principal models reported in each article were post-surgical endocrine outcomes (n = 10), tumor management (n = 3), and intra- and postoperative complications (n = 7). Overall, the included studies adhered to a median of 65% (IQR = 60–72%) of TRIPOD criteria, ranging from 43% to 83%. The median reported AUC was 0.84 (IQR = 0.80–0.91). The most popular algorithms were support vector machine (n = 5) and random forest (n = 5). Only two studies reported external validation and adherence to any reporting guideline. Calibration methods were not reported in 15 studies. No model achieved the phase of actual clinical applicability. Conclusion: Applications of ML in the prediction of pituitary outcomes are still nascent, as evidenced by the lack of any model validated for clinical practice. Although studies have demonstrated promising results, greater transparency in model development and reporting is needed to enable their use in clinical practice. Further adherence to reporting guidelines can help increase AI’s real-world utility and improve clinical practice.

The Application of Artificial Intelligence and Machine Learning in Pituitary Adenomas

Pituitary adenomas (PAs) are a group of tumors with complex and heterogeneous clinical manifestations. Early accurate diagnosis, individualized management, and precise prediction of the treatment response and prognosis of patients with PA are urgently needed. Artificial intelligence (AI) and machine learning (ML) have garnered increasing attention to quantitatively analyze complex medical data to improve individualized care for patients with PAs. Therefore, we critically examined the current use of AI and ML in the management of patients with PAs, and we propose improvements for future uses of AI and ML in patients with PAs. AI and ML can automatically extract many quantitative features based on massive medical data; moreover, related diagnosis and prediction models can be developed through quantitative analysis. Previous studies have suggested that AI and ML have wide applications in early accurate diagnosis; individualized treatment; predicting the response to treatments, including surgery, medications, and radiotherapy; and predicting the outcomes of patients with PAs. In addition, facial imaging-based AI and ML, pathological picture-based AI and ML, and surgical microscopic video-based AI and ML have also been reported to be useful in assisting the management of patients with PAs. In conclusion, the current use of AI and ML models has the potential to assist doctors and patients in making crucial surgical decisions by providing an accurate diagnosis, response to treatment, and prognosis of PAs. These AI and ML models can improve the quality and safety of medical services for patients with PAs and reduce the complication rates of neurosurgery. Further work is needed to obtain more reliable algorithms with high accuracy, sensitivity, and specificity for the management of PA patients.

Electronic Medical Records as Input to Predict Postoperative Immediate Remission of Cushing's Disease: Application of Word Embedding

Background

No existing machine learning (ML)-based models use free text from electronic medical records (EMR) as input to predict immediate remission (IR) of Cushing’s disease (CD) after transsphenoidal surgery.

Purpose

The aim of the present study is to develop an ML-based model that uses EMR that include both structured features and free text as input to preoperatively predict IR after transsphenoidal surgery.

Methods

A total of 419 patients with CD from Peking Union Medical College Hospital were enrolled between January 2014 and August 2020. The EMR of the patients were embedded and transformed into low-dimensional dense vectors that can be included in four ML-based models together with structured features. The area under the curve (AUC) of receiver operating characteristic curves was used to evaluate the performance of the models.

Results

The overall remission rate of the 419 patients was 75.7%. From the results of logistic multivariate analysis, operation (p < 0.001), invasion of cavernous sinus from MRI (p = 0.046), and ACTH (p = 0.024) were strongly correlated with IR. The AUC values for the four ML-based models ranged from 0.686 to 0.793. The highest AUC value (0.793) was for logistic regression when 11 structured features and “individual conclusions of the case by doctor” were included.

Conclusion

An ML-based model was developed using both structured and unstructured features (after being processed using a word embedding method) as input to preoperatively predict postoperative IR.