Development and assessment of machine learning algorithms for predicting remission after transsphenoidal surgery among patients with acromegaly

SPIN-PM: a consensus framework to evaluate the presence of spin in studies on prediction models

OBJECTIVES

To develop a framework to identify and evaluate spin practices and its facilitators in studies on clinical prediction model regardless of the modeling technique.

STUDY DESIGN AND SETTING

We followed a three-phase consensus process: (1) premeeting literature review to generate items to be included; (2) a series of structured meetings to provide comments discussed and exchanged viewpoints on items to be included with a panel of experienced researchers; and (3) postmeeting review on final list of items and examples to be included. Through this iterative consensus process, a framework was derived after all panel's researchers agreed.

RESULTS

This consensus process involved a panel of eight researchers and resulted in SPIN-Prediction Models which consists of two categories of spin (misleading interpretation and misleading transportability), and within these categories, two forms of spin (spin practices and facilitators of spin). We provide criteria and examples.

CONCLUSION

We proposed this guidance aiming to facilitate not only the accurate reporting but also an accurate interpretation and extrapolation of clinical prediction models which will likely improve the reporting quality of subsequent research, as well as reduce research waste.

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.

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.

Predictors of improvement in quality of life at 12-month follow-up in patients undergoing anterior endoscopic skull base surgery

Background

Patients with pituitary lesions experience decrements in quality of life (QoL) and treatment aims to arrest or improve QoL decline.

Objective

To detect associations with QoL in trans-nasal endoscopic skull base surgery patients and train supervised learning classifiers to predict QoL improvement at 12 months.

Methods

A supervised learning analysis of a prospective multi-institutional dataset (451 patients) was conducted. QoL was measured using the anterior skull base surgery questionnaire (ASBS). Factors associated with QoL at baseline and at 12-month follow-up were identified using multivariate logistic regression. Multiple supervised learning models were trained to predict postoperative QoL improvement with five-fold cross-validation.

Results

ASBS at 12-month follow-up was significantly higher (132.19,SD = 24.87) than preoperative ASBS (121.87,SD = 25.72,p<0.05). High preoperative scores were significantly associated with institution, diabetes and lesions at the planum sphenoidale / tuberculum sella site. Patients with diabetes were five times less likely to report high preoperative QoL. Low preoperative QoL was significantly associated with female gender, a vision-related presentation, diabetes, secreting adenoma and the cavernous sinus site. Top quartile change in postoperative QoL at 12-month follow-up was negatively associated with baseline hypercholesterolemia, acromegaly and intraoperative CSF leak. Positive associations were detected for lesions at the sphenoid sinus site and deficient preoperative endocrine function. AdaBoost, logistic regression and neural network classifiers yielded the strongest predictive performance.

Conclusion

It was possible to predict postoperative positive change in QoL at 12-month follow-up using perioperative data. Further development and implementation of these models may facilitate improvements in informed consent, treatment decision-making and patient QoL.

Prediction of Gestational Diabetes Mellitus under Cascade and Ensemble Learning Algorithm

Gestational diabetes mellitus (GDM) is one of the risk factors for fetal dysplasia and maternal pregnancy difficulties. Therefore, the prediction of the risk of GDM in advance has become a big demand for millions of families. Therefore, machine learning technology is adopted to study GDM prediction. Firstly, the data is preprocessed, and the mean value is used for outlier processing. After preprocessing of the data, the IV value method is used to screen the features. Of the 83 features in the original sample data, 40 important features are screened out through feature engineering. On this basis, Logistics regression model, Lasso-Logistics, Gradient Boosting Decision Tree (GBDT), Extreme Gradient Boosting (Xgboost), Light Gradient Boosting Machine (Lightgbm), and Gradient Boosting Categorical Features (Catboost) are established, and multiple learners are integrated. Finally, the constructed model is tested on data sets. The accuracy of the proposed model is 80.3%, the accuracy is 74.6%, the recall rate is 79.3%, and the running time is only 2.53 seconds. This means that the proposed model is superior to the previous models in terms of accuracy, precision, recall rate, and F1 value, and the time consumption is also in line with the actual engineering requirements. The proposed scheme provides some ideas for the research of machine learning technology in disease prediction.

Review on Facial-Recognition-Based Applications in Disease Diagnosis

Diseases not only manifest as internal structural and functional abnormalities, but also have facial characteristics and appearance deformities. Specific facial phenotypes are potential diagnostic markers, especially for endocrine and metabolic syndromes, genetic disorders, facial neuromuscular diseases, etc. The technology of facial recognition (FR) has been developed for more than a half century, but research in automated identification applied in clinical medicine has exploded only in the last decade. Artificial-intelligence-based FR has been found to have superior performance in diagnosis of diseases. This interdisciplinary field is promising for the optimization of the screening and diagnosis process and assisting in clinical evaluation and decision-making. However, only a few instances have been translated to practical use, and there is need of an overview for integration and future perspectives. This review mainly focuses on the leading edge of technology and applications in varieties of disease, and discusses implications for further exploration.

Machine learning as a clinical decision support tool for patients with acromegaly

OBJECTIVE

To develop machine learning (ML) models that predict postoperative remission, remission at last visit, and resistance to somatostatin receptor ligands (SRL) in patients with acromegaly and to determine the clinical features associated with the prognosis.

METHODS

We studied outcomes using the area under the receiver operating characteristics (AUROC) values, which were reported as the performance metric. To determine the importance of each feature and easy interpretation, Shapley Additive explanations (SHAP) values, which help explain the outputs of ML models, are used.

RESULTS

One-hundred fifty-two patients with acromegaly were included in the final analysis. The mean AUROC values resulting from 100 independent replications were 0.728 for postoperative 3 months remission status classification, 0.879 for remission at last visit classification, and 0.753 for SRL resistance status classification. Extreme gradient boosting model demonstrated that preoperative growth hormone (GH) level, age at operation, and preoperative tumor size were the most important predictors for early remission; resistance to SRL and preoperative tumor size represented the most important predictors of remission at last visit, and postoperative 3-month insulin-like growth factor 1 (IGF1) and GH levels (random and nadir) together with the sparsely granulated somatotroph adenoma subtype served as the most important predictors of SRL resistance.

CONCLUSIONS

ML models may serve as valuable tools in the prediction of remission and SRL resistance.

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.

Surgery for acromegaly: Indications and goals

Acromegaly is a disease that occurs secondary to high levels of GH, most often from a hormone-secreting pituitary adenoma, with multisystem adverse effects. Diagnosis includes serum GH and IGF-1 levels, and obtaining an MRI pituitary protocol to assess for a functional pituitary adenoma. Attempted gross total resection of the GH-secreting adenoma is the gold standard in treatment for patients with acromegaly for a goal of biochemical remission. Medical and radiation therapies are available when patients do not achieve biochemical cure after surgical therapy.

First but not second postoperative day growth hormone assessments as early predictive tests for long-term acromegaly persistence

PURPOSE

Postoperative assessment of acromegaly activity is typically performed at least 3 months after neurosurgery (NS). Few studies have evaluated the use of early postoperative growth hormone (GH) levels as a test to predict short- and long-term remission of acromegaly. Our objective was to evaluate the diagnostic performance of serum random GH on a postoperative day one (D1-rGH) and two (D2-rGH), particularly in predicting long-term disease persistence.

MATERIALS AND METHODS

Forty-one subjects with acromegaly who were undergoing NS were enrolled (mean age ± SD 47.4 ± 13.1 years at diagnosis; women 54%; macroadenomas 71%). The final assessment of disease activity was performed one year after NS. ROC curves were used to evaluate the diagnostic performance of D1-rGH and D2-rGH.

RESULTS

After a 1-year follow-up, the overall remission rate was 55%. ROC analysis identified an optimal D1-rGH cut-off value of 2.1 ng/mL for diagnosing long-term disease persistence (55.6% SE; 90.9% SP). The cut-off point became 2.5 ng/mL after maximizing specificity for disease persistence (yielding a 100% positive predictive value) and 0.3 ng/mL after maximizing sensitivity for disease remission. The optimal D2-rGH cut-off value was 0.6 ng/mL (81.8% SE; 50% SP); the cut-off point became 2.9 ng/mL after maximizing specificity and 0.1 ng/mL after maximizing sensitivity, with no clinical utility.

CONCLUSIONS

D1-rGH could be a highly specific test for the early diagnosis of long-term acromegaly persistence, which is predicted by a value > 2.5 ng/mL with a great degree of certainty. The diagnostic performance of D2-rGH was insufficient. Further research is required to validate these preliminary results prior to modifying the postoperative management of acromegaly.

Development and assessment of machine learning models for predicting recurrence risk after endovascular treatment in patients with intracranial aneurysms

Intracranial aneurysms (IAs) remain a major public health concern and endovascular treatment (EVT) has become a major tool for managing IAs. However, the recurrence rate of IAs after EVT is relatively high, which may lead to the risk for aneurysm re-rupture and re-bleed. Thus, we aimed to develop and assess prediction models based on machine learning (ML) algorithms to predict recurrence risk among patients with IAs after EVT in 6 months. Patient population included patients with IAs after EVT between January 2016 and August 2019 in Hunan Provincial People's Hospital, and an adaptive synthetic (ADASYN) sampling approach was applied for the entire imbalanced dataset. We developed five ML models and assessed the models. In addition, we used SHapley Additive exPlanations (SHAP) and local interpretable model-agnostic explanation (LIME) algorithms to determine the importance of the selected features and interpret the ML models. A total of 425 IAs were enrolled into this study, and 66 (15.5%) of which recurred in 6 months. Among the five ML models, gradient boosting decision tree (GBDT) model performed best. The area under curve (AUC) of the GBDT model on the testing set was 0.842 (sensitivity: 81.2%; specificity: 70.4%). Our study firstly demonstrated that ML-based models can serve as a reliable tool for predicting recurrence risk in patients with IAs after EVT in 6 months, and the GBDT model showed the optimal prediction performance.

Prospect of Artificial Intelligence Based on Electronic Medical Record

With the advent of the big data era, the interest of the international community is focusing on increasing the utilization of medical big data. Many hospitals are attempting to increase the efficiency of their operations and patient management by adopting artificial intelligence (AI) technology that enables the use of electronic medical record (EMR) data. EMR includes information about a patient's health history, such as diagnoses, medicines, tests, allergies, immunizations, treatment plans, personalized medical care, and improvement of medical quality and safety. EMR data can also be used for AI-based new drug development. In particular, it is effective to develop AI that can predict the occurrence of specific diseases or provide individualized customized treatments by classifying the individualized characteristics of patients. In order to improve performance of artificial intelligence research using EMR data, standardization and refinement of data are essential. In addition, since EMR data deal with sensitive personal information of patients, it is also vital to protect the patient's privacy. There are already various supports for the use of EMR data in the Korean government, and researchers are encouraged to be proactive.

Applications of Machine Learning in Bone and Mineral Research

In this unprecedented era of the overwhelming volume of medical data, machine learning can be a promising tool that may shed light on an individualized approach and a better understanding of the disease in the field of osteoporosis research, similar to that in other research fields. This review aimed to provide an overview of the latest studies using machine learning to address issues, mainly focusing on osteoporosis and fractures. Machine learning models for diagnosing and classifying osteoporosis and detecting fractures from images have shown promising performance. Fracture risk prediction is another promising field of research, and studies are being conducted using various data sources. However, these approaches may be biased due to the nature of the techniques or the quality of the data. Therefore, more studies based on the proposed guidelines are needed to improve the technical feasibility and generalizability of artificial intelligence algorithms.

LightGBM: an efficient and accurate method for predicting pregnancy diseases

As machine learning is becoming the fashion in disease prediction while no prediction model has performed very efficiently and accurately on predicting pregnancy diseases up to now, it's necessary to compare several common machine learning methods' performance on pregnancy diseases prediction and select out the best one. The data of two common pregnancy complications, pregnancy-induced hypertension (PIH) and Intrahepatic cholestasis of pregnancy (ICP), based on various maternal characteristics measured in patients' routine blood examination in 10-19 weeks of gestation are considered to be suitable to be learned. This is a retrospective study of 320 healthy pregnancies in 10-19 weeks, with 149 patients who subsequently developed PIH and 250 patients who subsequently developed ICP. Nine machine learning methods were used to predict PIH and ICP and their performance was compared via 8 evaluation indexes. Finally, the light Gradient Boosting Machine (lightGBM) is considered to be the best method to predict gestational diseases.Impact statementWhat is already known on this subject? As a kind of commonly used method in disease prediction, machine learning could be applied to clinical data for developing robust risk models and many achievements have been made. Also, machine learning can be used to predict pregnancy diseases. Although some machine learning methods have been used for screening gestational diseases, methods based on simple theories, such as logistic regression and decision tree, are frequently used. They don't always have a very satisfactory prediction results. Besides, only a few types of pregnancy diseases can be predicted.What do the results of this study add? LightGBM has the best prediction results of PIH and ICP among 9 machine learning methods in this study. It can predict PIH (AUC = 81.72%) with a sensitivity of 70.59%, and ICP (AUC = 95.91%) with a sensitivity of 97.91%.What are the implications of these findings for clinical practice and/or further research? A new model has been developed for effective first-trimester screening for two common pregnancy diseases, PIH and ICP. This lightGBM model can be used in relative hospitals and population of the research, and provide references for doctors' diagnosis and treatment of pregnant women. In further research, the predicted effect of lightGBM on daily practice and other pregnancy diseases such as pregnancy diabetes, will be verified.

Machine Learning-based Prediction Model for Treatment of Acromegaly With First-generation Somatostatin Receptor Ligands

CONTEXT

Artificial intelligence (AI), in particular machine learning (ML), may be used to deeply analyze biomarkers of response to first-generation somatostatin receptor ligands (fg-SRLs) in the treatment of acromegaly.

OBJECTIVE

To develop a prediction model of therapeutic response of acromegaly to fg-SRL.

METHODS

Patients with acromegaly not cured by primary surgical treatment and who had adjuvant therapy with fg-SRL for at least 6 months after surgery were included. Patients were considered controlled if they presented growth hormone (GH) <1.0 ng/mL and normal age-adjusted insulin-like growth factor (IGF)-I levels. Six AI models were evaluated: logistic regression, k-nearest neighbor classifier, support vector machine, gradient-boosted classifier, random forest, and multilayer perceptron. The features included in the analysis were age at diagnosis, sex, GH, and IGF-I levels at diagnosis and at pretreatment, somatostatin receptor subtype 2 and 5 (SST2 and SST5) protein expression and cytokeratin granulation pattern (GP).

RESULTS

A total of 153 patients were analyzed. Controlled patients were older (P = .002), had lower GH at diagnosis (P = .01), had lower pretreatment GH and IGF-I (P < .001), and more frequently harbored tumors that were densely granulated (P = .014) or highly expressed SST2 (P < .001). The model that performed best was the support vector machine with the features SST2, SST5, GP, sex, age, and pretreatment GH and IGF-I levels. It had an accuracy of 86.3%, positive predictive value of 83.3% and negative predictive value of 87.5%.

CONCLUSION

We developed a ML-based prediction model with high accuracy that has the potential to improve medical management of acromegaly, optimize biochemical control, decrease long-term morbidities and mortality, and reduce health services costs.

Machine learning in predicting early remission in patients after surgical treatment of acromegaly: a multicenter study

PURPOSE

Accurate prediction of postoperative remission is beneficial for effective patient-physician communication in acromegalic patients. This study aims to train and validate machine learning prediction models for early endocrine remission of acromegalic patients.

METHODS

The training cohort included 833 patients with growth hormone (GH) secreting pituitary adenoma from 2010 to 2018. We trained a partial model (only using pre-operative variables) and a full model (using all variables) to predict off-medication endocrine remission at six-month follow-up after surgery using multiple algorithms. The models were validated in 99 prospectively collected patients from a second campus and 52 patients from a third institution.

RESULTS

C-statistic and the accuracy of the best partial model was 0.803 (95% CI 0.757-0.849) and 72.5% (95% CI 67.6-77.5%), respectively. C-statistic and the accuracy of the best full model was 0.888 (95% CI 0.861-0.914) and 80.3% (95% CI 77.5-83.1%), respectively. The c-statistics (and accuracy) of using only Knosp grade, total resection, or postoperative day 1 GH level as the single predictor were lower than our partial model or full model (p < 0.001). C-statistics remained similar in the prospective cohort (partial model 0.798, and full model 0.903) and in the external cohort (partial model 0.771, and full model 0.871). A web-based application integrated with the trained models was published at  https://deepvep.shinyapps.io/Acropred/ .

CONCLUSION

We developed and validated interpretable and applicable machine learning models to predict early endocrine remission after surgical resection of a GH-secreting pituitary adenoma. Predication accuracy of the trained models were better than those using single variables.

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

BACKGROUND

There are no established accurate models that use machine learning (ML) methods to preoperatively predict immediate remission after transsphenoidal surgery (TSS) in patients diagnosed with histology-positive Cushing's disease (CD).

PURPOSE

Our current study aims to devise and assess an ML-based model to preoperatively predict immediate remission after TSS in patients with CD.

METHODS

A total of 1,045 participants with CD who received TSS at Peking Union Medical College Hospital in a 20-year period (between February 2000 and September 2019) were enrolled in the present study. In total nine ML classifiers were applied to construct models for the preoperative prediction of immediate remission with preoperative factors. The area under the receiver operating characteristic (ROC) curve (AUC) was used to evaluate the performance of the models. The performance of each ML-based model was evaluated in terms of AUC.

RESULTS

The overall immediate remission rate was 73.3% (766/1045). First operation (p<0.001), cavernous sinus invasion on preoperative MRI(p<0.001), tumour size (p<0.001), preoperative ACTH (p=0.008), and disease duration (p=0.010) were significantly related to immediate remission on logistic univariate analysis. The AUCs of the models ranged between 0.664 and 0.743. The highest AUC, i.e., the best performance, was 0.743, which was achieved by stacking ensemble method with four factors: first operation, cavernous sinus invasion on preoperative MRI, tumour size and preoperative ACTH.

CONCLUSION

We developed a readily available ML-based model for the preoperative prediction of immediate remission in patients with CD.

Development of Machine Learning Models for Predicting Postoperative Delayed Remission in Patients With Cushing's Disease

CONTEXT

Postoperative hypercortisolemia mandates further therapy in patients with Cushing's disease (CD). Delayed remission (DR) is defined as not achieving postoperative immediate remission (IR), but having spontaneous remission during long-term follow-up.

OBJECTIVE

We aimed to develop and validate machine learning (ML) models for predicting DR in non-IR patients with CD.

METHODS

We enrolled 201 CD patients, and randomly divided them into training and test datasets. We then used the recursive feature elimination (RFE) algorithm to select features and applied 5 ML algorithms to construct DR prediction models. We used permutation importance and local interpretable model-agnostic explanation (LIME) algorithms to determine the importance of the selected features and interpret the ML models.

RESULTS

Eighty-eight (43.8%) of the 201 CD patients met the criteria for DR. Overall, patients who were younger, had a low body mass index, a Knosp grade of III-IV, and a tumor not found by pathological examination tended to achieve a lower rate of DR. After RFE feature selection, the Adaboost model, which comprised 18 features, had the greatest discriminatory ability, and its predictive ability was significantly better than using Knosp grading and postoperative immediate morning serum cortisol (PoC). The results obtained from permutation importance and LIME algorithms showed that preoperative 24-hour urine free cortisol, PoC, and age were the most important features, and showed the reliability and clinical practicability of the Adaboost model in DC prediction.

CONCLUSIONS

Machine learning-based models could serve as an effective noninvasive approach to predicting DR, and could aid in determining individual treatment and follow-up strategies for CD patients.

Predictors of Immediate Remission after Surgery in Cushing's Disease Patients: A Large Retrospective Study from a Single Center

OBJECTIVE

Transsphenoidal surgery (TSS) is the first-line treatment of patients with Cushing's disease (CD). However, biochemical remission rates after TSS for CD vary from 59 to 95%, and the predictors of surgical outcomes remain unclear. The aim of this study was to identify the predictors of early outcomes in patients with CD treated with TSS.

METHODS

The clinical features and outcomes of CD patients who underwent TSS between February 2000 and September 2019 at the Peking Union Medical College Hospital were collected from medical records and analyzed. Uni- and multivariate odds ratio (OR) analyses were performed to identify the predictors of early outcomes in patients with CD.

RESULTS

A total of 1,045 patients were included. The median age at TSS was 34.0 years (IQR 26.0-45.0), with a female:male ratio of 4.2:1 (844/201). The median duration of symptoms was 46.0 months (IQR 24.0-72.0). After surgery, the overall postoperative immediate remission rate was 73.3%, and 26.7% of patients had persistent hypercortisolism. Univariate analysis demonstrated that the number of operations was correlated with a lower immediate remission rate (OR 0.393, 95% CI 0.266-0.580, p = 0.000), as was tumor size (OR 0.462, 95% CI 0.334-0.639, p = 0.000), the duration of disease (OR 0.996, 95% CI 0.993-0.999, p = 0.003), and preoperative ACTH concentration (0.998, 95% CI 0.996-0.999, p = 0.003). Cavernous sinus invasion has also been identified as an important factor associated with a lower immediate remission rate (OR 0.275, 95% CI 0.166-0.456, p = 0.000). No correlations were detected between the immediate outcomes and age, gender, BMI, the combination of a low- and high-dose dexamethasone suppression test, preoperative morning serum cortisol level, or 24-h urinary free cortisol level (all p > 0.05). The results of multivariate analysis were similar to those of univariate analysis. Preoperative ACTH ≤67.35 ng/L predicted remission with 60.9% sensitivity and 49.5% specificity (AUC 0.553; p = 0.008). A cutoff of ≤64.5 months for disease duration predicted immediate remission with 40.5% sensitivity and 71.0% specificity (AUC 0.552; p = 0.01).

CONCLUSION

Early outcomes of TSS in CD patients can be predicted by factors including the number of operations, duration of disease, tumor invasion, tumor size, and preoperative ACTH concentration. These predictors can be used to improve the perioperative management of CD patients.

The definition of remission and recurrence of Cushing's disease

Accurate classification of postsurgical remission, and early recognition of recurrence are crucial to timely treat and prevent excess mortality in Cushing's Disease, yet the criteria used to define remission are variable and there is no consensus to define recurrence. Remission is defined as postsurgical hypocortisolemia, but delayed remission may occur. Recurrence is the return of clinical manifestations with biochemical evidence of hypercortisolism. The proper combination of tests and their timing are controversial. Reliable predicting tools may lead to earlier diagnosis upon recurrence. Many factors have been studied independently for prediction with variable performance. Novel artificial intelligence approaches seek to integrate these variables into risk calculators and machine-learning algorithms with an acceptable short-term predictive performance but lack longer-term accuracy. Prospective studies using these approaches are needed. This review summarizes the evidence behind the definitions of remission and recurrence and provide an overview of the available tools to predict and/or diagnose them.

Artificial intelligence for brain diseases: A systematic review

Artificial intelligence (AI) is a major branch of computer science that is fruitfully used for analyzing complex medical data and extracting meaningful relationships in datasets, for several clinical aims. Specifically, in the brain care domain, several innovative approaches have achieved remarkable results and open new perspectives in terms of diagnosis, planning, and outcome prediction. In this work, we present an overview of different artificial intelligent techniques used in the brain care domain, along with a review of important clinical applications. A systematic and careful literature search in major databases such as Pubmed, Scopus, and Web of Science was carried out using "artificial intelligence" and "brain" as main keywords. Further references were integrated by cross-referencing from key articles. 155 studies out of 2696 were identified, which actually made use of AI algorithms for different purposes (diagnosis, surgical treatment, intra-operative assistance, and postoperative assessment). Artificial neural networks have risen to prominent positions among the most widely used analytical tools. Classic machine learning approaches such as support vector machine and random forest are still widely used. Task-specific algorithms are designed for solving specific problems. Brain images are one of the most used data types. AI has the possibility to improve clinicians' decision-making ability in neuroscience applications. However, major issues still need to be addressed for a better practical use of AI in the brain. To this aim, it is important to both gather comprehensive data and build explainable AI algorithms.

Machine Learning Applications in Endocrinology and Metabolism Research: An Overview

Machine learning (ML) applications have received extensive attention in endocrinology research during the last decade. This review summarizes the basic concepts of ML and certain research topics in endocrinology and metabolism where ML principles have been actively deployed. Relevant studies are discussed to provide an overview of the methodology, main findings, and limitations of ML, with the goal of stimulating insights into future research directions. Clear, testable study hypotheses stem from unmet clinical needs, and the management of data quality (beyond a focus on quantity alone), open collaboration between clinical experts and ML engineers, the development of interpretable high-performance ML models beyond the black-box nature of some algorithms, and a creative environment are the core prerequisites for the foreseeable changes expected to be brought about by ML and artificial intelligence in the field of endocrinology and metabolism, with actual improvements in clinical practice beyond hype. Of note, endocrinologists will continue to play a central role in these developments as domain experts who can properly generate, refine, analyze, and interpret data with a combination of clinical expertise and scientific rigor.

Development and Interpretation of Multiple Machine Learning Models for Predicting Postoperative Delayed Remission of Acromegaly Patients During Long-Term Follow-Up

Background: Some patients with acromegaly do not reach the remission standard in the short term after surgery but achieve remission without additional postoperative treatment during long-term follow-up; this phenomenon is defined as postoperative delayed remission (DR). DR may complicate the interpretation of surgical outcomes in patients with acromegaly and interfere with decision-making regarding postoperative adjuvant therapy. Objective: We aimed to develop and validate machine learning (ML) models for predicting DR in acromegaly patients who have not achieved remission within 6 months of surgery. Methods: We enrolled 306 acromegaly patients and randomly divided them into training and test datasets. We used the recursive feature elimination (RFE) algorithm to select features and applied six ML algorithms to construct DR prediction models. The performance of these ML models was validated using receiver operating characteristics analysis. We used permutation importance, SHapley Additive exPlanations (SHAP), and local interpretable model-agnostic explanation (LIME) algorithms to determine the importance of the selected features and interpret the ML models. Results: Fifty-five (17.97%) acromegaly patients met the criteria for DR, and five features (post-1w rGH, post-1w nGH, post-6m rGH, post-6m IGF-1, and post-6m nGH) were significantly associated with DR in both the training and the test datasets. After the RFE feature selection, the XGboost model, which comprised the 15 important features, had the greatest discriminatory ability (area under the curve = 0.8349, sensitivity = 0.8889, Youden's index = 0.6842). The XGboost model showed good discrimination ability and provided significantly better estimates of DR of patients with acromegaly compared with using only the Knosp grade. The results obtained from permutation importance, SHAP, and LIME algorithms showed that post-6m IGF-1 is the most important feature in XGboost algorithm prediction and showed the reliability and the clinical practicability of the XGboost model in DR prediction. Conclusions: ML-based models can serve as an effective non-invasive approach to predicting DR and could aid in determining individual treatment and follow-up strategies for acromegaly patients who have not achieved remission within 6 months of surgery.

Risk Assessment of Sarcopenia in Patients With Type 2 Diabetes Mellitus Using Data Mining Methods

Purpose: Sarcopenia is a geriatric syndrome, and it is closely related to the prevalence of type 2 diabetes mellitus (T2DM). Until now, the diagnosis of sarcopenia requires Dual Energy X-ray Absorptiometry (DXA) scanning. This study aims to make risk assessment of sarcopenia with support vector machine (SVM) and random forest (RF) when DXA is not available. Methods: Firstly, we recruited 132 patients aged over 65 and diagnosed with T2DM in Changchun, China. Clinical data were collected for predicting sarcopenia. Secondly, we selected 3, 5, and 7 features out of over 40 features of patient's data with backward selection, respectively, to train SVM and RF classification models and regression models. Finally, to evaluate the performance of the models, we performed leave one out and 5-fold cross validation. Results: When training the model with 5 features, the sensitivity, specificity, negative predictive value (NPV) and positive predictive value (PPV) were favorable, and it was better than the models trained with 3 features and 7 features. Area under the receiver operating characteristic (ROC) curve (AUC) were over 0.7, and the mean AUC of SVM models was higher than that of RF. Conclusions: Using SVM and RF to make risk assessment of sarcopenia in the elderly is an option in clinical setting. Only 5 features are needed to input into the software to run the algorithm for a primary assessment. It cannot replace DXA to diagnose sarcopenia, but is a good tool to evaluate sarcopenia.