Combining metabolomics and machine learning models as a tool to distinguish non-classic 21-hydroxylase deficiency from polycystic ovary syndrome without adrenocorticotropic hormone testing

The interpretation of immunometric, chromatographic and mass spectrometric data for steroids in diagnosis of endocrine disorders

The analysis of steroids for endocrine disorders is in transition from immunoassay of individual steroids to more specific chromatographic and mass spectrometric methods with simultaneous determination of several steroids. Gas chromatography (GC) and liquid chromatography (LC) coupled with mass spectrometry (MS) offer unrivalled analytical capability for steroid analysis. These specialist techniques were often judged to be valuable only in a research laboratory but this is no longer the case. In a urinary steroid profile up to 30 steroids are identified with concentrations and excretion rates reported in a number of ways. The assays must accommodate the wide range in steroid concentrations in biological fluids from micromolar for dehydroepiandrosterone sulphate (DHEAS) to picomolar for oestradiol and aldosterone. For plasma concentrations, panels of 5-20 steroids are reported. The profile results are complex and interpretation is a real challenge in order to inform clinicians of likely implications. Although artificial intelligence and machine learning will in time generate reports from the analysis this is a way off being adopted into clinical practice. This review offers guidance on current interpretation of the data from steroid determinations in clinical practice. Using this approach more laboratories can use the techniques to answer clinical questions and offer broader interpretation of the results so that the clinician can understand the conclusion for the steroid defect, and can be advised to program further tests if necessary and instigate treatment. The biochemistry is part of the patient workup and a clinician led multidisciplinary team discussion of the results will be required for challenging patients. The laboratory will have to consider cost implications, bearing in mind that staff costs are the highest component. GC-MS and LC-MS/MS analysis of steroids are the choices. Steroid profiling has enormous potential to improve diagnosis of adrenal disorders and should be adopted in more laboratories in favour of the cheap, non-specific immunological methods.

Plasma 21-deoxycortisone: a sensitive additive tool in 21-hydroxylase deficiency in newborns

OBJECTIVE, DESIGN, AND METHODS

Although 17-hydroxyprogesterone (17OHP) has historically been the steroid assayed in the diagnosis of congenital adrenal 21-hydroxylase deficiency (CAH-21D), its C11-hydroxylated metabolite, 21-deoxycortisol (21DF), which is strictly of adrenal origin, is assayed in parallel in this pathology. This steroid (21DF) is oxidized by 11beta-hydroxysteroid dehydrogenase type 2 into 21-deoxycortisone (21DE). In the context of CAH-21D confirmation testing, confounding factors (such as intensive care unit admission, stress, prematurity, early sampling, and variations of sex development) can interfere with the interpretation of the gold-standard biomarkers (17OHP and 21DF). Since its tissue concentrations are especially high in the placenta, we hypothesized that 21DE quantification in the neonatal periods could be an interesting biomarker in addition to 17OHP and 21DF. To verify this hypothesis, we developed a new mass spectrometry-based assay for 21DE in serum and applied it to newborns screened for CAH-21D.

RESULTS

In newborns with CAH-21D, the mean serum levels of 21DE reached 17.56 ng/mL (ranging from 8.58 ng/mL to 23.20 ng/mL), and the mean 21DE:21DF ratio was 4.99. In contrast, in newborns without CAH-21D, the 21DE serum levels were low and not statistically different from the analytical 21DE limit of quantification (0.01 ng/mL).

CONCLUSION

Basal serum 21DE appears to be a novel sensitive and specific biomarker of CAH-21D in newborns.

Artificial intelligence in paediatric endocrinology: conflict or cooperation

Artificial intelligence (AI) in medicine is transforming healthcare by automating system tasks, assisting in diagnostics, predicting patient outcomes and personalising patient care, founded on the ability to analyse vast datasets. In paediatric endocrinology, AI has been developed for diabetes, for insulin dose adjustment, detection of hypoglycaemia and retinopathy screening; bone age assessment and thyroid nodule screening; the identification of growth disorders; the diagnosis of precocious puberty; and the use of facial recognition algorithms in conditions such as Cushing syndrome, acromegaly, congenital adrenal hyperplasia and Turner syndrome. AI can also predict those most at risk from childhood obesity by stratifying future interventions to modify lifestyle. AI will facilitate personalised healthcare by integrating data from 'omics' analysis, lifestyle tracking, medical history, laboratory and imaging, therapy response and treatment adherence from multiple sources. As data acquisition and processing becomes fundamental, data privacy and protecting children's health data is crucial. Minimising algorithmic bias generated by AI analysis for rare conditions seen in paediatric endocrinology is an important determinant of AI validity in clinical practice. AI cannot create the patient-doctor relationship or assess the wider holistic determinants of care. Children have individual needs and vulnerabilities and are considered in the context of family relationships and dynamics. Importantly, whilst AI provides value through augmenting efficiency and accuracy, it must not be used to replace clinical skills.

Steroid profiling in adrenal disease

The measurement of steroid hormones in blood and urine, which reflects steroid biosynthesis and metabolism, has been recognized as a valuable tool for identifying and distinguishing steroidogenic disorders. The application of mass spectrometry enables the reliable and simultaneous analysis of large panels of steroids, ushering in a new era for diagnosing adrenal diseases. However, the interpretation of complex hormone results necessitates the expertise and experience of skilled clinicians. In this scenario, machine learning techniques are gaining worldwide attention within healthcare fields. The clinical values of combining mass spectrometry-based steroid profiles analysis with machine learning models, also known as steroid metabolomics, have been investigated for identifying and discriminating adrenal disorders such as adrenocortical carcinomas, adrenocortical adenomas, and congenital adrenal hyperplasia. This promising approach is expected to lead to enhanced clinical decision-making in the field of adrenal diseases. This review will focus on the clinical performances of steroid profiling, which is measured using mass spectrometry and analyzed by machine learning techniques, in the realm of decision-making for adrenal diseases.

The serum steroid signature of PCOS hints at the involvement of novel pathways for excess androgen biosynthesis

CONTEXT

Polycystic ovary syndrome (PCOS) is defined by androgen excess and ovarian dysfunction in the absence of a specific physiological diagnosis. The best clinical marker of androgen excess is hirsutism, while the best biochemical parameter is still a matter of debate. Current consensus guidelines recommend, among other hormones, serum free testosterone as an important serum parameter to measure androgen excess. Recently, however, novel active androgens and androgen metabolic pathways have been discovered.

OBJECTIVE

To assess the contribution of novel androgens and related steroid biosynthetic pathways to the serum steroid pool in PCOS women in comparison to healthy controls.

DESIGN

This is a case control study, wherein PCOS was diagnosed according to the AE-PCOS 2009 criteria. Serum steroid profiling was performed by liquid chromatography high-resolution mass spectrometry.

SETTING

Yeditepe University and associated clinics in Istanbul, Turkey, together with Bern University Hospital Inselspital, Bern, Switzerland.

PARTICIPANTS

42 PCOS women and 42 matched, healthy control women.

MAIN OUTCOME MEASURES

Assessment of 34 steroids compartmentalized in four androgen related pathways: the classic androgen pathway, the backdoor pathway, the C11-oxy backdoor pathway, and the C11-oxy (11β-hydroxyandrostenedione) pathway.

RESULTS

Metabolites of all four pathways were identified in healthy and PCOS women. Highest concentrations were found for progesterone in controls and androstenedione in PCOS. Lowest levels were found for 11-ketotestosterone in controls compared to PCOS, and for 20α-hydroxyprogesterone in PCOS compared to controls. PCOS also had higher serum testosterone levels compared to the controls. PCOS women had overall higher levels of steroid metabolites of all four androgen pathways compared to healthy controls.

CONCLUSIONS

Novel alternative pathways contribute to the androgen production in healthy and PCOS women. Hyperandrogenism in PCOS is characterized by an overall increase of serum androgens in the classic, backdoor and C11-oxy pathways. While monogenetic disorders of steroid biosynthesis can be recognized by a specific pattern in the steroid profile, no diagnostic pattern or classifier was found in the serum for PCOS.