Development of a prediction score to avoid confirmatory testing in patients with suspected primary aldosteronism

2020 ◽  
Author(s):  
Jacopo Burrello ◽  
Martina Amongero ◽  
Fabrizio Buffolo ◽  
Elisa Sconfienza ◽  
Vittorio Forestiero ◽  
...  
Keyword(s):  
Machine Learning ◽  
Primary Aldosteronism ◽  
External Validation ◽  
Plasma Renin ◽  
Organ Damage ◽  
Internal Validation ◽  
Confirmatory Testing ◽  
Diagnostic Models ◽  
Confirmatory Tests ◽  
Diagnostic Work

Abstract Context The diagnostic work-up of primary aldosteronism (PA) includes screening and confirmation steps. Case confirmation is time-consuming, expensive, and there is no consensus on tests and thresholds to be used. Diagnostic algorithms to avoid confirmatory testing may be useful for the management of patients with PA. Objective Development and validation of diagnostic models to confirm or exclude PA diagnosis in patients with a positive screening test. Design, Patients and Setting We evaluated 1,024 patients who underwent confirmatory testing for PA. The diagnostic models were developed in a training cohort (n=522), and then tested on an internal validation cohort (n=174) and on an independent external prospective cohort (n=328). Main outcome measure Different diagnostic models and a 16-point score were developed by machine learning and regression analysis to discriminate patients with a confirmed diagnosis of PA. Results Male sex, antihypertensive medication, plasma renin activity, aldosterone, potassium levels and presence of organ damage were associated with a confirmed diagnosis of PA. Machine learning based models displayed an accuracy of 72.9-83.9%. The Primary Aldosteronism Confirmatory Testing (PACT) score correctly classified 84.1% at training and 83.9% or 81.1% at internal and external validation, respectively. A flow chart employing the PACT score to select patients for confirmatory testing, correctly managed all patients, and resulted in a 22.8% reduction in the number of confirmatory tests. Conclusions The integration of diagnostic modelling algorithms in clinical practice may improve the management of patients with PA by circumventing unnecessary confirmatory testing.

scholarly journals Development and Validation of Prediction Models for Subtype Diagnosis of Patients With Primary Aldosteronism

2020 ◽  
Vol 105 (10) ◽  
pp. e3706-e3717 ◽  
Author(s):  
Jacopo Burrello ◽  
Alessio Burrello ◽  
Jacopo Pieroni ◽  
Elisa Sconfienza ◽  
Vittorio Forestiero ◽  
...  
Keyword(s):  
Machine Learning ◽  
Primary Aldosteronism ◽  
Prediction Models ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Supervised Machine Learning ◽  
Internal Validation ◽  
Point Score ◽  
Diagnostic Models ◽  
Independent Cohort

Abstract Context Primary aldosteronism (PA) comprises unilateral (lateralized [LPA]) and bilateral disease (BPA). The identification of LPA is important to recommend potentially curative adrenalectomy. Adrenal venous sampling (AVS) is considered the gold standard for PA subtyping, but the procedure is available in few referral centers. Objective To develop prediction models for subtype diagnosis of PA using patient clinical and biochemical characteristics. Design, Patients and Setting Patients referred to a tertiary hypertension unit. Diagnostic algorithms were built and tested in a training (N = 150) and in an internal validation cohort (N = 65), respectively. The models were validated in an external independent cohort (N = 118). Main outcome measure Regression analyses and supervised machine learning algorithms were used to develop and validate 2 diagnostic models and a 20-point score to classify patients with PA according to subtype diagnosis. Results Six parameters were associated with a diagnosis of LPA (aldosterone at screening and after confirmatory testing, lowest potassium value, presence/absence of nodules, nodule diameter, and computed tomography results) and were included in the diagnostic models. Machine learning algorithms displayed high accuracy at training and internal validation (79.1%-93%), whereas a 20-point score reached an area under the curve of 0.896, and a sensitivity/specificity of 91.7/79.3%. An integrated flowchart correctly addressed 96.3% of patients to surgery and would have avoided AVS in 43.7% of patients. The external validation on an independent cohort confirmed a similar diagnostic performance. Conclusions Diagnostic modelling techniques can be used for subtype diagnosis and guide surgical decision in patients with PA in centers where AVS is unavailable.

scholarly journals Applications of Artificial Intelligence and Machine Learning in Diagnosis and Prognosis of COVID-19 infection: A systematic review

2021 ◽  
Vol 10 (1) ◽  
pp. 93
Author(s):  
Mahdieh Montazeri ◽  
Ali Afraz ◽  
Mitra Montazeri ◽  
Sadegh Nejatzadeh ◽  
Fatemeh Rahimi ◽  
...  
Keyword(s):  
Machine Learning ◽  
High Risk ◽  
Prediction Models ◽  
External Validation ◽  
Area Under The Curve ◽  
Risk Of Bias ◽  
Prognostic Models ◽  
Discriminative Performance ◽  
Internal Validation ◽  
Diagnostic Models

Introduction: Our aim in this study was to summarize information on the use of intelligent models for predicting and diagnosing the Coronavirus disease 2019 (COVID-19) to help early and timely diagnosis of the disease.Material and Methods: A systematic literature search included articles published until 20 April 2020 in PubMed, Web of Science, IEEE, ProQuest, Scopus, bioRxiv, and medRxiv databases. The search strategy consisted of two groups of keywords: A) Novel coronavirus, B) Machine learning. Two reviewers independently assessed original papers to determine eligibility for inclusion in this review. Studies were critically reviewed for risk of bias using prediction model risk of bias assessment tool.Results: We gathered 1650 articles through database searches. After the full-text assessment 31 articles were included. Neural networks and deep neural network variants were the most popular machine learning type. Of the five models that authors claimed were externally validated, we considered external validation only for four of them. Area under the curve (AUC) in internal validation of prognostic models varied from .94 to .97. AUC in diagnostic models varied from 0.84 to 0.99, and AUC in external validation of diagnostic models varied from 0.73 to 0.94. Our analysis finds all but two studies have a high risk of bias due to various reasons like a low number of participants and lack of external validation.Conclusion: Diagnostic and prognostic models for COVID-19 show good to excellent discriminative performance. However, these models are at high risk of bias because of various reasons like a low number of participants and lack of external validation. Future studies should address these concerns. Sharing data and experiences for the development, validation, and updating of COVID-19 related prediction models is needed. 

scholarly journals Diagnostics of primary aldosteronism: is obligatory use of confirmatory tests justified?

2012 ◽  
Vol 13 (3) ◽  
pp. 367-371 ◽  
Author(s):  
Janusz Myśliwiec ◽  
Łukasz żukowski ◽  
Anna Grodzka ◽  
Agata Piłaszewicz ◽  
Szymon Drągowski ◽  
...  
Keyword(s):  
Plasma Renin Activity ◽  
Primary Aldosteronism ◽  
Plasma Renin ◽  
Cost Effective ◽  
Plasma Aldosterone ◽  
Renin Activity ◽  
Plasma Aldosterone Concentration ◽  
Number Of Patients ◽  
Confirmatory Tests ◽  
Medical University

Introduction: Assessment of the renin-angiotensin-aldosterone system has been recently granted a much greater role in the evaluation of patients with arterial hypertension. There is no single test efficient in selection of patients for second-step etiological investigation. Methods: Altogether, 198 consecutive patients − 119 women (60%) and 79 men (40%) – hospitalized in years 2009–2011 at the Clinical Department of Endocrinology Medical University of Bialystok were diagnosed with primary aldosteronism. In each patient, plasma renin activity and plasma aldosterone concentration (basic and after 2 l NaCl infusion) were evaluated. Results: The percentage of patients with plasma aldosterone concentration ≥15 ng/ml was 53 and the percentage of patients with plasma renin activity ≤0.1 ng/ml/h was 20. The percentage of patients screened for primary aldosteronism in which the aldosterone:renin ratio exceeded consecutive cut-offs of 20, 30, 40 and 50 were respectively 57, 45, 34 and 29. Among 15 patients in which plasma aldosterone concentration after infusion of 2 l of saline was ≥6.5 ng/dl (8.6%), 13 (6.6%) were diagnosed with primary aldosteronism. Conclusion: The obligatory use of tests confirming autonomy of aldosterone secretion in patients screened for primary aldosteronism seems cost-effective in limiting the number of patients for further diagnosis.

scholarly journals Machine Learning Prediction Model for Acute Renal Failure After Acute Aortic Syndrome Surgery

2022 ◽  
Vol 8 ◽  
Author(s):  
Jinzhang Li ◽  
Ming Gong ◽  
Yashutosh Joshi ◽  
Lizhong Sun ◽  
Lianjun Huang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Renal Failure ◽  
Prediction Model ◽  
Prediction Models ◽  
External Validation ◽  
Scoring Systems ◽  
Acute Aortic Syndrome ◽  
Internal Validation ◽  
Medical Centers ◽  
Better Than

BackgroundAcute renal failure (ARF) is the most common major complication following cardiac surgery for acute aortic syndrome (AAS) and worsens the postoperative prognosis. Our aim was to establish a machine learning prediction model for ARF occurrence in AAS patients.MethodsWe included AAS patient data from nine medical centers (n = 1,637) and analyzed the incidence of ARF and the risk factors for postoperative ARF. We used data from six medical centers to compare the performance of four machine learning models and performed internal validation to identify AAS patients who developed postoperative ARF. The area under the curve (AUC) of the receiver operating characteristic (ROC) curve was used to compare the performance of the predictive models. We compared the performance of the optimal machine learning prediction model with that of traditional prediction models. Data from three medical centers were used for external validation.ResultsThe eXtreme Gradient Boosting (XGBoost) algorithm performed best in the internal validation process (AUC = 0.82), which was better than both the logistic regression (LR) prediction model (AUC = 0.77, p < 0.001) and the traditional scoring systems. Upon external validation, the XGBoost prediction model (AUC =0.81) also performed better than both the LR prediction model (AUC = 0.75, p = 0.03) and the traditional scoring systems. We created an online application based on the XGBoost prediction model.ConclusionsWe have developed a machine learning model that has better predictive performance than traditional LR prediction models as well as other existing risk scoring systems for postoperative ARF. This model can be utilized to provide early warnings when high-risk patients are found, enabling clinicians to take prompt measures.

scholarly journals Prediction of Masked Hypertension and Masked Uncontrolled Hypertension Using Machine Learning

2021 ◽  
Vol 8 ◽  
Author(s):  
Ming-Hui Hung ◽  
Ling-Chieh Shih ◽  
Yu-Ching Wang ◽  
Hsin-Bang Leu ◽  
Po-Hsun Huang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Clinical Characteristics ◽  
Prediction Models ◽  
External Validation ◽  
Uncontrolled Hypertension ◽  
Gradient Boosting ◽  
Masked Hypertension ◽  
Internal Validation ◽  
Hypertensive Patients ◽  
Extreme Gradient Boosting

Objective: This study aimed to develop machine learning-based prediction models to predict masked hypertension and masked uncontrolled hypertension using the clinical characteristics of patients at a single outpatient visit.Methods: Data were derived from two cohorts in Taiwan. The first cohort included 970 hypertensive patients recruited from six medical centers between 2004 and 2005, which were split into a training set (n = 679), a validation set (n = 146), and a test set (n = 145) for model development and internal validation. The second cohort included 416 hypertensive patients recruited from a single medical center between 2012 and 2020, which was used for external validation. We used 33 clinical characteristics as candidate variables to develop models based on logistic regression (LR), random forest (RF), eXtreme Gradient Boosting (XGboost), and artificial neural network (ANN).Results: The four models featured high sensitivity and high negative predictive value (NPV) in internal validation (sensitivity = 0.914–1.000; NPV = 0.853–1.000) and external validation (sensitivity = 0.950–1.000; NPV = 0.875–1.000). The RF, XGboost, and ANN models showed much higher area under the receiver operating characteristic curve (AUC) (0.799–0.851 in internal validation, 0.672–0.837 in external validation) than the LR model. Among the models, the RF model, composed of 6 predictor variables, had the best overall performance in both internal and external validation (AUC = 0.851 and 0.837; sensitivity = 1.000 and 1.000; specificity = 0.609 and 0.580; NPV = 1.000 and 1.000; accuracy = 0.766 and 0.721, respectively).Conclusion: An effective machine learning-based predictive model that requires data from a single clinic visit may help to identify masked hypertension and masked uncontrolled hypertension.

Development and Validation of Criteria for Sparing Confirmatory Tests in Diagnosing Primary Aldosteronism

2020 ◽  
Vol 105 (7) ◽  
pp. e2449-e2456 ◽  
Author(s):  
Kanran Wang ◽  
Jinbo Hu ◽  
Jun Yang ◽  
Ying Song ◽  
Peter J Fuller ◽  
...  
Keyword(s):  
Primary Aldosteronism ◽  
Challenge Test ◽  
Plasma Renin ◽  
Diagnostic Value ◽  
Endocrine Society ◽  
Plasma Aldosterone Concentration ◽  
Hypertensive Patients ◽  
Confirmatory Tests ◽  
Chinese Cohort ◽  
Development And Validation

Abstract Context The Endocrine Society Guidelines for the diagnosis of primary aldosteronism (PA) suggest that confirmatory tests (CFT) are not required when the following criteria are met: plasma aldosterone concentration (PAC) is >20 ng/dL, plasma renin is below detection levels, and hypokalemia is present. The evidence for the applicability of the guideline criteria is limited. Objective To develop and validate optimized criteria for sparing CFT in the diagnosis of PA. Design and Setting The optimized criteria were developed in a Chinese cohort using the captopril challenge test, verified by saline infusion test (SIT) and fludrocortisone suppression test (FST), and validated in an Australian cohort. Participants Hypertensive patients who completed PA screening and CFT. Main Outcome Measure Diagnostic value of the optimized criteria. Results In the development cohort (518 PA and 266 non-PA), hypokalemia, PAC, and plasma renin concentration (PRC) were selected as diagnostic indicators by multivariate logistic analyses. The combination of PAC >20 ng/dL plus PRC <2.5 μIU/mL plus hypokalemia had much higher sensitivity than the guideline criteria (0.36 vs 0.11). The optimized criteria remained superior when the SIT or FST were used as CFT. Non-PA patients were not misdiagnosed by either criteria, but the percentage of patients in whom CFT could be spared was higher with the optimized criteria. In the validation cohort (125 PA and 81 non-PA), the sensitivity of the optimized criteria was also significantly higher (0.12 vs 0.02). Conclusions Hypertensive patients with PAC >20 ng/dL, PRC <2.5 μIU/mL, plus hypokalemia can be confidently diagnosed with PA without confirmatory tests.

Baseline Plasma Aldosterone Level and Renin Activity Allowing Omission of Confirmatory Testing in Primary Aldosteronism

2020 ◽  
Vol 105 (5) ◽  
pp. e1990-e1998 ◽  
Author(s):  
Junji Kawashima ◽  
Eiichi Araki ◽  
Mitsuhide Naruse ◽  
Isao Kurihara ◽  
Katsutoshi Takahashi ◽  
...  
Keyword(s):  
Primary Aldosteronism ◽  
Challenge Test ◽  
Plasma Renin ◽  
Plasma Aldosterone ◽  
Renin Activity ◽  
Plasma Aldosterone Concentration ◽  
Cutoff Value ◽  
Confirmatory Testing ◽  
Cutoff Values ◽  
Number Of Patients

Abstract Context Previous studies have proposed cutoff value of baseline plasma aldosterone concentration (bPAC) under renin suppression that could diagnose primary aldosteronism (PA) without confirmatory testing. However, those studies are limited by selection bias due to a small number of patients and a single-center study design. Objective This study aimed to determine cutoff value of bPAC and baseline plasma renin activity (bPRA) for predicting positive results in confirmatory tests for PA. Design The multi-institutional, retrospective, cohort study was conducted using the PA registry in Japan (JPAS/JRAS). We compared bPAC in patients with PA who showed positive and negative captopril challenge test (CCT) or saline infusion test (SIT) results. Patients Patients with PA who underwent CCT (n = 2256) and/or SIT (n = 1184) were studied. Main outcome measures The main outcomes were cutoff value of bPAC (ng/dL) and bPRA (ng/mL/h) for predicting positive CCT and/or SIT results. Results In patients with renin suppression (bPRA ≤ 0.3), the cutoff value of bPAC that would give 100% specificity for predicting a positive SIT result was lower than that for predicting a positive CCT result (30.85 vs 56.35, respectively). Specificities of bPAC cutoff values ≥ 30.85 for predicting positive SIT and CCT results remained high (100.0% and 97.0%, respectively) in patients with bPRA ≤ 0.6. However, the specificities of bPAC cutoff values ≥ 30.85 for predicting positive SIT and CCT results decreased when patients with bPRA > 0.6 were included. Conclusion Confirmatory testing could be omitted in patients with bPAC ≥ 30.85 in the presence of bPRA ≤ 0.6.

scholarly journals Confirmatory testing in primary aldosteronism: extensive medication switching is not needed in all patients

2012 ◽  
Vol 166 (4) ◽  
pp. 679-686 ◽  
Author(s):  
Miroslav Solar ◽  
Eva Malirova ◽  
Marek Ballon ◽  
Radek Pelouch ◽  
Jiri Ceral
Keyword(s):  
Primary Aldosteronism ◽  
Aldosterone Antagonists ◽  
Confirmatory Testing ◽  
Chronic Therapy ◽  
Serum Aldosterone ◽  
Confirmatory Tests ◽  
Group A ◽  
Group B ◽  
Recommended Therapy ◽  
Test Serum

ObjectiveConfirmatory testing of suspected primary aldosteronism (PA) requires an extensive medication switch that can be difficult for patients with severe complicated hypertension and/or refractory hypokalemia. For this reason, we investigated the effect of chronic antihypertensive medication on confirmatory testing results. To allow the results to be interpreted, the reproducibility of confirmatory testing was also evaluated.Design and methodsThe study enrolled 114 individuals with suspected PA who underwent two confirmatory tests. The patients were divided into two groups. In Group A, both tests were performed on the guidelines-recommended therapy, i.e. not interfering with the renin–angiotensin–aldosterone system. In Group B, the first test was performed on chronic therapy with the exclusion of thiazides, loop diuretics, and aldosterone antagonists; and the second test was performed on guidelines-recommended therapy. Saline infusion, preceded by oral sodium loading, was used to suppress aldosterone secretion.ResultsAgreement in the interpretation of the two confirmatory tests was observed in 84 and 66% of patients in Groups A and B respectively. For all 20 individuals in Group A who ever had end-test serum aldosterone levels ≥240 pmol/l, aldosterone was concordantly nonsuppressible during the other test. Similarly, for all 16 individuals in Group B who had end-test serum aldosterone levels ≥240 pmol/l on modified chronic therapy, aldosterone remained nonsuppressible with guidelines-recommended therapy.ConclusionConfirmatory testing performed while the patient is on chronic therapy without diuretics and aldosterone antagonists can confirm the diagnosis of PA, provided serum aldosterone remains markedly elevated at the end of saline infusion.

scholarly journals Establishing Machine Learning Models to Predict Curative Resection in Early Gastric Cancer with Undifferentiated Histology: Development and Usability Study (Preprint)

2020 ◽  
Author(s):  
Chang Seok Bang ◽  
Ji Yong Ahn ◽  
Jie-Hyun Kim ◽  
Young-Il Kim ◽  
Il Ju Choi ◽  
...  
Keyword(s):  
Machine Learning ◽  
Gastric Cancer ◽  
Early Gastric Cancer ◽  
Curative Resection ◽  
External Validation ◽  
Data Set ◽  
Internal Validation ◽  
Size And Shape ◽  
Extreme Gradient Boosting ◽  
Undifferentiated Histology

BACKGROUND Undifferentiated type of early gastric cancer (U-EGC) is included among the expanded indications of endoscopic submucosal dissection (ESD); however, the rate of curative resection remains unsatisfactory. Endoscopists predict the probability of curative resection by considering the size and shape of the lesion and whether ulcers are present or not. The location of the lesion, indicating the likely technical difficulty, is also considered. OBJECTIVE The aim of this study was to establish machine learning (ML) models to better predict the possibility of curative resection in U-EGC prior to ESD. METHODS A nationwide cohort of 2703 U-EGCs treated by ESD or surgery were adopted for the training and internal validation cohorts. Separately, an independent data set of the Korean ESD registry (n=275) and an Asan medical center data set (n=127) treated by ESD were chosen for external validation. Eighteen ML classifiers were selected to establish prediction models of curative resection with the following variables: age; sex; location, size, and shape of the lesion; and whether ulcers were present or not. RESULTS Among the 18 models, the extreme gradient boosting classifier showed the best performance (internal validation accuracy 93.4%, 95% CI 90.4%-96.4%; precision 92.6%, 95% CI 89.5%-95.7%; recall 99.0%, 95% CI 97.8%-99.9%; and F1 score 95.7%, 95% CI 93.3%-98.1%). Attempts at external validation showed substantial accuracy (first external validation 81.5%, 95% CI 76.9%-86.1% and second external validation 89.8%, 95% CI 84.5%-95.1%). Lesion size was the most important feature in each explainable artificial intelligence analysis. CONCLUSIONS We established an ML model capable of accurately predicting the curative resection of U-EGC before ESD by considering the morphological and ecological characteristics of the lesions.

scholarly journals A Novel Machine Learning-Based Radiomic Model for Diagnosing High Bleeding Risk Esophageal Varices in Cirrhotic Patients

2021 ◽  
Author(s):  
Yijie Yan ◽  
Yue Li ◽  
Chunlei Fan ◽  
Yuening Zhang ◽  
Shibin Zhang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Sensitivity And Specificity ◽  
Esophageal Varices ◽  
External Validation ◽  
Bleeding Risk ◽  
Internal Validation ◽  
Portal Venous Phase ◽  
Net Reclassification Improvement ◽  
Cirrhotic Patients ◽  
High Bleeding Risk

Abstract Background & aims: To develop and validate a novel machine learning-based radiomic model (RM) for diagnosing high bleeding risk esophageal varices (HREV) in cirrhosis. Methods: In training cohort, total 218 cirrhotic patients for mild esophageal varices (EV) and 240 for HREV RM were enrolled for training and internal validation. In external validation cohort, 159 and 340 cirrhotic patients were respectively used for mild EV and HREV RM validation. Interesting regions of liver, spleen, and esophagus were labeled on the portal venous-phase enhanced CT images. RM was assessed by area under the receiver operating characteristic curves (AUROC), sensitivity, specificity, calibration and decision curve analysis (DCA). Results: The AUROC of mild EV RM in training and internal validation was 0.943 and 0.732, sensitivity and specificity was 0.863, 0.773 and 0.763, 0.763. The AUROC, sensitivity and specificity was 0.654, 0.773 and 0.632 in external validation. Interestingly, the AUROC of HREV RM in training and internal validation was 0.983 and 0.834, sensitivity and specificity was 0.948, 0.916 and 0.977, 0.969. The AUROC, sensitivity and specificity was 0.736, 0.690 and 0.762 in external validation. Calibration and DCA indicated RM had good performance in clinical practice. Compared with Baveno VI and its expanded criteria, HREV RM had a higher accuracy and net reclassification improvement reached 49.0% and 32.8%. Conclusion: A novel non-invasive RM for diagnosing HREV in cirrhotic patients with highly accuracy was developed. However, this RM still needs to be validated by a multi-center large cohort.

Sign in / Sign up

Export Citation Format

Share Document