Shuji Ando
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Shuji Ando has a total of 41 co-authors. Here are the top co-authors by number of shared publications:
Sadao Tomizawa
Department of Information Science Meisei University Tokyo Japan
4 shared publications- Sadao Tomizawa
Department of Information Science, Meisei University, Hino City, Japan
4 shared publications - Tomotaka Momozaki
Department of Information Sciences, Faculty of Science and Technology Tokyo University of Science Chiba Japan
3 shared publications Akihito Inatsu
Division of Nephrology, Kisen Hospital, Tokyo, Japan
2 shared publicationsAkimi Uehata
Division of Cardiology, Kisen Hospital, Tokyo, Japan
2 shared publicationsHideki Hisadome
Division of Cardiology, Kisen Hospital, Tokyo, Japan
2 shared publications
Latest Publications
- Open Access
- 10 November 2026
- Published by Walter de Gruyter GmbH in Biometrical Letters
A contrast-ratio representation of directional departure from marginal mean equality in ordinal square contingency tables
Summary: For ordinal square contingency tables with equally spaced category scores, we give an explicit contrast-ratio representation of the angular measure of departure from marginal mean equality introduced by Ando (2024). The bounded contrast D and the angular measure Ψ satisfy Ψ = (4 /π ) arctan( D ) and therefore contain the same directional information. Ratio and half-log-ratio identities clarify the interpretation of the aggregated cumulative marginal quantities. A ratio-of-means formulation gives a compact asymptotic variance and two simple confidence intervals: a naive Wald interval and an atanh-transformed Wald interval. The transformed interval respects the parameter range whenever defined, but is unavailable at boundary estimates. Simulations examine departures at a fixed denominator and null scenarios with smaller denominators; performance for non-null departures combined with a small denominator is not established. Paired insomnia data illustrate reporting on equivalent scales and the coding-dependent interpretation of between-group comparisons. The contribution is improved representation, interpretation, and formulation of large-sample inference, rather than additional information or a general finite-sample guarantee.
- 10 November 2026
- Published by Walter de Gruyter GmbH in Biometrical Letters
Open AccessA contrast-ratio representation of directional departure from marginal mean equality in ordinal square contingency tables
Summary: For ordinal square contingency tables with equally spaced category scores, we give an explicit contrast-ratio representation of the angular measure of departure from marginal mean equality introduced by Ando (2024). The bounded contrast D and the angular measure Ψ satisfy Ψ = (4 /π ) arctan( D ) and therefore contain the same directional information. Ratio and half-log-ratio identities clarify the interpretation of the aggregated cumulative marginal quantities. A ratio-of-means formulation gives a compact asymptotic variance and two simple confidence intervals: a naive Wald interval and an atanh-transformed Wald interval. The transformed interval respects the parameter range whenever defined, but is unavailable at boundary estimates. Simulations examine departures at a fixed denominator and null scenarios with smaller denominators; performance for non-null departures combined with a small denominator is not established. Paired insomnia data illustrate reporting on equivalent scales and the coding-dependent interpretation of between-group comparisons. The contribution is improved representation, interpretation, and formulation of large-sample inference, rather than additional information or a general finite-sample guarantee.
- Open Access
- 3 November 2026
- Published by Elsevier in Statistics & Probability Letters
- Vol. 242
Exact likelihood-ratio additivity for ordinal quasi-symmetry models in square contingency tables
- 3 November 2026
- Published by Elsevier in Statistics & Probability Letters
- Vol. 242
Open AccessExact likelihood-ratio additivity for ordinal quasi-symmetry models in square contingency tables
- Open Access
- 1 June 2026
- Published by Institute of Mathematical Statistics in Brazilian Journal of Probability and Statistics
- Vol. 40 (2) , 186-202
Two-dimensional index for measuring deviance from quasi-symmetry corresponding to conditional quasi-symmetry for ordinal square contingency tables
This study proposes a two-dimensional index for measuring the degree of deviance from the quasi-symmetry (QS) model corresponding to the conditional QS (CQS) model for ordinal square contingency tables. The CQS model indicates the structure of asymmetry for the local odds ratios. Previous study proposed a two-dimensional index for measuring the degree of deviance from the QS model corresponding to the extended QS (EQS) which has a different probability structure from the CQS model. The asymmetry parameters of the CQS and EQS models indicate both the degree and direction of deviance from the QS model. When the CQS (or EQS) model does not fit for the presented data well, we cannot evaluate them using the asymmetry parameter. The two-dimensional index can address this issue. The proposed two-dimensional index is assembled by combining two new sub-indexes. One represents the degree of deviance from the QS model corresponding to the CQS model, and the other represents its direction. Additionally, this study derives a plug-in estimator and an approximate confidence region for the proposed two-dimensional index. For comparing several datasets, we reveal that the magnitude relationship between the degrees of deviance from the QS model changes by whether the proposed or existing two-dimensional index is used.
- 1 June 2026
- Published by Institute of Mathematical Statistics in Brazilian Journal of Probability and Statistics
- Vol. 40 (2) , 186-202
Open AccessTwo-dimensional index for measuring deviance from quasi-symmetry corresponding to conditional quasi-symmetry for ordinal square contingency tables
This study proposes a two-dimensional index for measuring the degree of deviance from the quasi-symmetry (QS) model corresponding to the conditional QS (CQS) model for ordinal square contingency tables. The CQS model indicates the structure of asymmetry for the local odds ratios. Previous study proposed a two-dimensional index for measuring the degree of deviance from the QS model corresponding to the extended QS (EQS) which has a different probability structure from the CQS model. The asymmetry parameters of the CQS and EQS models indicate both the degree and direction of deviance from the QS model. When the CQS (or EQS) model does not fit for the presented data well, we cannot evaluate them using the asymmetry parameter. The two-dimensional index can address this issue. The proposed two-dimensional index is assembled by combining two new sub-indexes. One represents the degree of deviance from the QS model corresponding to the CQS model, and the other represents its direction. Additionally, this study derives a plug-in estimator and an approximate confidence region for the proposed two-dimensional index. For comparing several datasets, we reveal that the magnitude relationship between the degrees of deviance from the QS model changes by whether the proposed or existing two-dimensional index is used.
- Open Access
- 16 March 2026
- Published by Wiley in Statistics in Medicine
- Vol. 45 (6-7) , e70491
On Window Mean Survival Time With Interval‐Censored Data
In recent years, cancer clinical trials have increasingly encountered non proportional hazards (NPH) scenarios, particularly with the emergence of immunotherapy. In randomized controlled trials comparing immunotherapy with conventional chemotherapy or placebo, late difference and early crossing survival curves scenarios are commonly observed. In such cases, window mean survival time (WMST), the area under the survival curve within a pre-specified interval , has gained increasing attention due to its superior power compared to restricted mean survival time (RMST), the area under the survival curve up to a pre-specified time point. Considering the increasing use of progression-free survival as a co-primary endpoint alongside overall survival, there is a critical need to establish a WMST estimation method for interval-censored data; however, sufficient research has yet to be conducted. To bridge this gap, this study proposes a WMST inference method utilizing one-point imputations and Turnbull's method. Extensive numerical simulations demonstrate that the WMST estimation method using mid-point imputation for interval-censored data exhibits comparable performance to that using Turnbull's method. Since the former facilitates standard error calculation, we adopt it as the standard method. Numerical simulations on two-sample tests confirm that the proposed WMST testing method have higher power than RMST in late difference and early crossing survival curves scenarios, while having compatible power to the log-rank test under the PH. Furthermore, even when pre-specified deviated from the clinically desirable time point, WMST consistently maintains higher power than RMST in late difference and early crossing survival curves scenarios.- 16 March 2026
- Published by Wiley in Statistics in Medicine
- Vol. 45 (6-7) , e70491
Open AccessOn Window Mean Survival Time With Interval‐Censored Data
In recent years, cancer clinical trials have increasingly encountered non proportional hazards (NPH) scenarios, particularly with the emergence of immunotherapy. In randomized controlled trials comparing immunotherapy with conventional chemotherapy or placebo, late difference and early crossing survival curves scenarios are commonly observed. In such cases, window mean survival time (WMST), the area under the survival curve within a pre-specified interval , has gained increasing attention due to its superior power compared to restricted mean survival time (RMST), the area under the survival curve up to a pre-specified time point. Considering the increasing use of progression-free survival as a co-primary endpoint alongside overall survival, there is a critical need to establish a WMST estimation method for interval-censored data; however, sufficient research has yet to be conducted. To bridge this gap, this study proposes a WMST inference method utilizing one-point imputations and Turnbull's method. Extensive numerical simulations demonstrate that the WMST estimation method using mid-point imputation for interval-censored data exhibits comparable performance to that using Turnbull's method. Since the former facilitates standard error calculation, we adopt it as the standard method. Numerical simulations on two-sample tests confirm that the proposed WMST testing method have higher power than RMST in late difference and early crossing survival curves scenarios, while having compatible power to the log-rank test under the PH. Furthermore, even when pre-specified deviated from the clinically desirable time point, WMST consistently maintains higher power than RMST in late difference and early crossing survival curves scenarios. - Open Access
- 5 November 2025
- Published by New York Business Global LLC in European Journal of Pure and Applied Mathematics
- Vol. 18 (4) , 6439
Anti-Linear-Diagonals-Parameter Symmetry Model and Orthogonal Decomposition of Anti-Symmetry for Square Contingency Tables with Ordinal Classifications
For $R \times R$ square contingency tables with the same ordinal classifications for rows and columns, this study investigates models in which the relationship between the row and column variables is symmetric or asymmetric with respect to the anti-diagonal, rather than the main diagonal. The recently proposed anti-diagonals-parameter symmetry model includes $R - 1$ asymmetric parameters and is capable of representing complex asymmetric structures. However, this model is saturated in the following cells: the cell in the first row and first column, the cell in the $R$th row and $R$th column, and all anti-diagonal cells. Since observed frequencies in square contingency tables tend to concentrate along the main diagonal, a model saturated only in the anti-diagonal cells may be more appropriate. We propose the anti-linear diagonals-parameter symmetry model, which captures asymmetry with respect to the anti-diagonal. The proposed model is saturated solely in the anti-diagonal cells and, like the anti-diagonals-parameter symmetry model, expresses how the degree of asymmetry varies according to the distance from the anti-diagonal. Furthermore, we demonstrate a decomposition of the anti-symmetry model using the proposed model and derive an orthogonal decomposition of the test statistic for the anti-symmetry model.- 5 November 2025
- Published by New York Business Global LLC in European Journal of Pure and Applied Mathematics
- Vol. 18 (4) , 6439
Open AccessAnti-Linear-Diagonals-Parameter Symmetry Model and Orthogonal Decomposition of Anti-Symmetry for Square Contingency Tables with Ordinal Classifications
For $R \times R$ square contingency tables with the same ordinal classifications for rows and columns, this study investigates models in which the relationship between the row and column variables is symmetric or asymmetric with respect to the anti-diagonal, rather than the main diagonal. The recently proposed anti-diagonals-parameter symmetry model includes $R - 1$ asymmetric parameters and is capable of representing complex asymmetric structures. However, this model is saturated in the following cells: the cell in the first row and first column, the cell in the $R$th row and $R$th column, and all anti-diagonal cells. Since observed frequencies in square contingency tables tend to concentrate along the main diagonal, a model saturated only in the anti-diagonal cells may be more appropriate. We propose the anti-linear diagonals-parameter symmetry model, which captures asymmetry with respect to the anti-diagonal. The proposed model is saturated solely in the anti-diagonal cells and, like the anti-diagonals-parameter symmetry model, expresses how the degree of asymmetry varies according to the distance from the anti-diagonal. Furthermore, we demonstrate a decomposition of the anti-symmetry model using the proposed model and derive an orthogonal decomposition of the test statistic for the anti-symmetry model. - Open Access
- 25 October 2025
- Published by Wiley in Pharmaceutical Statistics
- Vol. 24 (6) , e70046
Improving Maximum Tolerated Dose Selection in Model‐Assisted Designs for Phase I Trials Through Bayesian Dose–Response Model
Model‐assisted designs have garnered significant attention in recent years due to their high accuracy in identifying the maximum tolerated dose (MTD) and their operational simplicity. To identify the MTD, they employ estimated dose limiting toxicity (DLT) probabilities via isotonic regression with pool‐adjacent violators algorithm (PAVA) after trials have been completed. PAVA adjusts independently estimated DLT probabilities with the Bayesian binomial model at each dose level using posterior variances ensure the monotonicity that toxicity increases with dose. However, in small sample settings such as Phase I oncology trials, this approach can lead to unstable DLT probability estimates and reduce MTD selection accuracy. To address this problem, we propose a novel MTD identification strategy in model‐assisted designs that leverages a Bayesian dose–response model. Employing the dose–response model allows for stable estimation of the DLT probabilities under the monotonicity by borrowing information across dose levels, leading to an improvement in MTD identification accuracy. We discuss the specification of prior distributions that can incorporate information from similar trials or the absence of such information. We examine dose–response models employing logit, log–log, and complementary log–log link functions to assess the impact of link function differences on the accuracy of MTD selection. Through extensive simulations, we demonstrate that the proposed approach improves MTD selection accuracy by more than 10% in some scenarios and by approximately 6% on average compared to conventional approach. These findings indicate that the proposed approach can contribute to further enhancing the efficiency of Phase I oncology trials.
- 25 October 2025
- Published by Wiley in Pharmaceutical Statistics
- Vol. 24 (6) , e70046
Open AccessImproving Maximum Tolerated Dose Selection in Model‐Assisted Designs for Phase I Trials Through Bayesian Dose–Response Model
Model‐assisted designs have garnered significant attention in recent years due to their high accuracy in identifying the maximum tolerated dose (MTD) and their operational simplicity. To identify the MTD, they employ estimated dose limiting toxicity (DLT) probabilities via isotonic regression with pool‐adjacent violators algorithm (PAVA) after trials have been completed. PAVA adjusts independently estimated DLT probabilities with the Bayesian binomial model at each dose level using posterior variances ensure the monotonicity that toxicity increases with dose. However, in small sample settings such as Phase I oncology trials, this approach can lead to unstable DLT probability estimates and reduce MTD selection accuracy. To address this problem, we propose a novel MTD identification strategy in model‐assisted designs that leverages a Bayesian dose–response model. Employing the dose–response model allows for stable estimation of the DLT probabilities under the monotonicity by borrowing information across dose levels, leading to an improvement in MTD identification accuracy. We discuss the specification of prior distributions that can incorporate information from similar trials or the absence of such information. We examine dose–response models employing logit, log–log, and complementary log–log link functions to assess the impact of link function differences on the accuracy of MTD selection. Through extensive simulations, we demonstrate that the proposed approach improves MTD selection accuracy by more than 10% in some scenarios and by approximately 6% on average compared to conventional approach. These findings indicate that the proposed approach can contribute to further enhancing the efficiency of Phase I oncology trials.
- Open Access
- 21 July 2025
- Published by Springer Nature in Journal of the Korean Statistical Society
- Vol. 54 (4) , 1251-1268
A directional index to measure the degree of asymmetry for square contingency tables
In the analysis of square contingency tables, wherein the row and column variables are composed of the same ordered categories, researchers typically seek to ascertain whether the row and column variables are symmetrical. The degree of asymmetry (i.e., degree of departure from symmetry) between the row and column variables is measured using the index based on Kullback–Leibler divergence. This index value of 1 indicates a perfect upper asymmetry (namely, the cell probabilities in the lower triangle of the table, excluding the diagonal elements, are all zero) or a perfect lower asymmetry (namely, the cell probabilities in the upper triangle of the table, excluding the diagonal elements, are all zero). Consequently, this index cannot discriminate between these two types of asymmetries. The objective of the present paper is to propose a new directional index to discriminate between perfect lower and upper asymmetries. An asymptotically unbiased estimator and an approximate confidence interval for the proposed index are given. We evaluate the performances of those in a finite sample through numerical experiments. The usefulness of the proposed index is demonstrated though real data analysis.
- 21 July 2025
- Published by Springer Nature in Journal of the Korean Statistical Society
- Vol. 54 (4) , 1251-1268
Open AccessA directional index to measure the degree of asymmetry for square contingency tables
In the analysis of square contingency tables, wherein the row and column variables are composed of the same ordered categories, researchers typically seek to ascertain whether the row and column variables are symmetrical. The degree of asymmetry (i.e., degree of departure from symmetry) between the row and column variables is measured using the index based on Kullback–Leibler divergence. This index value of 1 indicates a perfect upper asymmetry (namely, the cell probabilities in the lower triangle of the table, excluding the diagonal elements, are all zero) or a perfect lower asymmetry (namely, the cell probabilities in the upper triangle of the table, excluding the diagonal elements, are all zero). Consequently, this index cannot discriminate between these two types of asymmetries. The objective of the present paper is to propose a new directional index to discriminate between perfect lower and upper asymmetries. An asymptotically unbiased estimator and an approximate confidence interval for the proposed index are given. We evaluate the performances of those in a finite sample through numerical experiments. The usefulness of the proposed index is demonstrated though real data analysis.
- Open Access
- 1 June 2025
- Published by Walter de Gruyter GmbH in Biometrical Letters
- Vol. 62 (1) , 49-63
An index for discriminating the direction of anti-sum-asymmetry for square contingency tables
A square contingency table is a special case of a two-way contingency table wherein the row and column variables consist of the same classification. In square contingency tables, observations tend to be concentrated in the main diagonal cells of the table or nearby, and independence between row and column variables often does not hold. The anti-sum-symmetry model has a symmetrical structure with respect to the anti-diagonal cells of the table. The anti-sum-symmetry model should be applied to square contingency tables with ordered categories. The existing index, which can measure the degree of departure from the anti-sum-symmetry model, cannot discriminate between perfect upper and lower anti-sum-asymmetries. To address this issue, we propose here a directional index which can discriminate between the two types of anti-sum-asymmetries. The proposed index can be interpreted as an index for measuring the degree of perfect anti-sum-asymmetry. We derive an approximately unbiased estimator and an approximate confidence interval for the proposed index. The utility of the proposed index is demonstrated through a real data analysis.
- 1 June 2025
- Published by Walter de Gruyter GmbH in Biometrical Letters
- Vol. 62 (1) , 49-63
Open AccessAn index for discriminating the direction of anti-sum-asymmetry for square contingency tables
A square contingency table is a special case of a two-way contingency table wherein the row and column variables consist of the same classification. In square contingency tables, observations tend to be concentrated in the main diagonal cells of the table or nearby, and independence between row and column variables often does not hold. The anti-sum-symmetry model has a symmetrical structure with respect to the anti-diagonal cells of the table. The anti-sum-symmetry model should be applied to square contingency tables with ordered categories. The existing index, which can measure the degree of departure from the anti-sum-symmetry model, cannot discriminate between perfect upper and lower anti-sum-asymmetries. To address this issue, we propose here a directional index which can discriminate between the two types of anti-sum-asymmetries. The proposed index can be interpreted as an index for measuring the degree of perfect anti-sum-asymmetry. We derive an approximately unbiased estimator and an approximate confidence interval for the proposed index. The utility of the proposed index is demonstrated through a real data analysis.
- Open Access
- 1 May 2025
- Published by New York Business Global LLC in European Journal of Pure and Applied Mathematics
- Vol. 18 (2) , 6079
Anti-Diagonals-Parameter Symmetry Model for Square Contingency Tables with Ordinal Classifications
For analyzing square tables having same row and column classifications, analysts are often interested in whether or not the relation between the row and column variables is symmetric or asymmetric regarding the main-diagonal cells of the table. However, for the dataset of grip strength test, analysts may be interested in whether or not the relation of them is symmetric or asymmetric regarding the anti-diagonal cells, instead of the main-diagonal cells. This study proposes the anti-diagonals-parameter symmetry model that represents the asymmetric structure regarding the anti-diagonal cells. Furthermore, this study provides a separation of the anti-symmetry model using the anti-diagonals-parameter symmetry model and an orthogonal separation of the test statistic for the anti-symmetry model. This study shows the advantages of the anti-diagonals-parameter symmetry model by applying it to the real-dataset of grip strength test.
- 1 May 2025
- Published by New York Business Global LLC in European Journal of Pure and Applied Mathematics
- Vol. 18 (2) , 6079
Open AccessAnti-Diagonals-Parameter Symmetry Model for Square Contingency Tables with Ordinal Classifications
For analyzing square tables having same row and column classifications, analysts are often interested in whether or not the relation between the row and column variables is symmetric or asymmetric regarding the main-diagonal cells of the table. However, for the dataset of grip strength test, analysts may be interested in whether or not the relation of them is symmetric or asymmetric regarding the anti-diagonal cells, instead of the main-diagonal cells. This study proposes the anti-diagonals-parameter symmetry model that represents the asymmetric structure regarding the anti-diagonal cells. Furthermore, this study provides a separation of the anti-symmetry model using the anti-diagonals-parameter symmetry model and an orthogonal separation of the test statistic for the anti-symmetry model. This study shows the advantages of the anti-diagonals-parameter symmetry model by applying it to the real-dataset of grip strength test.
- 18 December 2024
- Published by Wolters Kluwer Health in Clinical Journal of the American Society of Nephrology
- Vol. 20 (3) , 420-431
Association of Physiological Reserve Obtained from Cardiopulmonary Exercise Testing and Frailty with All-Cause Mortality in Patients on Hemodialysis
Key Points: This study analyzed the prognostic value of reserves obtained from cardiopulmonary exercise testing in patients on hemodialysis. Each reserve (cardiac, autonomic, and muscular) was associated with mortality, with muscle reserve having the highest prognostic accuracy. Patients with physical frailty also had a fairly good prognosis if their physiological reserve is preserved by exercise testing. Background: Potential impairment of exercise capacity is prevalent even in patients undergoing hemodialysis without frailty. Cardiopulmonary exercise testing (CPET) can detect physiological reserves, such as cardiopulmonary, muscle, and autonomic function. We hypothesized that these indices could accurately determine the prognosis of patients on hemodialysis and analyzed them on the basis of their relationship to frailty. Methods: In this two-center prospective cohort study of patients on hemodialysis from Japan, patients underwent CPET and physical assessment to evaluate peak oxygen uptake (peak VO2, indicator of exercise capacity), peak work rate (WR, indicator of muscle function), ventilatory equivalent for carbon dioxide (VE/VCO2) slope (indicator of cardiac reserve), heart rate reserve (indicator of chronotropic incompetence), and frailty phenotype. Survival was followed up for up to 5 years. Results: Data from 189 patients (median [interquartile range] age: 71 [62–77] years) were analyzed. All CPET indicators showed a consistent nonlinear relationship with all-cause mortality after adjustment: for peak VO2, hazard ratio (HR), 0.79 (95% confidence interval [CI], 0.71 to 0.88), P < 0.001; for peak WR, HR, 0.95 (95% CI, 0.93 to 0.97), P < 0.001; for VE/VCO2 slope, HR, 1.09 (95% CI, 1.05 to 1.13), P < 0.001; and for heart rate reserve, HR, 0.96 (95% CI, 0.93 to 0.99), P = 0.02. Frailty phenotype was associated with mortality after adjustment (HR, 1.73 [95% CI, 1.06 to 2.81], P = 0.03); however, this association was not statistically significant in the model after adding peak VO2 (P = 0.41). Furthermore, in both subgroups with and without frailty, CPET measures were significantly associated with mortality risk (peak VO2, peak WR, and VE/VCO2 slope: P < 0.05). The peak VO2 (Δ area under the curve, 0.09; 95% CI, 0.02 to 0.16) or the peak WR (Δ area under the curve, 0.09; 95% CI, 0.02 to 0.15) most significantly improved the prognostic accuracy. Conclusions: Results showed the fragile aspect of the frailty phenotype in the hemodialysis population and the superior ability of CPET to indicate death risk complementing that aspect.
- 18 December 2024
- Published by Wolters Kluwer Health in Clinical Journal of the American Society of Nephrology
- Vol. 20 (3) , 420-431
Association of Physiological Reserve Obtained from Cardiopulmonary Exercise Testing and Frailty with All-Cause Mortality in Patients on Hemodialysis
Key Points: This study analyzed the prognostic value of reserves obtained from cardiopulmonary exercise testing in patients on hemodialysis. Each reserve (cardiac, autonomic, and muscular) was associated with mortality, with muscle reserve having the highest prognostic accuracy. Patients with physical frailty also had a fairly good prognosis if their physiological reserve is preserved by exercise testing. Background: Potential impairment of exercise capacity is prevalent even in patients undergoing hemodialysis without frailty. Cardiopulmonary exercise testing (CPET) can detect physiological reserves, such as cardiopulmonary, muscle, and autonomic function. We hypothesized that these indices could accurately determine the prognosis of patients on hemodialysis and analyzed them on the basis of their relationship to frailty. Methods: In this two-center prospective cohort study of patients on hemodialysis from Japan, patients underwent CPET and physical assessment to evaluate peak oxygen uptake (peak VO2, indicator of exercise capacity), peak work rate (WR, indicator of muscle function), ventilatory equivalent for carbon dioxide (VE/VCO2) slope (indicator of cardiac reserve), heart rate reserve (indicator of chronotropic incompetence), and frailty phenotype. Survival was followed up for up to 5 years. Results: Data from 189 patients (median [interquartile range] age: 71 [62–77] years) were analyzed. All CPET indicators showed a consistent nonlinear relationship with all-cause mortality after adjustment: for peak VO2, hazard ratio (HR), 0.79 (95% confidence interval [CI], 0.71 to 0.88), P < 0.001; for peak WR, HR, 0.95 (95% CI, 0.93 to 0.97), P < 0.001; for VE/VCO2 slope, HR, 1.09 (95% CI, 1.05 to 1.13), P < 0.001; and for heart rate reserve, HR, 0.96 (95% CI, 0.93 to 0.99), P = 0.02. Frailty phenotype was associated with mortality after adjustment (HR, 1.73 [95% CI, 1.06 to 2.81], P = 0.03); however, this association was not statistically significant in the model after adding peak VO2 (P = 0.41). Furthermore, in both subgroups with and without frailty, CPET measures were significantly associated with mortality risk (peak VO2, peak WR, and VE/VCO2 slope: P < 0.05). The peak VO2 (Δ area under the curve, 0.09; 95% CI, 0.02 to 0.16) or the peak WR (Δ area under the curve, 0.09; 95% CI, 0.02 to 0.15) most significantly improved the prognostic accuracy. Conclusions: Results showed the fragile aspect of the frailty phenotype in the hemodialysis population and the superior ability of CPET to indicate death risk complementing that aspect.