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

Immunological signatures and predictive biomarkers for first-generation somatostatin receptor ligand resistance in Acromegaly

PURPOSE

Predicting resistance to first-generation Somatostatin Receptor Ligands (fg-SRL) in Acromegaly patients remains an ongong challenge. Tumor-associated immune components participate in various pathological processes, including drug-resistance. We aimed to identify the immune components involved in resistance of fg-SRL, and to investigate biomarkers that can be targeted to treat those drug-resistant Acromegaly.

METHODS

We conducted a retrospective study involving 35 Acromegaly patients with somatotropinomas treated postoperatively with fg-SRL. Gathering clinicopathological data, SSTR2 expression, and immunological profiles, we utilized univariate, binary logistic regression, and ROC analyses to assess their predictive roles in fg-SRL resistance. Spearman correlation analysis further examined interactions among interested characteristics.

RESULTS

19 patients (54.29%) exhibited resistance to postoperative fg-SRL. GH level at diagnosis, preoperative tumor volume, T2WI-MRI intensity, granularity, PD-L1, SSTR2, and CD8 + T cell infiltration showed association with clinical outcomes of fg-SRL. Notably, T2WI-MRI hyperintensity, PD-L1-IRS > 7, CD8 + T cell infiltration < 14.8/HPF, and SSTR2-IRS < 5.4 emerged as reliable predictors for fg-SRL resistance. Correlation analysis highlighted a negative relationship between PD-L1 expression and CD8 + T cell infiltration, while showcasing a positive correlation with preoperative tumor volume of somatotropinomas. Additionally, 5 patients with fg-SRL resistance underwent re-operation were involved. Following fg-SRL treatment, significant increases in PD-L1 and SSTR5 expression were observed, while SSTR2 expression decreased in somatotropinoma.

CONCLUSION

PD-L1 expression and CD8 + T cell infiltration, either independently or combined with SSTR2 expression and T2WI-MRI intensity, could form a predictive model guiding clinical decisions on fg-SRL employment. Furthermore, targeting PD-L1 through immunotherapy and embracing second-generations of SRL with higher affinity to SSTR5 represent promising strategies to tackle fg-SRL resistance in somatotropinomas.

The Multibiomarker Acro-TIME Score Predicts fg-SRLs Response: Preliminary Results of a Retrospective Acromegaly Cohort

CONTEXT

The prompt control of acromegaly is a primary treatment aim for reducing related disease morbidity and mortality. First-generation somatostatin receptor ligands (fg-SRLs) are the cornerstone of medical therapies. A non-negligible number of patients do not respond to this treatment. Several predictors of fg-SRL response were identified, but a comprehensive prognostic model is lacking.

OBJECTIVE

We aimed to design a prognostic model based on clinical and biochemical parameters, and pathological features, including data on immune tumor microenvironment.

METHODS

A retrospective, monocenter, cohort study was performed on 67 medically naïve patients with acromegaly. Fifteen clinical, pathological, and radiological features were collected and analyzed as independent risk factors of fg-SRLs response, using univariable and multivariable logistic regression analyses. A stepwise selection method was applied to identify the final regression model. A nomogram was then obtained.

RESULTS

Thirty-seven patients were fg-SRLs responders. An increased risk to poor response to fg-SRLs were observed in somatotropinomas with absent/cytoplasmatic SSTR2 expression (OR 5.493 95% CI 1.19-25.16, P = .028), with low CD68+/CD8+ ratio (OR 1.162, 95% CI 1.01-1.33, P = .032). Radical surgical resection was associated with a low risk of poor fg-SRLs response (OR 0.106, 95% CI 0.025-0.447 P = .002). The nomogram obtained from the stepwise regression model was based on the CD68+/CD8+ ratio, SSTR2 score, and the persistence of postsurgery residual tumor and was able to predict the response to fg-SRLs with good accuracy (area under the curve 0.85).

CONCLUSION

Although our predictive model should be validated in prospective studies, our data suggest that this nomogram may represent an easy to use tool for predicting the fg-SRL outcome early.

Predictive factors and the management of hyperglycemia in patients with acromegaly and Cushing's disease receiving pasireotide treatment: post hoc analyses from the SOM230B2219 study

Introduction

Pasireotide, a somatostatin receptor ligand, is approved for treating acromegaly and Cushing's disease (CD). Hyperglycemia during treatment can occur because of the drug's mechanism of action, although treatment discontinuation is rarely required. The prospective, randomized, Phase IV SOM230B2219 (NCT02060383) trial was designed to assess optimal management of pasireotide-associated hyperglycemia. Here, we investigated predictive factors for requiring antihyperglycemic medication during pasireotide treatment.

Methods

Participants with acromegaly or CD initiated long-acting pasireotide 40 mg/28 days intramuscularly (acromegaly) or pasireotide 600 μg subcutaneously twice daily during pre-randomization (≤16 weeks). Those who did not need antihyperglycemic medication, were managed with metformin, or received insulin from baseline entered an observational arm ending at 16 weeks. Those who required additional/alternative antihyperglycemic medication to metformin were randomized to incretin-based therapy or insulin for an additional 16 weeks. Logistic-regression analyses evaluated quantitative and qualitative factors for requiring antihyperglycemic medication during pre-randomization.

Results

Of 190 participants with acromegaly and 59 with CD, 88 and 15, respectively, did not need antihyperglycemic medication; most were aged <40 years (acromegaly 62.5%, CD 86.7%), with baseline glycated hemoglobin (HbA1c) <6.5% (<48 mmol/mol; acromegaly 98.9%, CD 100%) and fasting plasma glucose (FPG) <100 mg/dL (<5.6 mmol/L; acromegaly 76.1%, CD 100%). By logistic regression, increasing baseline HbA1c (odds ratio [OR] 3.6; P=0.0162) and FPG (OR 1.0; P=0.0472) and history of diabetes/pre-diabetes (OR 3.0; P=0.0221) predicted receipt of antihyperglycemic medication in acromegaly participants; increasing baseline HbA1c (OR 12.6; P=0.0276) was also predictive in CD participants. Investigator-reported hyperglycemia-related adverse events were recorded in 47.9% and 54.2% of acromegaly and CD participants, respectively, mainly those with diabetes/pre-diabetes.

Conclusion

Increasing age, HbA1c, and FPG and pre-diabetes/diabetes were associated with increased likelihood of requiring antihyperglycemic medication during pasireotide treatment. These risk factors may be used to identify those who need more vigilant monitoring to optimize outcomes during pasireotide treatment.

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.

Current role of pasireotide in the treatment of acromegaly

"First-generation" somatostatin receptor agonists (SSTRAs) octreotide and lanreotide are the most commonly used first-line pharmacological therapy for patients with acromegaly. A subset of patients respond only partially or not at all to the first-generation SSTRA, necessitating the use of additional pharmacological agents or other modes of therapy. Pasireotide is a "second-generation" SSTRA that has multi-receptor activity. Prospective studies have shown promise in the use of pasireotide in patients with poor response to first-generation SSTRA. Here we elucidate the molecular pathways of resistance to first-generation SSTRA, the mechanism of action, pre-clinical and clinical evidence of the use of pasireotide in patients having incomplete / lack of response to first-generation SSTRA. We also discuss the clinical, pathological, and radiological markers predicting response to pasireotide, and the difference in side-effect profiles of pasireotide, compared to first-generation SSTRA.

Biomarkers of response to treatment in acromegaly

INTRODUCTION

Medical treatment of acromegaly is based in a `trial and error` approach. First-generation somatostatin receptor ligands (fg-SRL) are prescribed as first-line medical therapy to the vast majority of patients, despite lack of disease control in approximately 60% of patients. However, other drugs used in acromegaly treatment are available (cabergoline, pasireotide and pegvisomant).

AREAS COVERED

In this article, we review and discuss the biomarkers of response to medical treatment in acromegaly.

EXPERT OPINION

Biomarkers for fg-SRL that can already be applied in clinical practice are: gender, age, pretreatment GH and IGF-I levels, cytokeratin granulation pattern, and the expression of somatostatin receptor type 2. Using biomarkers of response could guide treatment towards precision medicine with greater efficacy and lower costs.

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.

Long-term Efficacy and Safety of Pasireotide in Patients With Acromegaly: 14 Years of Single-Center Real-World Experience

CONTEXT

Acromegaly is a rare, chronic, debilitating disorder caused by prolonged hypersecretion of growth hormone (GH) and overproduction of insulin-like growth factor I (IGF-I). Medical therapies, including the somatostatin receptor ligand (SRL) pasireotide, are frequently used to restore biochemical control.

OBJECTIVE

As patients often receive therapy over prolonged periods, long-term data from real-life settings are needed.

METHODS

A retrospective analysis was performed using a prospectively maintained database of all patients with acromegaly from our primary care center who were enrolled in clinical studies with pasireotide (first visit November 2008). The main outcome measures were safety and biochemical control (age-adjusted IGF-I ≤ upper limit of normal).

RESULTS

Patients (n = 50) entered 4 parental studies and 30 continued in the rollover; at data cutoff (June 2022), 27 were still receiving pasireotide. Overall, median (range) exposure was 58 (3-137) months. Normal IGF-I was achieved in 54%, and acromegaly symptoms and quality of life were improved with treatment. No predictors of pasireotide response were identified; however, controlled patients had smaller tumors and lower GH at baseline. Tumor volume reduction occurred in 63% of evaluable patients (n = 10/16). Most patients presented hyperglycemic events, including 63.2% of patients with normal glucose before treatment. Older patients and those with higher IGF-I, glucose, and HbA1c at baseline had higher glucose and HbA1c during pasireotide treatment.

CONCLUSION

Pasireotide provided clinical benefit and was well tolerated for more than 11 years of treatment in acromegaly patients, most of whom were resistant to first-generation SRLs.

Revisiting the usefulness of the short acute octreotide test to predict treatment outcomes in acromegaly

Introduction

We previously described that a short version of the acute octreotide test (sAOT) can predict the response to first-generation somatostatin receptor ligands (SRLs) in patients with acromegaly. We have prospectively reassessed the sAOT in patients from the ACROFAST study using current ultra-sensitive GH assays. We also studied the correlation of sAOT with tumor expression of E-cadherin and somatostatin receptor 2 (SSTR2) .

Methods

A total of 47 patients treated with SRLs for 6 months were evaluated with the sAOT at diagnosis and correlated with SRLs' response. Those patients whose IGF1 decreased to <3SDS from normal value were considered responders and those whose IGF1 was ≥3SDS, were considered non-responders. The 2 hours GH value (GH2h) after s.c. administration of 100 mcg of octreotide was used to define predictive cutoffs. E-cadherin and SSTR2 immunostaining in somatotropinoma tissue were investigated in 24/47 and 18/47 patients, respectively.

Results

In all, 30 patients were responders and 17 were non-responders. GH2h was 0.68 (0.25-1.98) ng/mL in responders vs 2.35 (1.59-9.37) ng/mL in non-responders (p<0.001). GH2h = 1.4ng/mL showed the highest ability to identify responders (accuracy of 81%, sensitivity of 73.3%, and specificity of 94.1%). GH2h = 4.3ng/mL was the best cutoff for non-response prediction (accuracy of 74%, sensitivity of 35.3%, and specificity of 96.7%). Patients with E-cadherin-positive tumors showed a lower GH2h than those with E-cadherin-negative tumors [0.9 (0.3-2.1) vs 3.3 (1.5-12.1) ng/mL; p<0.01], and patients with positive E-cadherin presented a higher score of SSTR2 (7.5 ± 4.2 vs 3.3 ± 2.1; p=0.01).

Conclusion

The sAOT is a good predictor tool for assessing response to SRLs and correlates with tumor E-cadherin and SSTR2 expression. Thus, it can be useful in clinical practice for therapeutic decision-making in patients with acromegaly.

Magnetic resonance imaging as a predictor of therapeutic response to pasireotide in acromegaly

OBJECTIVE

Hyperintensity signal in T2-weighted magnetic resonance imaging (MRI) has been related to better therapeutic response during pasireotide treatment in acromegaly. The aim of the study was to evaluate T2 MRI signal intensity and its relation with pasireotide therapeutic effectiveness in real-life clinical practice.

DESIGN, PATIENTS AND MEASUREMENTS

Retrospective multicentre study including acromegaly patients treated with pasireotide. Adenoma T2-weighted MRI signal at diagnosis was qualitatively classified as iso-hyperintense or hypointense. Insulin-like growth factor (IGF-I), growth hormone (GH) and tumour volume reduction were assessed after 6 and 12 months of treatment and its effectiveness evaluated according to baseline MRI signal. Hormonal response was considered 'complete' when normalization of IGF-I levels was achieved. Significant tumour shrinkage was defined as a volume reduction of ≥25% from baseline.

RESULTS

Eighty-one patients were included (48% women, 50 ± 1.5 years); 93% had previously received somatostatin receptor ligands (SRLs) treatment. MRI signal was hypointense in 25 (31%) and hyperintense in 56 (69%) cases. At 12 months of follow-up, 42/73 cases (58%) showed normalization of IGF-I and 37% both GH and IGF-I. MRI signal intensity was not associated with hormonal control. 19/51 cases (37%) presented a significant tumour volume shrinkage, 16 (41%) from the hyperintense group and 3 (25%) from the hypointense.

CONCLUSIONS

T2-signal hyperintensity was more frequently observed in pasireotide treated patients. Almost 60% of SRLs resistant patients showed a complete normalization of IGF-I after 1 year of pasireotide treatment, regardless of the MRI signal. There was also no difference in the percentage tumour shrinkage over basal residual volume between the two groups.

miR-383-5p, miR-181a-5p, and miR-181b-5p as Predictors of Response to First-Generation Somatostatin Receptor Ligands in Acromegaly

Acromegaly is a chronic systemic disease caused in the vast majority of cases by growth hormone (GH)-secreting adenoma, with surgery being the first-line treatment. When a cure is not attained with surgery, first-generation somatostatin receptor ligands (fg-SRLs) are the most common medication prescribed. Predictors of response to fg-SRLs have been studied; however, they cannot fully predict the response to fg-SRL. MicroRNAs are small RNAs, the main role of which is messenger RNA (mRNA) post-transcriptional regulation. This study aimed to identify the microRNAs involved in resistance to treatment with fg-SRLs in acromegaly. Ten patients with acromegaly undergoing treatment with fg-SRLs were selected to undergo miRNA sequencing: five controlled and five uncontrolled with treatment. Bioinformatic analysis was performed to detect differentially expressed miRNAs. Then, the same 10 samples were used for validation by qPCR and an additional 22 samples were analyzed, totaling 32 samples. e We found 59 differentially expressed miRNAs in the first analysis. miR-181a-5p and miR-181b-5p were downregulated, and miR-383-5p was upregulated in the uncontrolled group. Receiver operating characteristic (ROC) curve analysis of miR-383-5p showed an NPV of 84.3% and a PPV of 84.5%. In summary, miR-181a-5p, miR-181b-5p, and miR-383-5p are biomarkers of response to fg-SRLs, and they can be used individually or included in prediction models as tools to guide clinical decisions.

Multidisciplinary management of difficult/aggressive growth-hormone pituitary neuro-endocrine tumors

Growth Hormone-secreting adenomas exhibits variable biological behavior and heterogeneous natural history, ranging from small adenomas and mild disease, to invasive and aggressive neoplasms with more severe clinical picture. Patients not cured or controlled after neurosurgical and first-generation somatostatin receptor ligands (SRL) therapy could require multiple surgical, medical and/or radiation treatments to achieve disease control. To date, no clinical, laboratory, histopathological, or neuroradiological markers are able to define the aggressiveness or predict the disease prognosis in patients with acromegaly. Therefore, the management of these patients requires careful evaluation of laboratory assessments, diagnostic criteria, neuroradiology examinations, and neurosurgical approaches to choose an effective and patient-tailored medical therapy. A multidisciplinary approach is particularly useful in difficult/aggressive acromegaly to schedule multimodal treatment, which includes radiation therapy, chemotherapy with temozolomide and other, recent emerging treatments. Herein, we describe the role of the different members of the multidisciplinary team according to our personal experience; a flow-chart for the therapeutic approach of difficult/aggressive acromegaly patients is proposed.

Resistance to Somatostatin Analogs in Italian Acromegaly Patients: The MISS Study

Approximately 60% of acromegaly patients are not adequately controlled by first-generation somatostatin receptor ligands. This multicenter retrospective study aimed to identify the most relevant biomarkers specific for the Italian acromegaly population. Resistant patients were enrolled consecutively based on time of neurosurgery, while responders were collected in a 1:2 ratio. Clinical characteristics and T2-intensity on MRI scans at diagnosis were retrospectively re-evaluated. Histological analyses of CAM5.2 granulation patterns and SSTR2 expression were centrally performed. Sixty-three resistant patients and thirty-three responders were enrolled. A low-grade SSTR2 expression was the most relevant predictor of resistance identified (OR 4.58, p = 0.013), even considering CAM5.2 immunohistochemistry (OR 2.65, p = 0.047). T2-iso/hyperintense pattern on MRI was also associated with a 3.3-fold greater probability of poor response to medical treatment (p = 0.027), as well as a young age at diagnosis (OR 0.96, p = 0.035). In those patients treated only after neurosurgery due to persistent GH-hypersecretion (51, 53.1%) the absence of any appreciable adenomatous remnant on postoperative MRI was associated with a negligible risk of resistance (OR 0.04, p = 0.003). In the Italian acromegaly population, a low-grade SSTR2 expression seems to be the most relevant predictor of resistance to first-generation somatostatin receptor ligands, followed by a SG/intermediate cytokeratin pattern and a T2-iso/hyperintense MRI signal.

Predictive Factors of Somatostatin Receptor Ligand Response in Acromegaly-A Prospective Study

CONTEXT

Somatostatin receptor ligands (SRLs) are the cornerstone medical treatments for acromegaly; however, many patients remain unresponsive to SRLs. Well-established predictive markers of response are needed.

OBJECTIVE

We aimed to explore the relationship between responsiveness to SRLs relative to somatostatin (SST)2A and 5 receptor expression, adenoma granularity, and T2-weighted magnetic resonance imaging (MRI) signal intensity (T2WSI).

METHODS

We conducted a multicentric, prospective, observational cohort study, in France. Forty-nine naïve patients (ie, patients without preoperative SRL treatment) with active acromegaly following surgery were treated with octreotide (group 1; n = 47), or pasireotide if uncontrolled under first-generation SRLs (group 2; n = 9). Data were collected at baseline and months 3 and 6. Biochemical measurements, immunohistochemistry studies, and MRI readings were centralized.

RESULTS

In group 1, IGF-I decrease from baseline to month 6 positively correlated with SST2A immunoreactive score (IRS), P = 0.01. Densely granulated/intermediate adenomas had a greater IGF-I and GH decrease under octreotide compared with sparsely granulated adenomas (P = 0.02 and P = 0.006, respectively), and expressed greater levels of SST2A (P < 0.001), coupled with lower levels of SST5 (P = 0.004). T2WSI changed between preoperative MRI and month 6 MRI in one-half of the patients. Finally, SST5 IRS was higher in preoperative hyperintense compared with preoperative hypointense adenomas (P = 0.04), and most sparsely granulated and most hyperintense adenomas expressed high SST5 levels.

CONCLUSION

We prospectively confirm that SST2A and adenoma granularity are good predictors of response to octreotide. We propose the IRS for scoring system harmonization. MRI sequences must be optimized to be able to use the T2WSI as a predictor of treatment response.

Acromegaly: pathogenesis, diagnosis, and management

Growth hormone-secreting pituitary adenomas that cause acromegaly arise as monoclonal expansions of differentiated somatotroph cells and are usually sporadic. They are almost invariably benign, yet they can be locally invasive and show progressive growth despite treatment. Persistent excess of both growth hormone and its target hormone insulin-like growth factor 1 (IGF-1) results in a wide array of cardiovascular, respiratory, metabolic, musculoskeletal, neurological, and neoplastic comorbidities that might not be reversible with disease control. Normalisation of IGF-1 and growth hormone are the primary therapeutic aims; additional treatment goals include tumour shrinkage, relieving symptoms, managing complications, reducing excess morbidity, and improving quality of life. A multimodal approach with surgery, medical therapy, and (more rarely) radiation therapy is required to achieve these goals. In this Review, we examine the epidemiology, pathogenesis, diagnosis, complications, and treatment of acromegaly, with an emphasis on the importance of tailoring management strategies to each patient to optimise outcomes.

MicroRNA in Acromegaly: Involvement in the Pathogenesis and in the Response to First-Generation Somatostatin Receptor Ligands

Acromegaly is a chronic and systemic disease due to excessive growth hormone and insulin-like growth factor type I caused, in the vast majority of cases, by a GH-secreting pituitary adenoma. About 40% of these tumors have somatic mutations in the stimulatory G protein alpha-subunit 1 gene. The pathogenesis of the remaining tumors, however, is still not fully comprehended. Surgery is the first-line therapy for these tumors, and first-generation somatostatin receptor ligands (fg-SRL) are the most prescribed medications in patients who are not cured by surgery. MicroRNAs are small, non-coding RNAs that control the translation of many mRNAs, and are involved in the post-transcriptional regulation of gene expression. Differentially expressed miRNAs can explain differences in the pathogenesis of acromegaly and tumor resistance. In this review, we focus on the most validated miRNAs, which are mainly involved in acromegaly’s tumorigenesis and fg-SRL resistance, as well as in circulating miRNAs in acromegaly.

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.

Data mining analyses for precision medicine in acromegaly: a proof of concept

Predicting which acromegaly patients could benefit from somatostatin receptor ligands (SRL) is a must for personalized medicine. Although many biomarkers linked to SRL response have been identified, there is no consensus criterion on how to assign this pharmacologic treatment according to biomarker levels. Our aim is to provide better predictive tools for an accurate acromegaly patient stratification regarding the ability to respond to SRL. We took advantage of a multicenter study of 71 acromegaly patients and we used advanced mathematical modelling to predict SRL response combining molecular and clinical information. Different models of patient stratification were obtained, with a much higher accuracy when the studied cohort is fragmented according to relevant clinical characteristics. Considering all the models, a patient stratification based on the extrasellar growth of the tumor, sex, age and the expression of E-cadherin, GHRL, IN1-GHRL, DRD2, SSTR5 and PEBP1 is proposed, with accuracies that stand between 71 to 95%. In conclusion, the use of data mining could be very useful for implementation of personalized medicine in acromegaly through an interdisciplinary work between computer science, mathematics, biology and medicine. This new methodology opens a door to more precise and personalized medicine for acromegaly patients.

Diagnosis and Treatment of Acromegaly: An Update

Acromegaly is typically caused by a growth hormone-secreting pituitary adenoma, driving excess secretion of insulin-like growth factor 1. Acromegaly may result in a variety of cardiovascular, respiratory, endocrine, metabolic, musculoskeletal, and neoplastic comorbidities. Early diagnosis and adequate treatment are essential to mitigate excess mortality associated with acromegaly. PubMed searches were conducted using the keywords growth hormone, acromegaly, pituitary adenoma, diagnosis, treatment, pituitary surgery, medical therapy, and radiation therapy (between 1981 and 2021). The diagnosis of acromegaly is confirmed on biochemical grounds, including elevated serum insulin-like growth factor 1 and lack of growth hormone suppression after glucose administration. Pituitary magnetic resonance imaging is advised in patients with acromegaly to identify an underlying pituitary adenoma. Transsphenoidal pituitary surgery is generally first-line therapy for patients with acromegaly. However, patients with larger and invasive tumors (macroadenomas) are often not in remission postoperatively. Medical therapies, including somatostatin receptor ligands, cabergoline, and pegvisomant, can be recommended to patients with persistent disease after surgery. Select patients may also be candidates for preoperative medical therapy. In addition, primary medical therapy has a role for patients without mass effect on the optic chiasm who are unlikely to be cured by surgery. Clinical, endocrine, imaging, histologic, and molecular markers may help predict the response to medical therapy; however, confirmation in prospective studies is needed. Radiation therapy is usually a third-line option and is increasingly administered by a variety of stereotactic techniques. An improved understanding of the pathogenesis of acromegaly may ultimately lead to the design of novel, efficacious therapies for this serious condition.

The Future of Somatostatin Receptor Ligands in Acromegaly

Currently, the first-generation somatostatin receptor ligands (fg-SRLs), octreotide LAR and lanreotide autogel, are the mainstays of acromegaly treatment and achieve biochemical control in approximately 40% of patients and tumor shrinkage in over 60% of patients. Pasireotide, a second-generation SRL, shows higher efficacy with respect to both biochemical control and tumor shrinkage but has a worse safety profile. In this review, we discuss the future perspectives of currently available SRLs, focusing on the use of biomarkers of response and precision medicine, new formulations of these SRLs and new drugs, which are under development. Precision medicine, which is based on biomarkers of response to treatment, will help guide the decision-making process by allowing physicians to choose the appropriate drug for each patient and improving response rates. New formulations of available SRLs, such as oral, subcutaneous depot, and nasal octreotide, may improve patients' adherence to treatment and quality of life since there will be more options available that better suit each patient. Finally, new drugs, such as paltusotine, somatropin, ONO-5788, and ONO-ST-468, may improve treatment adherence and present higher efficacy than currently available drugs.

Personalized Medical Treatment in Patients with Acromegaly: A Review

Acromegaly is associated with significant morbidity and mortality if not appropriately treated. In addition to insulin-like growth factor 1 (IGF-1) and growth hormone (GH) normalization, and tumor shrinkage, treatment goals include symptom relief, managing complications and improving quality of life. Surgical resection is a first-line treatment in most patients, with few being pretreated pre-operatively with medications. Somatostatin receptor ligands (SRLs), injectable and more recently oral capsules, have been the cornerstone of first-line medical therapy for persistent disease. However, several factors, including sparsely granulated adenomas, absent/low somatostatin receptor (SSTR2) status, imaging T2-hyperintensity, young age and aryl hydrocarbon receptor interacting protein mutations could predict first-generation SRL resistance. Patients with these characteristics may be better candidates for the GH receptor antagonist, pegvisomant, or in cases of large tumors the second-generation SRL, pasireotide. Combination therapy should be further pursued in patients who remain biochemically uncontrolled or have high remnant tumor after monotherapy. An efficacious and cost-effective pegvisomant dose-sparing effect of SRLs when used in combination has been demonstrated. With such a wide array of medical treatment options, it is increasingly important to tailor treatment to patients' unique characteristics as well as preferences, with a goal of personalizing management to achieve high quality outcomes.

gsp Mutation Is Not a Molecular Biomarker of Long-Term Response to First-Generation Somatostatin Receptor Ligands in Acromegaly

Simple Summary

Acromegaly treatment consists of surgical, medical, and radiation therapy. First-generation somatostatin receptor ligands are the mainstay of medical therapy, with approximately 40% disease control rate. Several parameters have been evaluated as predictors of response to these drugs, including mutations in the stimulatory G-protein α subunit (gsp mutation), which is still controversial. In this study, we aimed to evaluate in a large series of patients whether gsp mutation predicts long-term response to medical treatment and to characterize the gsp mutated population. The ability to predict response to medical therapy would help to choose a therapy that presents higher odds of controlling the disease, which ultimately would reduce treatment costs and disease morbi-mortality.

Abstract

Background: It is still controversial if activating mutations in the stimulatory G-protein α subunit (gsp mutation) are a biomarker of response to first generation somatostatin receptor ligands (fg-SRL) treatment in acromegaly. Thus, we aimed to evaluate whether gsp mutation predicts long-term response to fg-SRL treatment and to characterize the phenotype of patients harboring gsp mutations. Methods: GNAS1 sequencing was performed by Sanger. SST2 and SST5 were analyzed by immunohistochemistry (IHC) and real-time RT-PCR. The cytokeratin granulation pattern was evaluated by IHC. Biochemical control was defined as GH < 1.0 ng/mL and normal age-adjusted IGF-I levels. Results: gsp mutation was found in 54 out of 136 patients evaluated. Biochemical control with fg-SRL treatment was similar in gsp+ and gsp- patients (37% vs. 25%, p = 0.219). Tumors harboring gsp mutation were smaller (p = 0.035) and had a lower chance of invading cavernous sinuses (p = 0.001). SST5 protein (p = 0.047) and mRNA (p = 0.013) expression levels were higher in wild-type tumors. Conclusions: In this largest series available in the literature, we concluded that gsp is not a molecular biomarker of response to fg-SRL treatment in acromegaly. However, the importance of its negative association with cavernous sinus invasion and SST5 expression needs to be further investigated.