Sex modifies the predictive value of computed tomography combined with serum potassium for primary aldosteronism subtype diagnosis

Objective

We aimed to investigate the predictive value of the CT findings combined with serum potassium levels for primary aldosteronism (PA) subtype diagnosis, with a particular interest in sex differences.

Methods

In this retrospective study, we eventually included 482 PA patients who underwent successful adrenal venous sampling (AVS) and had available data. We diagnosed the subjects as having either unilateral (n = 289) or bilateral PA (n = 193) based on AVS. We analyzed the concordance rate between AVS and adrenal CT combined with serum potassium and performed a logistic regression analysis to assess the prevalence of unilateral PA on AVS.

Results

The total diagnostic concordance rate between CT findings and AVS was 51.5% (248/482). The prevalence of hypokalemia in men and women was 47.96% (129/269) and 40.85% (87/213), respectively. The occurrence of unilateral lesions on CT and hypokalemia was significantly associated with an increased prevalence of unilateral PA [odds ratio (OR) 1.537; 95% confidence interval (CI) 1.364-1.731; p < 0.001]. In male participants, G2 (bilateral lesion on CT and normokalemia), G3 (unilateral lesion on CT and normokalemia), G4 (bilateral normal on CT and hypokalemia), G5 (bilateral lesion on CT and hypokalemia), and G6 (unilateral lesion on CT and hypokalemia) were significantly increased for the prevalence of unilateral PA on AVS (G2: OR 4.620, 95% CI 1.408-15.153; G3: OR 6.275, 95% CI 2.490-15.814; G4: OR 3.793, 95% CI 1.191-12.082; G5: OR 16.476, 95% CI 4.531-59.905; G6: OR 20.101, 95% CI 7.481-54.009; all p < 0.05), compared with G1 (patients with bilateral normal on CT and normokalemia). However, among female participants, we found an increased likelihood for unilateral PA in patients with unilateral lesions on CT and hypokalemia alone (OR 10.266, 95% CI 3.602-29.259, p < 0.001), while no associations were found in other groups (all p > 0.05). Sex had a significant effect on modifying the relationship between unilateral PA and the combination of CT findings and serum potassium (p for interaction <0.001).

Conclusion

In conclusion, our results indicated that CT findings combined with serum potassium levels have a great value for predicting the subtype of PA and are stronger in men.

A discriminative event-based model for subtype diagnosis of sporadic Creutzfeldt-Jakob disease using brain MRI

INTRODUCTION

Sporadic Creutzfeldt-Jakob disease (sCJD) comprises multiple subtypes (MM1, MM2, MV1, MV2C, MV2K, VV1, and VV2) with distinct disease durations and spatiotemporal cascades of brain lesions. Our goal was to establish the ante mortem diagnosis of sCJD subtype, based on patient-specific estimates of the spatiotemporal cascade of lesions detected by diffusion-weighted magnetic resonance imaging (DWI).

METHODS

We included 488 patients with autopsy-confirmed diagnosis of sCJD subtype and 50 patients with exclusion of prion disease. We applied a discriminative event-based model (DEBM) to infer the spatiotemporal cascades of lesions, derived from the DWI scores of 12 brain regions assigned by three neuroradiologists. Based on the DEBM cascades and the prion protein genotype at codon 129, we developed and validated a novel algorithm for the diagnosis of the sCJD subtype.

RESULTS

Cascades of MM1, MM2, MV1, MV2C, and VV1 originated in the parietal cortex and, following subtype-specific orderings of propagation, went toward the striatum, thalamus, and cerebellum; conversely, VV2 and MV2K cascades showed a striatum-to-cortex propagation. The proposed algorithm achieved 76.5% balanced accuracy for the sCJD subtype diagnosis, with low rater dependency (differences in accuracy of ± 1% among neuroradiologists).

DISCUSSION

Ante mortem diagnosis of sCJD subtype is feasible with this novel data-driven approach, and it may be valuable for patient prognostication, stratification in targeted clinical trials, and future therapeutics.

HIGHLIGHTS

Subtype diagnosis of sporadic Creutzfeldt-Jakob disease (sCJD) is achievable with diffusion MRI. Cascades of diffusion MRI abnormalities in the brain are subtype-specific in sCJD. We proposed a diagnostic algorithm based on cascades of diffusion MRI abnormalities and demonstrated that it is accurate. Our method may aid early diagnosis, prognosis, stratification in clinical trials, and future therapeutics. The present approach is applicable to other neurodegenerative diseases, enhancing the differential diagnoses.

A new machine learning-based prediction model for subtype diagnosis in primary aldosteronism

INTRODUCTION

Unilateral primary aldosteronism (UPA) and bilateral primary aldosteronism (BPA) are the two subtypes of PA. Discriminating UPA from BPA is of great significance. Although adrenal venous sampling (AVS) is the gold standard for diagnosis, it has shortcomings. Thus, improved methods are needed.

METHODS

The original data were extracted from the public database "Dryad". Ten parameters were included to develop prediction models for PA subtype diagnosis using machine learning technology. Moreover, the optimal model was chose and validated in an external dataset.

RESULTS

In the modeling dataset, 165 patients (71 UPA, 94 BPA) were included, while in the external dataset, 43 consecutive patients (20 UPA, 23 BPA) were included. The ten parameters utilized in the prediction model include age, sex, systolic and diastolic blood pressure, aldosterone to renin ratio (ARR), serum potassium, ARR after 50 mg captopril challenge test (CCT), primary aldosterone concentration (PAC) after saline infusion test (SIT), PAC reduction rate after SIT, and number of types of antihypertensive agents at diagnosis. The accuracy, sensitivity, specificity, F1 score, and AUC for the optimal model using the random forest classifier were 90.0%, 81.8%, 96.4%, 0.878, and 0.938, respectively, in the testing dataset and 81.4%, 90.0%, 73.9%, 0.818 and 0.887, respectively, in the validating external dataset. The most important variables contributing to the prediction model were PAC after SIT, ARR, and ARR after CCT.

DISCUSSION

We developed a machine learning-based predictive model for PA subtype diagnosis based on ten clinical parameters without CT imaging. In the future, artificial intelligence-based prediction models might become a robust prediction tool for PA subtype diagnosis, thereby, might reducing at least some of the requests for CT or AVS and assisting clinical decision-making.

A novel clinical nomogram to predict bilateral hyperaldosteronism in Chinese patients with primary aldosteronism

CONTEXT

Adrenal venous sampling (AVS) is recommended as the gold standard for subtype classification in primary aldosteronism (PA); however, this approach has limited availability.

OBJECTIVE

We aimed to develop a novel clinical nomogram to predict PA subtype based on routine variables, thereby reducing the number of candidates for AVS.

PATIENTS AND METHOD

Patients were randomly divided into a training set (n = 185) and a validation set (n = 79). Risk factors for idiopathic hyperaldosteronism (IHA) differentiating from aldosterone-producing adenoma (APA) were identified using logistic regression analysis. A nomogram was constructed to predict the probability of IHA. A receiver operating characteristic (ROC) curve and a calibration plot were applied to assess the predictive value. Then, 115 patients were prospectively enrolled, and a nomogram was used to predict the subtypes before AVS.

RESULTS

Body mass index (BMI), serum potassium and computed tomography (CT) finding were adopted in the nomogram. The nomogram presented an area under the ROC (AUC) of 0.924 (95% CI: 0.875-0.957), sensitivity of 86.59% and specificity of 87.38% in the training set and an AUC of 0.894 (95% CI: 0.804-0.952), sensitivity of 82.86% and specificity of 84.09% in the validation set. Predicted probability and actual probability matched well in the nomogram (Hosmer-Lemeshow test: P > 0.05). Using the nomogram as a surrogate to predict IHA in the prospective set before AVS, the specificity reached 100% when we increased the threshold to a probability of 90%.

CONCLUSION

We have developed a tool that is able to predict IHA in patients with PA and potentially avoid AVS.