Integrative Machine Learning Approach for Predicting Resistance to First-generation Receptor Ligands in Acromegaly
Wei Lin1,2, Songchang Shi3, Yuanyuan Zheng1,4
1Division of Endocrinology, Diabetes and Hypertension, Brigham and Women's Hospital, Harvard Medical School, Boston, MA 02115, USA.
Context:
Acromegaly, caused by excess GH and IGF-1 due to pituitary adenomas, often necessitates first-generation somatostatin receptor ligands (fgSRLs) therapy when surgery fails. However, responses to fgSRLs therapy vary widely.
Objective:
To develop a machine learning (ML)-based calculator that predicts individual responses to fgSRLs therapy, enabling evidence-based acromegaly management.
Design:
A retrospective study (January 2010-July 2024) utilizing the Research Patient Data Registry to evaluate 10 ML algorithms and create a predictive calculator.
Setting:
Single-center study conducted at Mass General Brigham-affiliated hospitals.
Patients:
One hundred eleven acromegaly patients met inclusion criteria, classified as fgSRLs-responsive (n = 64) or fgSRLs-resistant (n = 47).
Interventions:
IGF-1 trajectories were analyzed using linear mixed-effects modeling. Ten ML algorithms were assessed to predict fgSRLs resistance. SHapley Additive exPlanations (SHAP) analysis identified key predictors for the development of a web-based clinical calculator.
Main Outcome Measures:
Model performance was primarily evaluated using area under the receiver operating characteristic curve (AUROC), along with accuracy, precision, recall, specificity, F1 score, and decision curve analysis (DCA).
Results:
The CatBoost model exhibited optimal performance based on AUROC 0.896 (95% confidence interval: 0.751-0.990), with accuracy 82.4%, precision 86.7%, specificity 88.2%, and F1 score 81.2%. Key predictors of fgSRLs resistance identified via SHAP analysis included pre-fgSRLs treatment GH, Knosp grade, pre-fgSRLs treatment IGF-1 index, T2-weighted magnetic resonance imaging density, and comorbidity burden. The model demonstrated excellent calibration (Brier score 0.131) and clinical utility via DCA. A web-based calculator was developed for clinical use.
Conclusion:
The CatBoost-based calculator effectively predicts fgSRLs treatment response in acromegaly patients. Prospective validation is required before clinical implementation.
Insights
This study developed a machine learning calculator to predict treatment response in acromegaly patients, aiding personalized therapy. The tool accurately identifies individuals likely to benefit from first-generation somatostatin receptor ligands (fgSRLs).
Area of Science:
- Endocrinology
- Machine Learning in Medicine
- Computational Biology
Background:
- Acromegaly, driven by excess growth hormone (GH) and insulin-like growth factor-1 (IGF-1), often requires first-generation somatostatin receptor ligands (fgSRLs) therapy post-surgery.
- Patient responses to fgSRLs therapy exhibit significant variability, necessitating personalized treatment strategies.
Purpose of the Study:
- To create a machine learning (ML)-based calculator for predicting individual patient responses to fgSRLs therapy.
- To support evidence-based management of acromegaly by enabling prediction of treatment efficacy.
Main Methods:
- A retrospective analysis of 111 acromegaly patients treated between January 2010 and July 2024 at Mass General Brigham-affiliated hospitals.
- Evaluation of ten ML algorithms to predict fgSRLs resistance, with the CatBoost model selected for optimal performance (AUROC 0.896).
- Identification of key predictors of resistance, including pre-treatment GH, Knosp grade, IGF-1 index, MRI density, and comorbidity burden, using SHAP analysis.
Main Results:
- The CatBoost model achieved high predictive accuracy (82.4%) and specificity (88.2%) in identifying fgSRLs resistance.
- Key predictors for treatment resistance were identified, including pre-treatment GH and IGF-1 levels, Knosp grade, MRI characteristics, and overall comorbidity burden.
- A web-based clinical calculator was developed, demonstrating excellent calibration and clinical utility.
Conclusions:
- The developed CatBoost-based calculator demonstrates effectiveness in predicting fgSRLs treatment response in acromegaly.
- Further prospective validation is recommended prior to widespread clinical implementation of the predictive tool.
More Related Videos
10:51Reverse Yeast Two-hybrid System to Identify Mammalian Nuclear Receptor Residues that Interact with Ligands and/or Antagonists
Published on: November 15, 2013
08:04Identification and Classification of Position-specific GABAA Receptor Subunit Missense Variants for Their Role In Hippocampal Pyramidal Neurons
Published on: June 6, 2025
Related Concept Videos
01:29The Two-State Receptor Model
The binding affinity of a drug determines its interaction with...
01:29Drug-Receptor Interactions
Several parameters, such as the drug's affinity for its receptor and its efficacy, which is its ability to activate the receptor, determine the drug's effect on the tissue....
01:25Drug-Receptor Interaction: Agonist
Agonists can bind to receptors in different ways. Some agonists bind directly to the receptor's active site, mimicking the endogenous...
02:40Ligand Binding Sites
Protein-ligand interactions are quite specific; even though numerous potential ligands surround a cellular protein at any given time, only a particular ligand can bind to that protein. Moreover, a ligand binds only to a dedicated area on the surface of the protein, known as the...