Acromegaly: achieving timely diagnosis and improving outcomes by personalized care

Acromegaly: diagnostic challenges and individualized treatment

INTRODUCTION

Acromegaly is due in almost all cases to a GH-secreting pituitary tumor. GH and IGF-1 excesses lead to its multi-system clinical manifestations and comorbidities. Acromegaly is under-diagnosed and typically presents with advanced disease. When early or mild, clinical recognition and biochemical confirmation are especially challenging. Individualized treatment may optimize patient outcome.

AREAS COVERED

This review covers challenges to diagnosing acromegaly and reviews therapies for acromegaly with a focus on those aspects that can be individualized.

EXPERT OPINION

The first step in diagnosing acromegaly is recognizing it clinically. To improve this, increase awareness and education of the general population and healthcare professionals about the acromegaly phenotype is needed. Once suspected clinically, IGF-1 measurement is the initial step in making the biochemical diagnosis. GH may be < 1.0 µg/L after oral glucose suppression in early/mild cases. GH and IGF-1 should be considered in concert. Providers should be aware of conditions that can alter GH and IGF-1 levels and each assay's performance. An individualized treatment approach is best employed. Surgery is preferred as initial treatment and medical therapy as initial adjuvant therapy. In individualizing therapy, the advantages and disadvantages of each option and predictors of response to them should be considered.

Ends of the spectrum best practices for early detection and multidisciplinary management of acromegaly

PURPOSE

Acromegaly is characterized by an insidious clinical presentation and delayed diagnosis. Longer delays are associated with more comorbidities which can persist after treatment of the growth hormone-secreting pituitary adenoma (GH-PA). Surgery is the primary therapy of GH-secreting PA, which can lead to durable remission. However, approximately 50% of patients require medical treatment postoperatively. Survival normalizes after achieving biochemical control. This mini-review will address ends of the spectrum challenges in acromegaly, including delayed diagnosis and management of the residual tumor and persistent comorbidities.

METHODS

We synthesize relevant literature and present a case of acromegaly that highlights the complexity of clinical decision-making in the diagnosis and treatment of persistent acromegaly.

RESULTS

Despite improved biochemical assays, most patients with acromegaly are diagnosed on average five years after initial symptoms. A high index of suspicion does not rely exclusively on acral enlargement, but also a constellation of manifestations and comorbidities suggestive of acromegaly. Medical therapy is required in patients with persistent biochemical disease. Somatostatin receptor ligands are the cornerstone of medical treatment and can be used alone or in combination with dopamine agonists and growth hormone receptor antagonists. Improved options of medical treatment and careful consideration of comorbidities enables individualized patient management. Reoperation and radiation are considered for tumor progression despite medical therapy. In rare cases of resistant and aggressive tumors, neuro-oncology expertise is required.

CONCLUSIONS

Increased awareness through education targeting the multifaceted clinical presentation of acromegaly shortens the time to diagnosis and treatment. Multidisciplinary management by specialists increases the likelihood of biochemical and tumor control.

Machine learning-based algorithms applied to drug prescriptions and other healthcare services in the Sicilian claims database to identify acromegaly as a model for the earlier diagnosis of rare diseases

Acromegaly is a rare disease characterized by a diagnostic delay ranging from 5 to 10 years from the symptoms' onset. The aim of this study was to develop and internally validate machine-learning algorithms to identify a combination of variables for the early diagnosis of acromegaly. This retrospective population-based study was conducted between 2011 and 2018 using data from the claims databases of Sicily Region, in Southern Italy. To identify combinations of potential predictors of acromegaly diagnosis, conditional and unconditional penalized multivariable logistic regression models and three machine learning algorithms (i.e., the Recursive Partitioning and Regression Tree, the Random Forest and the Support Vector Machine) were used, and their performance was evaluated. The random forest (RF) algorithm achieved the highest Area under the ROC Curve value of 0.83 (95% CI 0.79-0.87). The sensitivity in the test set, computed at the optimal threshold of predicted probabilities, ranged from 28% for the unconditional logistic regression model to 69% for the RF. Overall, the only diagnosis predictor selected by all five models and algorithms was the number of immunosuppressants-related pharmacy claims. The other predictors selected by at least two models were eventually combined in an unconditional logistic regression to develop a meta-score that achieved an acceptable discrimination accuracy (AUC = 0.71, 95% CI 0.66-0.75). Findings of this study showed that data-driven machine learning algorithms may play a role in supporting the early diagnosis of rare diseases such as acromegaly.