The Application of Principal Component Analysis on Clinical and Biochemical Parameters Exemplified in Children With Congenital Adrenal Hyperplasia

Differentiation of Idiopathic Central Precocious Puberty From Premature Thelarche Using Principal Component Analysis

CONTEXT

Nonprogressive premature thelarche (PT) is a self-limiting variant of early puberty, while idiopathic central precocious puberty (ICPP) is a disorder that causes progressive development of secondary sexual characteristics and often requires treatment. The diagnostic differentiation between these conditions is important but can be challenging since they often both initially present clinically with isolated breast development.

OBJECTIVE

To describe relevant clinical variables in a large cohort of girls referred for early puberty, and to evaluate clinical and biochemical parameters to distinguish between girls with ICPP and PT.

METHODS

This retrospective study included 1361 girls referred with signs of early puberty to a single, tertiary center from 2009 to 2019. We evaluated clinical presentation, medical history, growth velocity, bone age, hormonal serum concentrations, and gonadotropin-releasing hormone (GnRH) test results.

RESULTS

Central precocious puberty was diagnosed in 11% (ICPP: n = 143, organic CPP: n = 11) girls, whereas 8% (n = 91 girls) presented with PT. Receiver operating characteristic (ROC) analysis showed several biochemical and anthropometric markers as potential parameters to differentiate between ICPP and PT; however, none were individually adequate. Principal component analysis (PCA)-derived clinical and hormone profiles could predict girls with ICPP from girls with PT with a specificity of 90% and sensitivity of 84%, outperforming any single marker.

CONCLUSION

Differentiation of girls with ICPP and PT can be supported by individual clinical and biochemical parameters. However, dimension reduction of clinical and hormonal profiles by PCA improved the diagnostic value, which in the future may support the diagnostic process as a supplement to the GnRH test in evaluation of pubertal disorders.

Feature Importance Analysis of a Deep Learning Model for Predicting Late Bladder Toxicity Occurrence in Uterine Cervical Cancer Patients

(1) In this study, we developed a deep learning (DL) model that can be used to predict late bladder toxicity. (2) We collected data obtained from 281 uterine cervical cancer patients who underwent definitive radiation therapy. The DL model was trained using 16 features, including patient, tumor, treatment, and dose parameters, and its performance was compared with that of a multivariable logistic regression model using the following metrics: accuracy, prediction, recall, F1-score, and area under the receiver operating characteristic curve (AUROC). In addition, permutation feature importance was calculated to interpret the DL model for each feature, and the lightweight DL model was designed to focus on the top five important features. (3) The DL model outperformed the multivariable logistic regression model on our dataset. It achieved an F1-score of 0.76 and an AUROC of 0.81, while the corresponding values for the multivariable logistic regression were 0.14 and 0.43, respectively. The DL model identified the doses for the most exposed 2 cc volume of the bladder (BD_2cc) as the most important feature, followed by BD_5cc and the ICRU bladder point. In the case of the lightweight DL model, the F-score and AUROC were 0.90 and 0.91, respectively. (4) The DL models exhibited superior performance in predicting late bladder toxicity compared with the statistical method. Through the interpretation of the model, it further emphasized its potential for improving patient outcomes and minimizing treatment-related complications with a high level of reliability.

Biochemical identification of prepubertal boys with Klinefelter syndrome by combined reproductive hormone profiling using machine learning

Objective

Klinefelter syndrome (KS) is the most common sex chromosome disorder and genetic cause of infertility in males. A highly variable phenotype contributes to the fact that a large proportion of cases are never diagnosed. Typical hallmarks in adults include small testes and azoospermia which may prompt biochemical evaluation that typically shows extremely high follicle-stimulating hormone and low/undetectable inhibin B serum concentrations. However, in prepubertal KS individuals, biochemical parameters are largely overlapping those of prepubertal controls. We aimed to characterize clinical profiles of prepubertal boys with KS in relation to controls and to develop a novel biochemical classification model to identify KS before puberty.

Methods

Retrospective, longitudinal data from 15 prepubertal boys with KS and data from 1475 controls were used to calculate age- and sex-adjusted standard deviation scores (SDS) for height and serum concentrations of reproductive hormones and used to infer a decision tree classification model for KS.

Results

Individual reproductive hormones were low but within reference ranges and did not discriminate KS from controls. Clinical and biochemical profiles including age- and sex-adjusted SDS from multiple reference curves provided input data to train a 'random forest' machine learning (ML) model for the detection of KS. Applied to unseen data, the ML model achieved a classification accuracy of 78% (95% CI, 61-94%).

Conclusions

Supervised ML applied to clinically relevant variables enabled computational classification of control and KS profiles. The application of age- and sex-adjusted SDS provided robust predictions irrespective of age. Specialized ML models applied to combined reproductive hormone concentrations may be useful diagnostic tools to improve the identification of prepubertal boys with KS.

Serum LH/FSH ratios in 87 infants with differences of sex development

The ratio between luteinizing hormone (LH) and follicle-stimulating hormone (FSH) has previously been described as an excellent marker of sex in healthy infants. However, LH/FSH remains not fully described in patients with differences of sex development (DSD). The aim was therefore to describe LH/FSH in infants with DSD. This was a retrospective study of DSD patients, all aged 0-1.2 years. In total, 87 infants with DSD and at least one serum sample per infant were included. Longitudinal samples from single patients were included whenever possible. Serum LH/FSH ratios in these patients were plotted against recently published age-related and sex-dimorphic cutoffs. Overall, LH/FSH sometimes corresponded to assigned sex without any obvious pattern in terms of diagnoses. LH/FSH corresponded to the biological sex in all patients with Turner or Klinefelter syndrome. In patients with 46,XX or 46,XY DSD (except congenital adrenal hyperplasia (CAH)), the ratios did not correspond to the assigned sex in all cases and were interchangeably within the male and female range. In patients with CAH, the ratio corresponded to biological sex (based on sex chromosomes) in some cases but also ranged across the cutoffs. In the 15 patients with 45,X/46,XY mosaicism, the LH/FSH ratios corresponded to the assigned sex in all cases (12 were raised as males, 3 as females) and at all time points in cases with multiple sampling. While this study describes LH/FSH in infants with DSD, the exact clinical role of the ratio in the management of these patients remains to be further elucidated.

Potassium Derangements: A Pathophysiological Review, Diagnostic Approach, and Clinical Management

Potassium is an essential cation critical in fluid and electrolyte balance, acid–base regulation, and neuromuscular functions. The normal serum potassium is kept within a narrow range of 3.5–5.2 meq/L while the intracellular concentration is approximately 140–150 meq/L. The total body potassium is about 45–55 mmol/kg; thus, a 70 kg male has an estimated ~136 g and 60 kg female has ~117 g of potassium. In total, 98% of the total body potassium is intracellular. Skeletal muscle contains ~80% of body potassium stores. The ratio of intracellular to extracellular potassium concentration (Ki/Ke) maintained by Na+/K+ ATPase determines the resting membrane potential. Disturbances of potassium homeostasis lead to hypo- and hyperkalemia, which if severe, can be life-threatening. Prompt diagnosis and management of these problems are important.