Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet #Preprint #PeerReviewMe: Warning: This is a unreviewed preprint. Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn. Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period. Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author). Background: Since medical research based on big data has become more common, community’s interest and effort to analyze a large amount of semi-structured or unstructured text data, such as examination reports, has rapidly increased. However, these large-scale text data are often not readily applicable to analysis due to typographical errors, inconsistencies, or data entry problems. Therefore, an efficient data cleaning process is required to ensure the veracity of such data. Objective: We propose an efficient data cleaning process for large-scale medical text data, which employs text clustering methods and value-converting technique to evaluate its performance with medical examination text data. Methods: The proposed data cleaning process consists of text clustering and value-merging. In the text clustering step, we suggest to use key collision and nearest neighbor methods in a complementary manner. Words (called as values) in the same cluster would be expected as a correct value and its wrong representations. In the value-converting step, wrong values for each identified cluster would be converted into their correct value. We applied this data cleaning process to 574,266 stool examination reports produced for parasite analysis at Samsung Medical Center from 1995 to 2015. The performance of the proposed process was examined and compared with data cleaning processes based on a single clustering method. We used OpenRefine 2.7, an open source application that provides various text clustering methods and an efficient user interface for value-converting with common-value suggestion. Results: A total of 1,167,104 words in stool examination reports were surveyed. In the data cleaning process, we discovered 30 correct words and 45 typographical errors in parasite names. We observed high correction rate in the number of typographical errors for words (98.61%) and typographical errors for parasite names (97.78%). The resulting data accuracy was nearly 100% based on the number of total words. Conclusions: Our data cleaning process based on the combinatorial use of key collision and nearest neighbor methods provides an efficient cleaning of large-scale text data, and hence improves data accuracy.

Background: We hypothesized that analysis of serial ECGs could predict new‐onset atrial fibrillation (AF) more accurately than analysis of a single ECG by detecting the subtle cardiac remodeling that occurs immediately before AF occurrence. Our aim in this study was to compare the performance of 2 types of machine learning (ML) algorithms. Methods and Results: Standard 12‐lead ECGs of patients selected by cardiologists between January 2010 and May 2021 were used for ML model development. Two ML models (single ECG and serial ECG) were developed using a light gradient boosting machine‐learning algorithm. Model performance was evaluated based on the area under the receiver operating characteristic curve, sensitivity, specificity, accuracy, and F1 score. We trained the ML models on 415 964 ECGs from 176 090 patients. When testing the 2 ML models using external validation data sets, the performance of the serial‐ML model was significantly better than that of the single‐ML model for predicting new‐onset AF (single‐ versus serial‐ML model: sensitivity 0.744 versus 0.810; specificity 0.742 versus 0.822; accuracy 0.743 versus 0.816; F1 score 0.743 versus 0.815; area under the receiver operating characteristic curve 0.812 versus 0.880; P <0.001). The Shapley Additive Explanations analysis ranked P‐wave duration and amplitude among the top 10 ECG parameters. Conclusions: An ML model based on serial ECGs from an individual had greater ability to predict new‐onset AF than the ML model based on a single ECG. P‐wave morphologies were associated with future AF prediction.

This study developed and validated multivariable quantitative ultrasound (QUS) model for diagnosing hepatic steatosis. Retrospective secondary analysis of prospectively collected QUS data was performed. Participants underwent QUS examinations and magnetic resonance imaging proton density fat fraction (MRI-PDFF; reference standard). A multivariable regression model for estimating hepatic fat fraction was determined using two QUS parameters from one tertiary hospital (development set). Correlation between QUS-derived estimated fat fraction(USFF) and MRI-PDFF and diagnostic performance of USFF for hepatic steatosis (MRI-PDFF ≥ 5%) were assessed, and validated in an independent data set from the other health screening center(validation set). Development set included 173 participants with suspected NAFLD with 126 (72.8%) having hepatic steatosis; and validation set included 452 health screening participants with 237 (52.4%) having hepatic steatosis. USFF was correlated with MRI-PDFF (Pearson r = 0.799 and 0.824; development and validation set). The model demonstrated high diagnostic performance, with areas under the receiver operating characteristic curves of 0.943 and 0.924 for development and validation set, respectively. Using cutoff of 6.0% from development set, USFF showed sensitivity, specificity, positive predictive value, and negative predictive value of 87.8%, 78.6%, 81.9%, and 85.4% for diagnosing hepatic steatosis in validation set. In conclusion, multivariable QUS parameters-derived estimated fat fraction showed high diagnostic performance for detecting hepatic steatosis.

Purpose: This study compared the diagnostic performance of quantitative ultrasonography (QUS) with that of conventional ultrasonography (US) in assessing hepatic steatosis among individuals undergoing health screening using magnetic resonance imaging–derived proton density fat fraction (MRI-PDFF) as the reference standard.Methods: This single-center prospective study enrolled 427 participants who underwent abdominal MRI and US. Measurements included the attenuation coefficient in tissue attenuation imaging (TAI) and the scatter-distribution coefficient in tissue scatter-distribution imaging (TSI). The correlation between QUS and MRI-PDFF was evaluated. The diagnostic capabilities of QUS, conventional B-mode US, and their combined models for detecting hepatic fat content of ≥5% (MRI-PDFF ≥5%) and ≥10% (MRI-PDFF ≥10%) were compared by analyzing the areas under the receiver operating characteristic curves. Additionally, clinical risk factors influencing the diagnostic performance of QUS were identified using multivariate linear regression analyses.Results: TAI and TSI were strongly correlated with MRI-PDFF (r=0.759 and r=0.802, respectively; both P<0.001) and demonstrated good diagnostic performance in detecting and grading hepatic steatosis. The combination of QUS and B-mode US resulted in the highest areas under the ROC curve (AUCs) (0.947 and 0.975 for detecting hepatic fat content of ≥5% and ≥10%, respectively; both P<0.05), compared to TAI, TSI, or B-mode US alone (AUCs: 0.887, 0.910, 0.878 for ≥5% and 0.951, 0.922, 0.875 for ≥10%, respectively). The independent determinants of QUS included skinliver capsule distance (β=7.134), hepatic fibrosis (β=4.808), alanine aminotransferase (β=0.202), triglyceride levels (β=0.027), and diabetes mellitus (β=3.710).Conclusion: QUS is a useful and effective screening tool for detecting and grading hepatic steatosis during health checkups.

The relationship between coronary artery calcium (CAC) and progression of diastolic dysfunction (DD) during longitudinal follow-up is uncertain. This study aimed to investigate the prevalence and progression of DD according to severity of CAC and understand their synergistic effect on mortality. This was a population-based cohort study. All 15,193 adults who underwent a health screening exam with simultaneous echocardiography and CAC scan were enrolled. Definite DD (≥ 3/4 abnormal parameters for DD [e′, E/e′, tricuspid regurgitation velocity, and left atrial volume index]) and definite or probable DD (≥ 2/4) were defined. All-cause mortality was assessed based on the CAC and DD. Among the population, 7995 participants (52.6%) had CAC = 0; 4661 (30.7%) had 0 < CAC < 100; and 2537 (16.7%) had CAC ≥ 100. The prevalence ratios for definite (adjusted ratio: 1.72, 95% CI: 1.23–2.22) and definite or probable DD (adjusted ratio: 1.83, 95% CI: 1.31–2.36) were significantly higher in individuals with CAC ≥ 100 than in those with CAC = 0. There was significant linear association of CAC with E/e′ (adjusted p for linearity = 0.001). Compared with CAC < 100 without definite DD, the adjusted HRs with 95% CI for mortality of CAC ≥ 100 without definite DD, CAC < 100 with definite DD, and CAC ≥ 100 with definite DD were 2.56 (95% CI: 1.67–3.94), 3.08 (95% CI: 1.28–7.39), and 3.91 (95% CI: 1.68–9.10). Among participants without DD at CAC measurement who had at least two echocardiographic measurements, the presence of significant CAC (≥ 100) was significantly associated with accelerated progression in definite DD over time (adjusted HR: 1.46, 95% CI: 1.13–1.88), with more rapid elevation of E/e′ during follow-up (difference: 0.06, 95% CI: 0.02–0.10, p = 0.003). In the general population, there was a significant relationship between CAC and prevalence of DD, and both subclinical parameters were associated with increased mortality. Moreover, CAC ≥ 100 significantly affects the progression of DD independently of other clinical factors.