Clinical Score and Machine Learning-Based Model to Predict Diagnosis of Primary Aldosteronism in Arterial Hypertension

Screening for Primary Aldosteronism by Mass Spectrometry Versus Immunoassay Measurements of Aldosterone: A Prospective Within-Patient Study

BACKGROUND

Measurements of aldosterone by mass spectrometry are more accurate and less prone to interferences than immunoassay measurements, and may produce a more accurate aldosterone:renin ratio (ARR) when screening for primary aldosteronism (PA).

METHODS

Differences in diagnostic performance of the ARR using mass spectrometry vs immunoassay measurements of aldosterone were examined in 710 patients screened for PA. PA was confirmed in 153 patients and excluded in 451 others. Disease classifications were not achieved in 106 patients. Areas under receiver-operating characteristic curves (AUROC) and other measures were used to compare diagnostic performance.

RESULTS

Mass spectrometry-based measurements yielded lower plasma aldosterone concentrations than immunoassay measurements. For the ARR based on immunoassay measurements of aldosterone, AUROCs were slightly lower (P = 0.018) than those using mass spectrometry measurements (0.895 vs 0.906). The cutoff for the ARR to reach a sensitivity of 95% was 30 and 21.5 pmol/mU by respective immunoassay and mass spectrometry-based measurements, which corresponded to specificities of 57% for both. With data restricted to patients with unilateral PA, diagnostic sensitivities of 94% with specificities >81% could be achieved at cutoffs of 68 and 52 pmol/mU for respective immunoassay and mass spectrometry measurements.

CONCLUSIONS

Mass spectrometry-based measurements of aldosterone for the ARR provide no clear diagnostic advantage over immunoassay-based measurements. Both approaches offer limited diagnostic accuracy for the ARR as a screening test. One solution is to employ the higher cutoffs to triage patients likely to have unilateral PA for further tests and possible adrenalectomy, while using the lower cutoffs to identify others for targeted medical therapy.German Clinical Trials Register ID: DRKS00017084.

Screening for primary aldosteronism in primary care: a scoping review

BACKGROUND

Primary aldosteronism (PA) is the most common treatable and potentially curable cause of secondary hypertension. Prompt diagnosis and management by primary care physicians (PCPs) is important given the increased risk of cardiovascular complications however screening rates are low in primary care. Our aim was to identify factors that influence screening behaviour for PA among PCPs.

METHOD

A rigorous scoping review of seven databases between 16/08/22 and 09/08/23 was used to investigate PA screening practices. Articles written in English from peer-reviewed literature within the last 20 years were eligible for inclusion if an aspect of their study was conducted in primary care.

RESULTS

A total of 1380 titles and abstracts, and 61 full texts were screened, with 20 studies selected for data extraction. We identified three broad categories of factors influencing screening by PCPs-the patient, the clinician, and the healthcare system. Some studies targeted these factors to improve screening rates although there is little data on implementation and outcomes.

CONCLUSION

Low awareness, inadequate guidelines, and poor access to testing were identified as key barriers to PA screening. Targeted education sessions for PCPs, clear guidelines, and closer proximity to diagnostic centres may be required to improve PA detection in primary care.

Comparison between screening for primary aldosteronism with and without drug adjustment

OBJECTIVE

Few studies have evaluated the performance of non-drug-adjusted primary aldosteronism (PA) screening. Therefore, we aimed to examine the consistency between PA screening results with and without drug adjustment and to explore the effectiveness of screening without drug adjustment.

METHODS

This prospective study included 650 consecutive patients with a high risk of incidence PA. Patients who initially screened positive underwent rescreening with drug adjustments and confirmatory tests. Regarding the remaining patients, one of every three consecutive patients underwent rescreening with drug adjustments and confirmatory tests. The changes in aldosterone and renin concentrations were compared between patients with essential hypertension (EH) and those with PA before and after drug adjustment. Sensitivity and specificity were used to assess the diagnostic performance of screening without drug adjustment, using the confirmatory test results as the reference.

RESULTS

We screened 650 patients with hypertension for PA. Forty-nine patients were diagnosed with PA and 195 with EH. Regarding drugs, 519 patients were taking angiotensin-converting enzyme inhibitors (ACEIs), angiotensin II receptor blockers (ARBs), calcium channel blockers (CCBs), or diuretics alone or in combination. Forty-one patients were taking beta-blockers. Ninety patients were taking beta-blockers in combination with other drugs. In patients treated with ACEIs, ARBs, CCBs, or diuretics alone, or in combination, or beta-blockers alone, PA positivity was determined using the criteria, aldosterone-to-renin ratio (ARR) >38 pg/mL/pg/mL and plasma aldosterone concentration (PAC) >100 pg/mL, and negativity, using the criteria, ARR <9 pg/mL/pg/mL; the sensitivity and specificity were 94.7% and 94.5%, respectively. After drug adjustment, the sensitivity and specificity of screening were 92.1% and 89%, respectively.

CONCLUSIONS

In patients not treated with beta-blockers combined with others, when ARR >38 pg/mL/pg/mL and plasma aldosterone concentration (PAC) >100 pg/mL, or, ARR <9 pg/mL/pg/mL, non-drug-adjusted screening results were identical to with drug adjustment. Non-drug-adjusted screening could reduce the chance of medication adjustment, enable patients to continue their treatments and avoiding adverse effects, is of clinical importance.

Long-Term Follow-Up of Patients With Elevated Aldosterone-to-Renin Ratio but Negative Confirmatory Test: The Progression of Primary Aldosteronism Phenotypes

BACKGROUND

About 10% of patients with arterial hypertension have a positive screening test for primary aldosteronism (PA) and 50% to 70% of them have a negative confirmatory test: the appropriate follow-up of these patients is currently unknown. We investigated the incidence of PA in patients with previous negative confirmatory testing, after at least a 2-year follow-up.

METHODS

One hundred eighty-four patients with a previously elevated aldosterone-to-renin ratio followed by a negative confirmatory test were recruited in 2 hypertension centers (Torino and Munich). We repeated the screening test for PA and, if positive, the confirmatory test (seated saline infusion test or captopril challenge test). Primary end point of the study was the incidence of newly diagnosed overt PA, as defined by a positive confirmatory test.

RESULTS

After a mean follow-up of 5 years, 20% of patients developed overt PA. When subtype diagnosis was offered systematically, one-third of patients displayed unilateral PA. Patients who developed PA showed worsening of blood pressure control and a higher rate of cardiac organ damage, despite similar implementation of antihypertensive therapy, compared with patients without PA. A mild progression of autonomous aldosterone secretion was evident even in patients without confirmed PA but with relatively stable control of blood pressure levels over time.

CONCLUSIONS

About one-fifth of patients with a negative confirmatory test develop overt PA over time. A clinical follow-up of patients with a negative confirmatory test is advisable, along with the repetition of PA investigation, primarily in patients with worsening of blood pressure control.

Treating Primary Aldosteronism-Induced Hypertension: Novel Approaches and Future Outlooks

Primary aldosteronism (PA) is the most common cause of secondary hypertension and is associated with increased morbidity and mortality when compared with blood pressure-matched cases of primary hypertension. Current limitations in patient care stem from delayed recognition of the condition, limited access to key diagnostic procedures, and lack of a definitive therapy option for nonsurgical candidates. However, several recent advances have the potential to address these barriers to optimal care. From a diagnostic perspective, machine-learning algorithms have shown promise in the prediction of PA subtypes, while the development of noninvasive alternatives to adrenal vein sampling (including molecular positron emission tomography imaging) has made accurate localization of functioning adrenal nodules possible. In parallel, more selective approaches to targeting the causative aldosterone-producing adrenal adenoma/nodule (APA/APN) have emerged with the advent of partial adrenalectomy or precision ablation. Additionally, the development of novel pharmacological agents may help to mitigate off-target effects of aldosterone and improve clinical efficacy and outcomes. Here, we consider how each of these innovations might change our approach to the patient with PA, to allow more tailored investigation and treatment plans, with corresponding improvement in clinical outcomes and resource utilization, for this highly prevalent disorder.

Development of a risk-prediction model for primary aldosteronism in veterans with hypertension

BACKGROUND

Rates of screening for primary aldosteronism in patients who meet the criteria are exceedingly low (1%-3%). To help clinicians prioritize screening in patients most likely to benefit, we developed a risk-prediction model.

METHODS

Using national Veterans Health Administration data, we identified patients who met the criteria for primary aldosteronism screening between 2000 and 2019. We performed multivariable logistic regression to identify characteristics associated with positive primary aldosteronism testing before generating a risk-scoring system based on the coefficients (0< β < 0.5 = 1 pt, 0.5 ≤ β < 1 = 2 pts, 1 ≤ β < 1.5 = 3 pts) and then tested the system performance using an internal validation cohort.

RESULTS

We identified 502,190 patients who met primary aldosteronism screening criteria, of whom 1.6% were screened and 15% tested positive. Based on the regression model, we generated a risk-scoring system based on a total of 9 possible points in which age under 50, absence of smoking history, and resistant hypertension each scored 1 point; elevated serum sodium 2 points; and hypokalemia 3 points. Rates of positive screening increased with risk score, with 5.6% to 6.7% of those scoring 0 points testing positive; 7.9% to 9.0% 1 point; 8.6% to 10% 2 points; 13% to 14% 3 points; 21% 4 points; 22% to 38% 5 points; 27% to 38% 6 points; 42% to 49% 7 points; and 50% to 51% ≥8 points.

CONCLUSION

In hypertensive patients who meet the criteria for primary aldosteronism screening, rates of positive screening range from 5.6% to 51%. Use of our risk-predication model incorporating these factors can identify patients most likely to benefit from testing.

Identifying KCNJ5 Mutation in Aldosterone-Producing Adenoma Patients With Baseline Characteristics Using Machine Learning Technology

Background

Primary aldosteronism is characterized by inappropriate aldosterone production, and unilateral aldosterone-producing adenoma (uPA) is a common type of PA. KCNJ5 mutation is a protective factor in uPA; however, there is no preoperative approach to detect KCNJ5 mutation in patients with uPA.

Objectives

This study aimed to provide a personalized surgical recommendation that enables more confidence in advising patients to pursue surgical treatment.

Methods

We enrolled 328 patients with uPA harboring KCNJ5 mutations (n = 158) or not (n = 170) who had undergone adrenalectomy. Eighty-seven features were collected, including demographics, various blood and urine test results, and clinical comorbidities. We designed 2 versions of the prediction model: one for institutes with complete blood tests (full version), and the other for institutes that may not be equipped with comprehensive testing facilities (condensed version).

Results

The results show that in the full version, the Light Gradient Boosting Machine outperformed other classifiers, achieving area under the curve and accuracy values of 0.905 and 0.864, respectively. The Light Gradient Boosting Machine also showed excellent performance in the condensed version, achieving area under the curve and accuracy values of 0.867 and 0.803, respectively.

Conclusions

We simplified the preoperative diagnosis of KCNJ5 mutations successfully using machine learning. The proposed lightweight tool that requires only baseline characteristics and blood/urine test results can be widely applied and can aid personalized prediction during preoperative counseling for patients with uPA.

Approach to the Patient on Antihypertensive Therapy: Screen for Primary Aldosteronism

Primary aldosteronism (PA) is a condition that is still largely overlooked, resulting in a considerable burden of mortality and morbidity. This is despite decades of clinical and translational research on the deleterious effects of aldosterone on the cardiovascular system and the publication of several guidelines and consensuses on its diagnosis and treatment. One of the main reasons for the low rate of testing is the difficulty of screening patients on antihypertensive therapy that potentially interferes with aldosterone and renin levels and thus confound the interpretation of the aldosterone to renin ratio, the accepted and conventionally used screening test. To avoid interference, usually the therapies that affect the renin-angiotensin aldosterone system are withdrawn and substituted with noninterfering medications. However, in many cases the screening test can be confidently interpreted even when such therapies are not discontinued. In this review, we will evaluate the effects of antihypertensive therapies on the screening test for PA and suggest a practical approach for its interpretation.

Primary aldosteronism - a multidimensional syndrome

Primary aldosteronism is a common cause of hypertension and is a risk factor for cardiovascular and renal morbidity and mortality, via mechanisms mediated by both hypertension and direct insults to target organs. Despite its high prevalence and associated complications, primary aldosteronism remains largely under-recognized, with less than 2% of people in at-risk populations ever tested. Fundamental progress made over the past decade has transformed our understanding of the pathogenesis of primary aldosteronism and of its clinical phenotypes. The dichotomous paradigm of primary aldosteronism diagnosis and subtyping is being redefined into a multidimensional spectrum of disease, which spans subclinical stages to florid primary aldosteronism, and from single-focal or multifocal to diffuse aldosterone-producing areas, which can affect one or both adrenal glands. This Review discusses how redefining the primary aldosteronism syndrome as a multidimensional spectrum will affect the approach to the diagnosis and subtyping of primary aldosteronism.

[Risk factors of persistent hypertension in primary aldosteronism patients after surgery]

OBJECTIVE

To analyze the risk factors of persistent hypertension in patients who underwent adrenalectomy for primary aldosteronism and to evaluate the predictive value of the aldosteronoma resolution score (ARS) scoring system for surgical outcomes of adrenalectomy for primary aldosteronism.

METHODS

We reviewed the clinical characteristics of patients who underwent adrenalectomy for primary aldosteronism from 2018 to 2021 at Peking University People' s Hospital to recognize risk factors of uncured hypertension after surgery. Based on the patient' s clinical outcomes, the patients were divided into complete success group and partial/absent success group. Risk factors for persistent hypertension were analyzed. The value of the ARS scoring system was assessed by the area under the curve (AUC).

RESULTS

In this study, 112 patients were included. Most of the patients benefited from the surgery for 94.6% were a complete or partial clinical success after follow-up for at least 6 months. According to postoperative hypertension status, the patients were divided into complete success group (51 cases) and partial/absent success group (61 cases). There were statistical differences between the two groups in age, body mass index (BMI), waist circumference, duration of hypertension, number of preoperative antihypertension medications, preoperative systolic blood pressure, history of diabetes, history of cardiovascular and cerebrovascular diseases, serum creatinine, estimated glomerular filtration rate(eGFR), high-density lipoprotein cholesterol and triglyceride. Logistic regression analysis showed that age (OR=1.111, 95%CI: 1.029-1.199), waist circumference (OR=1.073, 95%CI: 1.013-1.137), pre-operative systolic blood pressure (OR=1.033, 95%CI: 1.008-1.060) and history of cardiovascular and cerebrovascular diseases (OR=16.061, 95%CI: 1.312-196.612) were the risk factors for uncured hypertension in primary aldosteronism patients after surgery, but female gender not. The median ARS in the complete success group was 4 and in the partial/absent success group, it was 2. Among the patients with ARS of 4-5, the cure rate of hypertension was 76.5%. The area under the curve of ARS was 0.743.

CONCLUSION

The history of cardiovascular and cerebrovascular diseases is a significant risk factor for persistent hypertension after surgery in primary aldosteronism patients. ARS scoring system has a certain value in predicting the postoperative hypertension status of primary aldosteronism patients. However, further research is still needed on a prediction model for surgical outcomes of primary aldosteronism which is more suitable for the Chinese population is still needed.

Clinical Translationality of KCNJ5 Mutation in Aldosterone Producing Adenoma

Hypertension due to primary aldosteronism poses a risk of severe cardiovascular complications compared to essential hypertension. The discovery of the KCNJ5 somatic mutation in aldosteroene producing adenoma (APA) in 2011 and the development of specific CYP11B2 antibodies in 2012 have greatly advanced our understanding of the pathophysiology of primary aldosteronism. In particular, the presence of CYP11B2-positive aldosterone-producing micronodules (APMs) in the adrenal glands of normotensive individuals and the presence of renin-independent aldosterone excess in normotensive subjects demonstrated the continuum of the pathogenesis of PA. Furthermore, among the aldosterone driver mutations which incur excessive aldosterone secretion, KCNJ5 was a major somatic mutation in APA, while CACNA1D is a leading somatic mutation in APMs and idiopathic hyperaldosteronism (IHA), suggesting a distinctive pathogenesis between APA and IHA. Although the functional detail of APMs has not been still uncovered, its impact on the pathogenesis of PA is gradually being revealed. In this review, we summarize the integrated findings regarding APA, APM or diffuse hyperplasia defined by novel CYP11B2, and aldosterone driver mutations. Following this, we discuss the clinical implications of KCNJ5 mutations to support better cardiovascular outcomes of primary aldosteronism.

Primary Aldosteronism Screening Rates Differ with Sex, Race, and Comorbidities

Background

Primary aldosteronism (PA) is a common but under‐recognized cause of secondary hypertension. Data directly comparing screening rates across single and overlapping indications are lacking.

Methods and Results

We conducted a retrospective review of adults with hypertension seen in outpatient clinics at a tertiary referral academic center between January 1, 2017, and June 30, 2020. We included patients with hypertension plus at least one of the following: resistant hypertension; age<35 years; obstructive sleep apnea; hypokalemia; or an adrenal mass. We excluded patients with adrenal insufficiency, severe renal disease, or heart failure, and renovascular hypertension. Of 203 535 patients with hypertension, 86044 (42.3%) met at least 1 PA screening criterion, and of these, 2898 (3.4%) were screened for PA. Screening occurred in 2.7% of patients with resistant hypertension; 4.2% of those with obstructive sleep apnea; 5.1% of those <35 years; 10.0% of those with hypokalemia; and 47.3% of patients with an adrenal mass. Screening rates were higher in patients with multiple risk factors: 16.8% for ≥3, 5.7% for 2, and 2.5% for 1 criterion. Multiple logistic regression showed that the odds of PA screening were higher in patients with hypokalemia: odds ratio (95% CI): 3.0 (2.7–3.3); women: 1.3 (1.2–1.4); Black versus White: 1.5 (1.4–1.7); those with obstructive sleep apnea, chronic renal disease, stroke, and dyslipidemia.

Conclusions

Consideration for PA is given in a small subset of at‐risk patients, and typically after comorbidities have developed.

Online prediction model for primary aldosteronism in patients with hypertension in Chinese population: A two-center retrospective study

BACKGROUND

The prevalence of primary aldosteronism (PA) varies from 5% to 20% in patients with hypertension but is largely underdiagnosed. Expanding screening for PA to all patients with hypertension to improve diagnostic efficiency is needed. A novel and portable prediction tool that can expand screening for PA is highly desirable.

METHODS

Clinical characteristics and laboratory data of 1,314 patients with hypertension were collected for modeling and randomly divided into a training cohort (919 of 1,314, 70%) and an internal validation cohort (395 of 1,314, 30%). Additionally, an external dataset (n = 285) was used for model validation. Machine learning algorithms were applied to develop a discriminant model. Sensitivity, specificity, and accuracy were used to evaluate the performance of the model.

RESULTS

Seven independent risk factors for predicting PA were identified, including age, sex, hypokalemia, serum sodium, serum sodium-to-potassium ratio, anion gap, and alkaline urine. The prediction model showed sufficient predictive accuracy, with area under the curve (AUC) values of 0.839 (95% CI: 0.81-0.87), 0.814 (95% CI: 0.77-0.86), and 0.839 (95% CI: 0.79-0.89) in the training set, internal validation, and external validation set, respectively. The calibration curves exhibited good agreement between the predictive risk of the model and the actual risk. An online prediction model was developed to make the model more portable to use.

CONCLUSION

The online prediction model we constructed using conventional clinical characteristics and laboratory tests is portable and reliable. This allowed it to be widely used not only in the hospital but also in community health service centers and may help to improve the diagnostic efficiency of PA.

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.