The Application of Artificial Intelligence and Machine Learning in Pituitary Adenomas

Integration of big data analytics in the investigation of the relationship between acromegaly and cancer

OBJECTIVE

To evaluate the association between acromegaly and cancer and different types of cancer by using natural language processing systems and big data analytics.

MATERIAL AND METHODS

We conducted an observational, retrospective study utilizing data from the electronic health records (EHRs) of Hospital Universitario Puerta de Hierro Majadahonda, Madrid, Spain. Information from the EHRs was extracted using artificial intelligence techniques and analyzed using Savana Manager 4.0 software.

RESULTS

Out of a total of 708,047 registered patients (54.7% females), 544 patients (0.08%; 330 women, 60.7%; mean age at diagnosis 53.0±15.8 yr) were diagnosed with acromegaly. The incidence of cancer was higher in patients with acromegaly vs those without this condition (7.7% vs 3.9%, p<0.001; OR, 2.047, 95%CI, 1.493-2.804). Male acromegalic patients had a higher prevalence of cancer vs females (57.1% vs 42.9%, p=0.012). A significantly higher prevalence of colorectal cancer (2.9% vs 1.4%, p=0.006), bladder cancer (1.1% vs 0.3%, p=0.005), and lymphoma (1.1% vs 0.3%, p=0.009) was observed in patients with acromegaly vs those without the condition. Acromegalic men had significantly higher prevalence rates of colorectal cancer (4.7% vs 1.3%, p=0.001), bladder cancer (2.8% vs 0.4%, p<0.001), breast cancer (0.9% vs 0.2%, p=0.042), gastric cancer (0.9% vs 0.1%, p=0.011), lymphoma (1.4% vs 0.3%, p=0.037), and liver cancer (0.9% vs 0.1%, p=0.012) vs non-acromegalic men. On the other hand, acromegalic women showed a higher prevalence of thyroid cancer (1.2% vs 0.4%, p=0.043) vs non-acromegalic women.

CONCLUSION

Our study, based on artificial intelligence techniques and analysis of real-world data and information, revealed a significant association between acromegaly and cancer in our hospital population, mainly acromegalic men, with a higher frequency of colorectal cancer, bladder cancer and lymphoma in particular.

An objective way to predict remission and relapse in Cushing disease using Bayes' theorem of probability

OBJECTIVE

In this study on patients with Cushing disease, post-transsphenoidal surgery (TSS), we attempt to predict the probability of remaining in remission, at least for a year and relapse after that, using Bayes' theorem and the equation of conditional probability. The number of parameters, as well as the weightage of each, is incorporated in this equation.

DESIGN AND METHODS

The study design was a single-centre ambispective study. Ten clinical, biochemical, radiological and histopathological parameters capable of predicting Cushing disease remission were identified. The presence or absence of each parameter was entered as binary numbers. Bayes' theorem was applied, and each patient's probability of remission and relapse was calculated.

RESULTS

A total of 145 patients were included in the study. ROC plot showed a cut-off value of the probability of 0.68, with a sensitivity of 82% (range 73-89%) and a specificity of 94% (range 83-99%) to predict the probability of remission. Eighty-one patients who were in remission at 1 year were followed up for relapse and 23 patients developed relapse of the disease. The Bayes' equation was able to predict relapse in only 3 out of 23 patients.

CONCLUSIONS

Using various parameters, remission of Cushing disease can be predicted by applying Bayes' theorem of conditional probability with a sensitivity and a specificity of 82% and 94%, respectively. This study provided an objective way of predicting remission after TSS and relapse in patients with Cushing disease giving a weightage advantage to every parameter.

Role of artificial intelligence in brain tumour imaging

Artificial intelligence (AI) is a rapidly evolving field with many neuro-oncology applications. In this review, we discuss how AI can assist in brain tumour imaging, focusing on machine learning (ML) and deep learning (DL) techniques. We describe how AI can help in lesion detection, differential diagnosis, anatomic segmentation, molecular marker identification, prognostication, and pseudo-progression evaluation. We also cover AI applications in non-glioma brain tumours, such as brain metastasis, posterior fossa, and pituitary tumours. We highlight the challenges and limitations of AI implementation in radiology, such as data quality, standardization, and integration. Based on the findings in the aforementioned areas, we conclude that AI can potentially improve the diagnosis and treatment of brain tumours and provide a path towards personalized medicine and better patient outcomes.

Predictors of biochemical response to somatostatin receptor ligands in acromegaly

Although predictors of response to first-generation somatostatin receptor ligands (fg-SRLs), and to a lesser extent to pasireotide, have been studied in acromegaly for many years, their use is still not recommended in clinical guidelines. Is there insufficient evidence to use them? Numerous biomarkers including various clinical, functional, radiological and molecular markers have been identified. The first ones are applicable pre-surgery, while the molecular predictors are utilized for patients not cured after surgery. In this regard, factors predicting a good response to fg-SRLs are specifically: low basal GH, a low GH nadir in the acute octreotide test, T2 MRI hypointensity, a densely granulated pattern, high immunohistochemistry staining for somatostatin receptor 2 (SSTR2), and E-cadherin. However, there is still a lack of consensus regarding which of these biomarkers is more useful or how to integrate them into clinical practice. With classical statistical methods, it is complex to define reliable and generalizable cut-off values for a single biomarker. The potential solution to the limitations of traditional methods involves combining systems biology with artificial intelligence, which is currently providing answers to such long-standing questions that may eventually be finally included into the clinical guidelines and make personalized medicine a reality. The aim of this review is to describe the current knowledge of the main fg-SRLs and pasireotide response predictors, discuss their current usefulness, and point to future directions in the research of this field.

Establishment of a risk prediction model for olfactory disorders in patients with transnasal pituitary tumors by machine learning

To construct a prediction model of olfactory dysfunction after transnasal sellar pituitary tumor resection based on machine learning algorithms. A cross-sectional study was conducted. From January to December 2022, 158 patients underwent transnasal sellar pituitary tumor resection in three tertiary hospitals in Sichuan Province were selected as the research objects. The olfactory status was evaluated one week after surgery. They were randomly divided into a training set and a test set according to the ratio of 8:2. The training set was used to construct the prediction model, and the test set was used to evaluate the effect of the model. Based on different machine learning algorithms, BP neural network, logistic regression, decision tree, support vector machine, random forest, LightGBM, XGBoost, and AdaBoost were established to construct olfactory dysfunction risk prediction models. The accuracy, precision, recall, F1 score, and area under the ROC curve (AUC) were used to evaluate the model's prediction performance, the optimal prediction model algorithm was selected, and the model was verified in the test set of patients. Of the 158 patients, 116 (73.42%) had postoperative olfactory dysfunction. After missing value processing and feature screening, an essential order of influencing factors of olfactory dysfunction was obtained. Among them, the duration of operation, gender, type of pituitary tumor, pituitary tumor apoplexy, nasal adhesion, age, cerebrospinal fluid leakage, blood scar formation, and smoking history became the risk factors of olfactory dysfunction, which were the key indicators of the construction of the model. Among them, the random forest model had the highest AUC of 0.846, and the accuracy, precision, recall, and F1 score were 0.750, 0.870, 0.947, and 0.833, respectively. Compared with the BP neural network, logistic regression, decision tree, support vector machine, LightGBM, XGBoost, and AdaBoost, the random forest model has more advantages in predicting olfactory dysfunction in patients after transnasal sellar pituitary tumor resection, which is helpful for early identification and intervention of high-risk clinical population, and has good clinical application prospects.

Integrated analysis of m6A regulator-mediated RNA methylation modification patterns and immune characteristics in Sjögren's syndrome

The epigenetic modifier N6-methyladenosine (m6A), recognized as the most prevalent internal modification in messenger RNA (mRNA), has recently emerged as a pivotal player in immune regulation. Its dysregulation has been implicated in the pathogenesis of various autoimmune conditions. However, the implications of m6A modification within the immune microenvironment of Sjögren's syndrome (SS), a chronic autoimmune disorder characterized by exocrine gland dysfunction, remain unexplored. Herein, we leverage an integrative analysis combining public database resources and novel sequencing data to investigate the expression profiles of m6A regulatory genes in SS. Our cohort comprised 220 patients diagnosed with SS and 62 healthy individuals, enabling a comprehensive evaluation of peripheral blood at the transcriptomic level. We report a significant association between SS and altered expression of key m6A regulators, with these changes closely tied to the activation of CD4+ T cells. Employing a random forest (RF) algorithm, we identified crucial genes contributing to the disease phenotype, which facilitated the development of a robust diagnostic model via multivariate logistic regression analysis. Further, unsupervised clustering revealed two distinct m6A modification patterns, which were significantly associated with variations in immunocyte infiltration, immune response activity, and biological function enrichment in SS. Subsequently, we proceeded with a screening process aimed at identifying genes that were differentially expressed (DEGs) between the two groups distinguished by m6A modification. Leveraging these DEGs, we employed weight gene co-expression network analysis (WGCNA) to uncover sets of genes that exhibited strong co-variance and hub genes that were closely linked to m6A modification. Through rigorous analysis, we identified three critical m6A regulators - METTL3, ALKBH5, and YTHDF1 - alongside two m6A-related hub genes, COMMD8 and SRP9. These elements collectively underscore a complex but discernible pattern of m6A modification that appears to be integrally linked with SS's pathogenesis. Our findings not only illuminate the significant correlation between m6A modification and the immune microenvironment in SS but also lay the groundwork for a deeper understanding of m6A regulatory mechanisms. More importantly, the identification of these key regulators and hub genes opens new avenues for the diagnosis and treatment of SS, presenting potential targets for therapeutic intervention.

Process analysis of the patient pathway for automated data collection: an exemplar using pituitary surgery

Introduction

Automation of routine clinical data shows promise in relieving health systems of the burden associated with manual data collection. Identifying consistent points of documentation in the electronic health record (EHR) provides salient targets to improve data entry quality. Using our pituitary surgery service as an exemplar, we aimed to demonstrate how process mapping can be used to identify reliable areas of documentation in the patient pathway to target structured data entry interventions.

Materials and methods

This mixed methods study was conducted in the largest pituitary centre in the UK. Purposive snowball sampling identified frontline stakeholders for process mapping to produce a patient pathway. The final patient pathway was subsequently validated against a real-world dataset of 50 patients who underwent surgery for pituitary adenoma. Events were categorized by frequency and mapped to the patient pathway to determine critical data points.

Results

Eighteen stakeholders encompassing all members of the multidisciplinary team (MDT) were consulted for process mapping. The commonest events recorded were neurosurgical ward round entries (N = 212, 14.7%), pituitary clinical nurse specialist (CNS) ward round entries (N = 88, 6.12%) and pituitary MDT treatment decisions (N = 88, 6.12%) representing critical data points. Operation notes and neurosurgical ward round entries were present for every patient. 43/44 (97.7%) had a pre-operative pituitary MDT entry, pre-operative clinic letter, a post-operative clinic letter, an admission clerking entry, a discharge summary, and a post-operative histopathology pituitary multidisciplinary (MDT) team entries.

Conclusion

This is the first study to produce a validated patient pathway of patients undergoing pituitary surgery, serving as a comparison to optimise this patient pathway. We have identified salient targets for structured data entry interventions, including mandatory datapoints seen in every admission and have also identified areas to improve documentation adherence, both of which support movement towards automation.

Predictors of Response to Treatment with First-Generation Somatostatin Receptor Ligands in Patients with Acromegaly

BACKGROUND AND AIMS

Predictors of first-generation somatostatin receptor ligands (fgSRLs) response in acromegaly have been studied for over 30 years, but they are still not recommended in clinical guidelines. Is there not enough evidence to support their use? This systematic review aims to describe the current knowledge of the main predictors of fgSRLs response and discuss their current usefulness, as well as future research directions.

METHODS

A systematic search was performed in the Scopus and PubMed databases for functional, imaging, and molecular predictive factors.

RESULTS

A total of 282 articles were detected, of which 64 were included. Most of them are retrospective studies performed between 1990 and 2023 focused on the predictive response to fgSRLs in acromegaly. The usefulness of the predictive factors is confirmed, with good response identified by the most replicated factors, specifically low GH nadir in the acute octreotide test, T2 MRI hypointensity, high Somatostatin receptor 2 (SSTR2) and E-cadherin expression, and a densely granulated pattern. Even if these biomarkers are interrelated, the association is quite heterogeneous. With classical statistical methods, it is complex to define reliable and generalizable cut-off values worth recommending in clinical guidelines. Machine-learning models involving omics are a promising approach to achieve the highest accuracy values to date.

CONCLUSIONS

This survey confirms a sufficiently robust level of evidence to apply knowledge of predictive factors for greater efficiency in the treatment decision process. The irruption of artificial intelligence in this field is providing definitive answers to such long-standing questions that may change clinical guidelines and make personalized medicine a reality.

Prognostic Models in Growth-Hormone- and Prolactin-Secreting Pituitary Neuroendocrine Tumors: A Systematic Review

Growth-hormone (GH)- and prolactin (PRL)-secreting PitNETs (pituitary neuroendocrine tumors) are divided into multiple histological subtypes, which determine their clinical and biological variable behavior. Proliferation markers alone have a questionable degree of prediction, so we try to identify validated prognostic models as accurately as possible. (1) Background: The data available so far show that the use of staging and clinical-pathological classification of PitNETs, along with imaging, are useful in predicting the evolution of these tumors. So far, there is no consensus for certain markers that could predict tumor evolution. The application of the WHO (World Health Organisation) classification in practice needs to be further evaluated and validated. (2) Methods: We performed the CRD42023401959 protocol in Prospero with a systematic literature search in PubMed and Web of Science databases and included original full-text articles (randomized control trials and clinical trials) from the last 10 years, published in English, and the search used the following keywords: (i) pituitary adenoma AND (prognosis OR outcome OR prediction), (ii) growth hormone pituitary adenoma AND (prognosis OR outcome OR prediction), (iii) prolactin pituitary adenoma AND (prognosis OR outcome OR prediction); (iv) mammosomatotroph adenoma AND (prognosis OR outcome OR prediction). (3) Results: Two researchers extracted the articles of interest and if any disagreements occurred in the selection process, these were settled by a third reviewer. The articles were then assessed using the ROBIS bias assessment and 75 articles were included. (4) Conclusions: the clinical-pathological classification along with factors such as GH, IGF-1, prolactin levels both preoperatively and postoperatively offer valuable information.

Fully automated imaging protocol independent system for pituitary adenoma segmentation: a convolutional neural network-based model on sparsely annotated MRI

This study aims to develop a fully automated imaging protocol independent system for pituitary adenoma segmentation from magnetic resonance imaging (MRI) scans that can work without user interaction and evaluate its accuracy and utility for clinical applications. We trained two independent artificial neural networks on MRI scans of 394 patients. The scans were acquired according to various imaging protocols over the course of 11 years on 1.5T and 3T MRI systems. The segmentation model assigned a class label to each input pixel (pituitary adenoma, internal carotid artery, normal pituitary gland, background). The slice segmentation model classified slices as clinically relevant (structures of interest in slice) or irrelevant (anterior or posterior to sella turcica). We used MRI data of another 99 patients to evaluate the performance of the model during training. We validated the model on a prospective cohort of 28 patients, Dice coefficients of 0.910, 0.719, and 0.240 for tumour, internal carotid artery, and normal gland labels, respectively, were achieved. The slice selection model achieved 82.5% accuracy, 88.7% sensitivity, 76.7% specificity, and an AUC of 0.904. A human expert rated 71.4% of the segmentation results as accurate, 21.4% as slightly inaccurate, and 7.1% as coarsely inaccurate. Our model achieved good results comparable with recent works of other authors on the largest dataset to date and generalized well for various imaging protocols. We discussed future clinical applications, and their considerations. Models and frameworks for clinical use have yet to be developed and evaluated.

Radiomics and machine learning for predicting the consistency of benign tumors of the central nervous system: A systematic review

PURPOSE

Predicting the consistency of benign central nervous system (CNS) tumors prior to surgery helps to improve surgical outcomes. This review summarizes and analyzes the literature on using radiomics and/or machine learning (ML) for consistency prediction.

METHOD

The Medical Literature Analysis and Retrieval System Online (MEDLINE) database was screened for studies published in English from January 1st 2000. Data was extracted according to the PRISMA guidelines and quality of the studies was assessed in compliance with the Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2).

RESULTS

Eight publications were included focusing on pituitary macroadenomas (n = 5), pituitary adenomas (n = 1), and meningiomas (n = 2) using a retrospective (n = 6), prospective (n = 1), and unknown (n = 1) study design with a total of 763 patients for the consistency prediction. The studies reported an area under the curve (AUC) of 0.71-0.99 for their respective best performing model regarding the consistency prediction. Of all studies, four articles validated their models internally whereas none validated their models externally. Two articles stated making data available on request with the remaining publications lacking information with regard to data availability.

CONCLUSIONS

The research on consistency prediction of CNS tumors is still at an early stage regarding the use of radiomics and different ML techniques. Best-practice procedures regarding radiomics and ML need to be followed more rigorously to facilitate the comparison between publications and, accordingly, the possible implementation into clinical practice in the future.

The use of augmented reality in transsphenoidal surgery: A systematic review

BACKGROUND

Augmented reality (AR) has become a promising tool in neurosurgery. It can minimise the anatomical challenges faced by conventional endoscopic or microscopic transsphenoidal reoperations and can assist in intraoperative guidance, preoperative planning, and surgical training.

OBJECTIVES

The aims of this systematic review are to describe, compare, and evaluate the use of AR in endoscopic and microscopic transsphenoidal surgery, incorporating the latest primary research.

METHODS

A systematic review was performed to explore and evaluate existing primary evidence for using AR in transsphenoidal surgery. A comprehensive search of MEDLINE and EMBASE was conducted from database inception to 11th August 2021 for primary data on the use of AR in microscopic and endoscopic endonasal skull base surgery. Additional articles were identified through searches on PubMed, Google Scholar, JSTOR, SCOPUS, Web of Science, Engineering Village, IEEE transactions, and HDAS. A synthesis without meta-analysis (SWiM) analysis was employed quantitatively and qualitatively on the impact of AR on landmark identification, intraoperative navigation, accuracy, time, surgeon experience, and patient outcomes.

RESULTS

In this systematic review, 17 studies were included in the final analysis. The main findings were that AR provides a convincing improvement to landmark identification, intraoperative navigation, and surgeon experience in transsphenoidal surgery, with a further positive effect on accuracy and time. It did not demonstrate a convincing positive effect on patient outcomes. No studies reported comparative mortalities, morbidities, or cost-benefit indications.

CONCLUSION

AR-guided transsphenoidal surgery, both endoscopic and microscopic, is associated with an overall improvement in the areas of intraoperative guidance and surgeon experience as compared with their conventional counterparts. However, literature on this area, particularly comparative data and evidence, is very limited. More studies with similar methodologies and quantitative outcomes are required to perform appropriate meta-analyses and to draw significant conclusions.

Identification of DTL as Related Biomarker and Immune Infiltration Characteristics of Nasopharyngeal Carcinoma via Comprehensive Strategies

Purpose

Although considerable progress has been made in basic and clinical research on nasopharyngeal carcinoma (NPC), the biomarkers of the progression of NPC have not been fully studied and described. This study was designed to identify potential novel biomarkers for NPC using integrated analyses and explore the immune cell infiltration in this pathological process.

Methods

Five GEO data sets were downloaded from gene expression omnibus database (GEO) and analysed to identify differentially expressed genes (DEGs), followed by Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analyses. The four algorithms were adopted for screening of novel and key biomarkers for NPC, including random forest (RF) machine learning algorithm, least absolute shrinkage and selection operator (LASSO) logistic regression, support vector machine-recursive feature elimination (SVM-RFE), and weighted gene co-expression network analysis (WGCNA). Lastly, CIBERSORT was used to assess the infiltration of immune cells in NPC, and the correlation between diagnostic markers and infiltrating immune cells was analyzed.

Results

Herein, we identified 46 DEGs, and enrichment analysis results showed that DEGs and several kinds of signaling pathways might be closely associated with the occurrence and progression of NPC. DTL was recognized as NPC-related biomarker. DTL, also known as retinoic acid-regulated nuclear matrix-associated protein (RAMP), or DNA replication factor 2 (CDT2), is reported to be correlated with the cell proliferation, cell cycle arrest and cell invasion in hepatocellular carcinoma, breast cancer and gastric cancer. Immune infiltration analysis demonstrated that macrophages M0, macrophages M1 and T cells CD4 memory activated were linked to pathogenesis of NPC.

Conclusion

In summary, we adopted a comprehensive strategy to screen DTL as biomarkers related to NPC and explore the critical role of immune cell infiltration in NPC.