Authorship：Lead author   Language：English   Publishing type：Research paper (scientific journal)  

In the field of medicine, evaluating the diagnostic performance of new diagnostic methods can be challenging, especially in the absence of a gold standard. This study proposes a methodology for assessing the performance of diagnostic tests by estimating the posterior distribution of the F1 score using latent class analysis, without relying on a gold standard. The proposed method utilizes Markov Chain Monte Carlo sampling to estimate the posterior distribution of the F1 score, enabling a comprehensive evaluation of diagnostic test methods. By applying this method to internet addiction, we demonstrate how latent class analysis can be effectively used to assess diagnostic performance, offering a practical solution for situations where no gold standard is available. The effectiveness of the proposed approach was evaluated through simulation studies by examining the coverage probability of the 95% highest density interval of the estimated posterior distributions.

DOI： 10.1080/10543406.2025.2450319

PubMed

researchmap

Language：English   Publishing type：Research paper (scientific journal)  

Evaluating classifications is crucial in statistics and machine learning, as it influences decision-making across various fields, such as patient prognosis and therapy in critical conditions. The Matthews correlation coefficient (MCC), also known as the phi coefficient, is recognized as a performance metric with high reliability, offering a balanced measurement even in the presence of class imbalances. Despite its importance, there remains a notable lack of comprehensive research on the statistical inference of MCC. This deficiency often leads to studies merely validating and comparing MCC point estimates-a practice that, while common, overlooks the statistical significance and reliability of results. Addressing this research gap, our paper introduces and evaluates several methods to construct asymptotic confidence intervals for the single MCC and the differences between MCCs in paired designs. Through simulations across various scenarios, we evaluate the finite-sample behavior of these methods and compare their performances. Furthermore, through real data analysis, we illustrate the potential utility of our findings in comparing binary classifiers, highlighting the possible contributions of our research in this field.

DOI： 10.1002/sim.10303

PubMed

researchmap

Language：English   Publishing type：Research paper (scientific journal)  

BACKGROUND: The efficacy and safety of conversion surgery (CS) after FOLFIRINOX or gemcitabine plus nab-paclitaxel (GnP) chemotherapy in patients with initially unresectable pancreatic cancer (PC) remains unclear. METHODS: This multicenter retrospective cohort study enrolled patients, between 2014 and 2018, with initially locally advanced or metastatic PC who were considered candidates for CS following FOLFIRINOX or GnP chemotherapy. They were classified into surgery (207 patients [194 resection and 13 exploratory laparotomy only]) and continued chemotherapy (10 patients, control) groups. The primary endpoint was overall survival (OS) from the day of diagnosis of potentially curative resection on imaging studies, with an expected hazard ratio (HR) of 0.7. RESULTS: OS in the surgery group was longer than that in the control group (HR, 0.47; 95% confidence interval [CI]: 0.24-0.93). The median OS was 34.4 (95% CI: 27.9-43.4) and 19.8 (95% CI: 14.9-31.1) months in the surgery and control groups, respectively. The Clavien-Dindo grade ≥ IIIa postoperative complication and in-hospital mortality rates were 19.6% and 0.5%, respectively. Multivariate analysis revealed that preoperative chemotherapy duration was not associated with OS. CONCLUSIONS: CS, following a favorable response to FOLFIRINOX or GnP chemotherapy, improved initially unresectable PC prognosis (specifically, OS), regardless of the chemotherapy duration.

DOI： 10.1002/jhbp.12066

PubMed

researchmap

Language：English   Publishing type：Research paper (scientific journal)  

BACKGROUND: Anti-SS-A/Ro antibody (anti-SSA), the diagnostic marker of Sjögren's syndrome (SS), is often detected in systemic sclerosis (SSc). Some patients are diagnosed with SSc/SS overlap syndromes, while there are anti-SSA-positive SSc cases without SS. In this study, we investigated the clinical characteristics of SSc with anti-SSA and clarified the clinical impact of this antibody in SSc. METHODS: A retrospective chart review was conducted of 156 patients with SSc at Yokohama City University Hospital from 2018 to 2021. Clinical data, laboratory data, imaging, and autoantibody positivity status were collected and analysed to assess the association between these variables and anti-SSA using multivariable logistic regression analysis. RESULTS: This cohort included 18 men and 138 women with SSc (median age, 69.0 years). Thirty-nine patients had diffuse cutaneous SSc (dcSSc) (25%), and 117 patients had limited cutaneous SSc (75%). Forty-four patients were anti-SSA-positive. Among them, 24 fulfilled the SS criteria. Multivariable logistic regression revealed that anti-SSA was statistically associated with interstitial lung disease (ILD; odds ratio [OR] = 2.67; 95% confidence interval [CI], 1.14-6.3; P = 0.024). Meanwhile, anti-SSA positivity tended to increase the development of digital ulcer (OR = 2.18; 95% CI, 0.99-4.82, P = 0.054). In the comparative analysis of the autoantibody single-positive and anti-SSA/SSc-specific autoantibody double-positive groups, the anti-SSA single-positive group showed a significantly increased risk of ILD (OR = 12.1; 95% CI, 2.13-140.57; P = 0.003). Furthermore, patients with SSc and anti-SSA indicated that anti-SSA-positive SSc without SS was strongly associated with dcSSc when compared to that in patients with SS (OR = 6.45; 95% CI, 1.23-32.60; P = 0.024). CONCLUSIONS: Anti-SSA positivity increases the risk of organ involvement, such as ILD, in patients with SSc. Additionally, the anti-SSA-positive SSc without SS population may have more severe skin fibrosis than others. Anti-SSA may be a potential marker of ILD and skin severity in SSc.

DOI： 10.1186/s13075-024-03325-6

PubMed

researchmap

Language：English   Publishing type：Research paper (scientific journal)  

INTRODUCTION: Three randomized controlled trials have resulted in extremely extensive application of the strategy of using neoadjuvant chemotherapy (NAC) followed by interval debulking surgery (IDS) for patients with advanced epithelial ovarian cancer in Japan. This study aimed to evaluate the status and effectiveness of treatment strategies using NAC followed by IDS in Japanese clinical practice. PATIENTS AND METHODS: We conducted a multi-institutional observational study of 940 women with Federation of Gynecology and Obstetrics (FIGO) stages III-IV epithelial ovarian cancer treated at one of nine centers between 2010 and 2015. Progression-free survival (PFS) and overall survival (OS) were compared between 486 propensity-score matched participants who underwent NAC followed by IDS and primary debulking surgery (PDS) followed by adjuvant chemotherapy. RESULTS: Patients with FIGO stage IIIC receiving NAC had a shorter OS (median OS: 48.1 vs. 68.2 months, hazard ratio [HR]: 1.34; 95% confidence interval [CI] 0.99-1.82, p = 0.06) but not PFS (median PFS: 19.7 vs. 19.4 months, HR: 1.02; 95% CI: 0.80-1.31, p = 0.88). However, patients with FIGO stage IV receiving NAC and PDS had comparable PFS (median PFS: 16.6 vs. 14.7 months, HR: 1.07 95% CI: 0.74-1.53, p = 0.73) and OS (median PFS: 45.2 vs. 35.7 months, HR: 0.98; 95% CI: 0.65-1.47, p = 0.93). CONCLUSIONS: NAC followed by IDS did not improve survival. In patients with FIGO stage IIIC, NAC may be associated with a shorter OS.

DOI： 10.1007/s10147-023-02329-7

PubMed

researchmap

In the analysis of square contingency tables with ordered categories, it is
essential to assess deviations from marginal homogeneity (MH) when marginal
equivalency between row and column variables does not hold. Some measures for
evaluating the degree of departure from the MH model have been proposed. This
study proposes a new directional measure using the discrete-time hazard,
assuming that categories represent discrete time points. The proposed measure
is capable of capturing both the magnitude and direction of deviation from the
MH model. It is defined on a continuous scale from $-1$ to $1$, which allows
for intuitive interpretation of the nature of marginal change.
An estimator of the proposed measure and an asymptotic confidence interval
are derived using the delta method. The theoretical properties of the measure
are also discussed. The proposed measure provides a flexible tool for
characterizing marginal inhomogeneity in square contingency tables under
ordinal settings.

arXiv

researchmap

Other Link： http://arxiv.org/pdf/2504.18100v1

Classification problems are essential statistical tasks that form the
foundation of decision-making across various fields, including patient
prognosis and treatment strategies for critical conditions. Consequently,
evaluating the performance of classification models is of significant
importance, and numerous evaluation metrics have been proposed. Among these,
the Matthews correlation coefficient (MCC), also known as the phi coefficient,
is widely recognized as a reliable metric that provides balanced measurements
even in the presence of class imbalance. However, with the increasing
prevalence of multiclass classification problems involving three or more
classes, macro-averaged and micro-averaged extensions of MCC have been
employed, despite a lack of clear definitions or established references for
these extensions. In the present study, we propose a formal framework for MCC
tailored to multiclass classification problems using macro-averaged and
micro-averaged approaches. Moreover, discussions on the use of these extended
MCCs for multiclass problems often rely solely on point estimates, potentially
overlooking the statistical significance and reliability of the results. To
address this gap, we introduce several methods for constructing asymptotic
confidence intervals for the proposed metrics. Furthermore, we extend these
methods to include the construction of asymptotic confidence intervals for
differences in the proposed metrics, specifically for paired study designs. The
utility of our methods is evaluated through comprehensive simulations and
real-world data analyses.

arXiv

researchmap

Other Link： http://arxiv.org/pdf/2503.06450v1

researchmap

researchmap

researchmap

researchmap

researchmap

researchmap