Clinical Report: Hand Photos May Flag Rare Hormone Disorder
Overview
A deep learning model analyzing hand images shows promise in detecting acromegaly, achieving high sensitivity and specificity in a multicenter study. This approach could facilitate earlier diagnosis and referral for endocrine evaluation.
Background
Acromegaly is a rare disorder caused by excessive growth hormone secretion, often leading to significant physical changes and systemic complications. Delayed diagnosis is common, with many patients experiencing diagnostic delays of over 10 years. Innovative screening methods, such as image analysis, could improve early detection and management of this condition.
Data Highlights
| Metric | Value |
|---|---|
| Sensitivity | 0.89 |
| Specificity | 0.91 |
| Positive Predictive Value | 0.88 |
| Negative Predictive Value | 0.93 |
| F1-score | 0.89 |
| AUC | 0.96 |
Key Findings
- The deep learning model achieved a sensitivity of 0.89 and specificity of 0.91 in detecting acromegaly.
- Positive predictive value was 0.88, and negative predictive value was 0.93.
- Endocrinologists' F1-scores ranged from 0.43 to 0.63 when evaluating the same images.
- Model predictions were based on hand morphology, particularly around finger joints and the base of the thumb.
- The study included 716 adults, with 317 diagnosed with acromegaly.
- The tool is intended to support clinical evaluation rather than replace it.
Clinical Implications
The findings suggest that image-based AI could serve as a valuable adjunct in the early identification of acromegaly, potentially leading to timely referrals for endocrine assessment. Clinicians should consider integrating such innovative tools into their diagnostic workflows while adhering to established biochemical confirmation protocols.
Conclusion
The study highlights the potential of deep learning models in enhancing the detection of acromegaly through non-invasive hand image analysis, paving the way for improved patient outcomes through earlier diagnosis.
References
- Automatic acromegaly detection using deep learning on hand images: a multicenter observational study, The Journal of Clinical Endocrinology & Metabolism, 2023
- Consensus on acromegaly therapeutic outcomes: an update, Nature Reviews Endocrinology, 2025
- FDA approves new treatment for acromegaly, a rare endocrine disorder, FDA, 2025
- The Journal of Clinical Endocrinology & Metabolism — Cushing-induced Male Hypogonadism: Deciphering a Prevalent Yet Understudied Relationship
- conexiant — FDA Signals New Testosterone Pathway
- Frontiers in Endocrinology — Rare SRY-negative 46,XX disorder of sex development with male phenotype and ectopic gonads: a case report
- The Journal of Clinical Endocrinology & Metabolism — Impact of Hormonal Treatment and Puberty Blockade on Body Weight, BMI, and Lipid Levels in Danish Transgender Youth
- Consensus on acromegaly therapeutic outcomes: an update | Nature Reviews Endocrinology
- FDA approves new treatment for acromegaly, a rare endocrine disorder | FDA
- Automatic acromegaly detection using deep learning on hand images: a multicenter observational study | The Journal of Clinical Endocrinology & Metabolism | Oxford Academic
This content is an AI-generated, fully rewritten summary based on a published scholarly article. It does not reproduce the original text and is not a substitute for the original publication. Readers are encouraged to consult the source for full context, data, and methodology.
Newsletters
Receive the latest pathologist news, personalities, education, and career development – weekly to your inbox.
