James Randall Patrinely
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
James Randall Patrinely has a total of 105 co-authors. Here are the top co-authors by number of shared publications:
Douglas B. Johnson
13 shared publicationsAnna C. Pavlick
9 shared publications- Aristotelis Tsirigos
Department of Pathology, New York University Grossman School of Medicine, New York, USA
9 shared publications - David L. Rimm
Department of Pathology, Yale University School of Medicine, New Haven, USA
9 shared publications Douglas M. Donnelly
9 shared publicationsGeorge Jour
9 shared publications
Latest Publications
- Open Access
- 31 March 2023
- Published by American Association for Cancer Research (AACR)
Supplementary File 1 from Using Machine Learning Algorithms to Predict Immunotherapy Response in Patients with Advanced Melanoma
Deidentified patient clinical and demographic characteristics
- 31 March 2023
- Published by American Association for Cancer Research (AACR)
Open AccessSupplementary File 1 from Using Machine Learning Algorithms to Predict Immunotherapy Response in Patients with Advanced Melanoma
Deidentified patient clinical and demographic characteristics
- Open Access
- 31 March 2023
- Published by American Association for Cancer Research (AACR)
Data from Using Machine Learning Algorithms to Predict Immunotherapy Response in Patients with Advanced Melanoma
Purpose:Several biomarkers of response to immune checkpoint inhibitors (ICI) show potential but are not yet scalable to the clinic. We developed a pipeline that integrates deep learning on histology specimens with clinical data to predict ICI response in advanced melanoma.Experimental Design:We used a training cohort from New York University (New York, NY) and a validation cohort from Vanderbilt University (Nashville, TN). We built a multivariable classifier that integrates neural network predictions with clinical data. A ROC curve was generated and the optimal threshold was used to stratify patients as high versus low risk for progression. Kaplan–Meier curves compared progression-free survival (PFS) between the groups. The classifier was validated on two slide scanners (Aperio AT2 and Leica SCN400).Results:The multivariable classifier predicted response with AUC 0.800 on images from the Aperio AT2 and AUC 0.805 on images from the Leica SCN400. The classifier accurately stratified patients into high versus low risk for disease progression. Vanderbilt patients classified as high risk for progression had significantly worse PFS than those classified as low risk (P = 0.02 for the Aperio AT2; P = 0.03 for the Leica SCN400).Conclusions:Histology slides and patients' clinicodemographic characteristics are readily available through standard of care and have the potential to predict ICI treatment outcomes. With prospective validation, we believe our approach has potential for integration into clinical practice.
- 31 March 2023
- Published by American Association for Cancer Research (AACR)
Open AccessData from Using Machine Learning Algorithms to Predict Immunotherapy Response in Patients with Advanced Melanoma
Purpose:Several biomarkers of response to immune checkpoint inhibitors (ICI) show potential but are not yet scalable to the clinic. We developed a pipeline that integrates deep learning on histology specimens with clinical data to predict ICI response in advanced melanoma.Experimental Design:We used a training cohort from New York University (New York, NY) and a validation cohort from Vanderbilt University (Nashville, TN). We built a multivariable classifier that integrates neural network predictions with clinical data. A ROC curve was generated and the optimal threshold was used to stratify patients as high versus low risk for progression. Kaplan–Meier curves compared progression-free survival (PFS) between the groups. The classifier was validated on two slide scanners (Aperio AT2 and Leica SCN400).Results:The multivariable classifier predicted response with AUC 0.800 on images from the Aperio AT2 and AUC 0.805 on images from the Leica SCN400. The classifier accurately stratified patients into high versus low risk for disease progression. Vanderbilt patients classified as high risk for progression had significantly worse PFS than those classified as low risk (P = 0.02 for the Aperio AT2; P = 0.03 for the Leica SCN400).Conclusions:Histology slides and patients' clinicodemographic characteristics are readily available through standard of care and have the potential to predict ICI treatment outcomes. With prospective validation, we believe our approach has potential for integration into clinical practice.
- Open Access
- 31 March 2023
- Published by American Association for Cancer Research (AACR)
Supplementary File 1 from Using Machine Learning Algorithms to Predict Immunotherapy Response in Patients with Advanced Melanoma
Deidentified patient clinical and demographic characteristics
- 31 March 2023
- Published by American Association for Cancer Research (AACR)
Open AccessSupplementary File 1 from Using Machine Learning Algorithms to Predict Immunotherapy Response in Patients with Advanced Melanoma
Deidentified patient clinical and demographic characteristics
- Open Access
- 31 March 2023
- Published by American Association for Cancer Research (AACR)
Supplementary Figures from Using Machine Learning Algorithms to Predict Immunotherapy Response in Patients with Advanced Melanoma
Supplemental Figure 1. Training a Response Classifier to predict whether treatment-naïve advanced melanoma patients will respond to immunotherapy. (a) Schematic showing our computational workflow. We initially trained the neural network with a 5-fold cross validation. Hyper-parameter selection occurred during this phase. After selecting training conditions, we retrained the model on the entire NYU dataset using those parameters. We then tested the classifier on the independent cohort from Vanderbilt (b) During the 5-fold cross validation, neural network accuracy continued to improve until around 175,000 iterations. ROC curves show the performance of each of the 5 test sets at the optimal threshold. Supplemental Figure 2. Performance of the fully trained neural network and logistic regression classifiers from the NYU training dataset. Supplemental Figure 3. Development of a machine learning classifier that predicts whether treatment-naïve advanced melanoma patients will respond to immunotherapy or suffer disease progression. (a) Schematic showing the computational work-flow that is presented in this study. After development of the Segmentation Classifier, all tiles within the training and validation datasets were labeled for the 3 regions of interest. Hyper-parameter selection was performed during the 5-fold cross validation. Then, the model was retrained on the entire NYU dataset using the optimized foundation architecture and tested on the Vanderbilt cohort. (b) Suggested final pipeline where the slide is first pre-processed (tiled with suppression of the background tiles) and segmented by the first convolutional neural network. Identified tumor tiles are then assessed by the second network to extract a first estimate of the response to immunotherapy. The prediction is then refined by combining the output of the neural network with select clinical data. Supplemental Figure 4. Class activation mapping (CAM) analyses identify regions within the tiles that are used by the DCNN to classify the tile as (a) POD or (b) Response. From left to right, for each label, is an image of the tile image overlaid by the image from CAM analyses, the original tile image alone, and the image of CAM analyses alone. Supplemental Figure 5. CellProfiler was used to segment cell nuclei within tiles classified as having a high probability of POD or Response. The POD tiles analyzed had a prediction probability of 0.75 or higher (136,109 tiles). The Response tiles analyzed had a prediction probability of 0.25 or lower (51,220 tiles). Student's t-test was used to compare basic features of the segmented nuclei including area, density, and eccentricity. Supplemental Figure 6. Value importance of DCNN prediction, ECOG performance status, and treatment category was calculated as the absolute value of their Z-scores.
- 31 March 2023
- Published by American Association for Cancer Research (AACR)
Open AccessSupplementary Figures from Using Machine Learning Algorithms to Predict Immunotherapy Response in Patients with Advanced Melanoma
Supplemental Figure 1. Training a Response Classifier to predict whether treatment-naïve advanced melanoma patients will respond to immunotherapy. (a) Schematic showing our computational workflow. We initially trained the neural network with a 5-fold cross validation. Hyper-parameter selection occurred during this phase. After selecting training conditions, we retrained the model on the entire NYU dataset using those parameters. We then tested the classifier on the independent cohort from Vanderbilt (b) During the 5-fold cross validation, neural network accuracy continued to improve until around 175,000 iterations. ROC curves show the performance of each of the 5 test sets at the optimal threshold. Supplemental Figure 2. Performance of the fully trained neural network and logistic regression classifiers from the NYU training dataset. Supplemental Figure 3. Development of a machine learning classifier that predicts whether treatment-naïve advanced melanoma patients will respond to immunotherapy or suffer disease progression. (a) Schematic showing the computational work-flow that is presented in this study. After development of the Segmentation Classifier, all tiles within the training and validation datasets were labeled for the 3 regions of interest. Hyper-parameter selection was performed during the 5-fold cross validation. Then, the model was retrained on the entire NYU dataset using the optimized foundation architecture and tested on the Vanderbilt cohort. (b) Suggested final pipeline where the slide is first pre-processed (tiled with suppression of the background tiles) and segmented by the first convolutional neural network. Identified tumor tiles are then assessed by the second network to extract a first estimate of the response to immunotherapy. The prediction is then refined by combining the output of the neural network with select clinical data. Supplemental Figure 4. Class activation mapping (CAM) analyses identify regions within the tiles that are used by the DCNN to classify the tile as (a) POD or (b) Response. From left to right, for each label, is an image of the tile image overlaid by the image from CAM analyses, the original tile image alone, and the image of CAM analyses alone. Supplemental Figure 5. CellProfiler was used to segment cell nuclei within tiles classified as having a high probability of POD or Response. The POD tiles analyzed had a prediction probability of 0.75 or higher (136,109 tiles). The Response tiles analyzed had a prediction probability of 0.25 or lower (51,220 tiles). Student's t-test was used to compare basic features of the segmented nuclei including area, density, and eccentricity. Supplemental Figure 6. Value importance of DCNN prediction, ECOG performance status, and treatment category was calculated as the absolute value of their Z-scores.
- Open Access
- 31 March 2023
- Published by American Association for Cancer Research (AACR)
Data from Using Machine Learning Algorithms to Predict Immunotherapy Response in Patients with Advanced Melanoma
Purpose:Several biomarkers of response to immune checkpoint inhibitors (ICI) show potential but are not yet scalable to the clinic. We developed a pipeline that integrates deep learning on histology specimens with clinical data to predict ICI response in advanced melanoma.Experimental Design:We used a training cohort from New York University (New York, NY) and a validation cohort from Vanderbilt University (Nashville, TN). We built a multivariable classifier that integrates neural network predictions with clinical data. A ROC curve was generated and the optimal threshold was used to stratify patients as high versus low risk for progression. Kaplan–Meier curves compared progression-free survival (PFS) between the groups. The classifier was validated on two slide scanners (Aperio AT2 and Leica SCN400).Results:The multivariable classifier predicted response with AUC 0.800 on images from the Aperio AT2 and AUC 0.805 on images from the Leica SCN400. The classifier accurately stratified patients into high versus low risk for disease progression. Vanderbilt patients classified as high risk for progression had significantly worse PFS than those classified as low risk (P = 0.02 for the Aperio AT2; P = 0.03 for the Leica SCN400).Conclusions:Histology slides and patients' clinicodemographic characteristics are readily available through standard of care and have the potential to predict ICI treatment outcomes. With prospective validation, we believe our approach has potential for integration into clinical practice.
- 31 March 2023
- Published by American Association for Cancer Research (AACR)
Open AccessData from Using Machine Learning Algorithms to Predict Immunotherapy Response in Patients with Advanced Melanoma
Purpose:Several biomarkers of response to immune checkpoint inhibitors (ICI) show potential but are not yet scalable to the clinic. We developed a pipeline that integrates deep learning on histology specimens with clinical data to predict ICI response in advanced melanoma.Experimental Design:We used a training cohort from New York University (New York, NY) and a validation cohort from Vanderbilt University (Nashville, TN). We built a multivariable classifier that integrates neural network predictions with clinical data. A ROC curve was generated and the optimal threshold was used to stratify patients as high versus low risk for progression. Kaplan–Meier curves compared progression-free survival (PFS) between the groups. The classifier was validated on two slide scanners (Aperio AT2 and Leica SCN400).Results:The multivariable classifier predicted response with AUC 0.800 on images from the Aperio AT2 and AUC 0.805 on images from the Leica SCN400. The classifier accurately stratified patients into high versus low risk for disease progression. Vanderbilt patients classified as high risk for progression had significantly worse PFS than those classified as low risk (P = 0.02 for the Aperio AT2; P = 0.03 for the Leica SCN400).Conclusions:Histology slides and patients' clinicodemographic characteristics are readily available through standard of care and have the potential to predict ICI treatment outcomes. With prospective validation, we believe our approach has potential for integration into clinical practice.
- Open Access
- 31 March 2023
- Published by American Association for Cancer Research (AACR)
Supplementary Figures from Using Machine Learning Algorithms to Predict Immunotherapy Response in Patients with Advanced Melanoma
Supplemental Figure 1. Training a Response Classifier to predict whether treatment-naïve advanced melanoma patients will respond to immunotherapy. (a) Schematic showing our computational workflow. We initially trained the neural network with a 5-fold cross validation. Hyper-parameter selection occurred during this phase. After selecting training conditions, we retrained the model on the entire NYU dataset using those parameters. We then tested the classifier on the independent cohort from Vanderbilt (b) During the 5-fold cross validation, neural network accuracy continued to improve until around 175,000 iterations. ROC curves show the performance of each of the 5 test sets at the optimal threshold. Supplemental Figure 2. Performance of the fully trained neural network and logistic regression classifiers from the NYU training dataset. Supplemental Figure 3. Development of a machine learning classifier that predicts whether treatment-naïve advanced melanoma patients will respond to immunotherapy or suffer disease progression. (a) Schematic showing the computational work-flow that is presented in this study. After development of the Segmentation Classifier, all tiles within the training and validation datasets were labeled for the 3 regions of interest. Hyper-parameter selection was performed during the 5-fold cross validation. Then, the model was retrained on the entire NYU dataset using the optimized foundation architecture and tested on the Vanderbilt cohort. (b) Suggested final pipeline where the slide is first pre-processed (tiled with suppression of the background tiles) and segmented by the first convolutional neural network. Identified tumor tiles are then assessed by the second network to extract a first estimate of the response to immunotherapy. The prediction is then refined by combining the output of the neural network with select clinical data. Supplemental Figure 4. Class activation mapping (CAM) analyses identify regions within the tiles that are used by the DCNN to classify the tile as (a) POD or (b) Response. From left to right, for each label, is an image of the tile image overlaid by the image from CAM analyses, the original tile image alone, and the image of CAM analyses alone. Supplemental Figure 5. CellProfiler was used to segment cell nuclei within tiles classified as having a high probability of POD or Response. The POD tiles analyzed had a prediction probability of 0.75 or higher (136,109 tiles). The Response tiles analyzed had a prediction probability of 0.25 or lower (51,220 tiles). Student's t-test was used to compare basic features of the segmented nuclei including area, density, and eccentricity. Supplemental Figure 6. Value importance of DCNN prediction, ECOG performance status, and treatment category was calculated as the absolute value of their Z-scores.
- 31 March 2023
- Published by American Association for Cancer Research (AACR)
Open AccessSupplementary Figures from Using Machine Learning Algorithms to Predict Immunotherapy Response in Patients with Advanced Melanoma
Supplemental Figure 1. Training a Response Classifier to predict whether treatment-naïve advanced melanoma patients will respond to immunotherapy. (a) Schematic showing our computational workflow. We initially trained the neural network with a 5-fold cross validation. Hyper-parameter selection occurred during this phase. After selecting training conditions, we retrained the model on the entire NYU dataset using those parameters. We then tested the classifier on the independent cohort from Vanderbilt (b) During the 5-fold cross validation, neural network accuracy continued to improve until around 175,000 iterations. ROC curves show the performance of each of the 5 test sets at the optimal threshold. Supplemental Figure 2. Performance of the fully trained neural network and logistic regression classifiers from the NYU training dataset. Supplemental Figure 3. Development of a machine learning classifier that predicts whether treatment-naïve advanced melanoma patients will respond to immunotherapy or suffer disease progression. (a) Schematic showing the computational work-flow that is presented in this study. After development of the Segmentation Classifier, all tiles within the training and validation datasets were labeled for the 3 regions of interest. Hyper-parameter selection was performed during the 5-fold cross validation. Then, the model was retrained on the entire NYU dataset using the optimized foundation architecture and tested on the Vanderbilt cohort. (b) Suggested final pipeline where the slide is first pre-processed (tiled with suppression of the background tiles) and segmented by the first convolutional neural network. Identified tumor tiles are then assessed by the second network to extract a first estimate of the response to immunotherapy. The prediction is then refined by combining the output of the neural network with select clinical data. Supplemental Figure 4. Class activation mapping (CAM) analyses identify regions within the tiles that are used by the DCNN to classify the tile as (a) POD or (b) Response. From left to right, for each label, is an image of the tile image overlaid by the image from CAM analyses, the original tile image alone, and the image of CAM analyses alone. Supplemental Figure 5. CellProfiler was used to segment cell nuclei within tiles classified as having a high probability of POD or Response. The POD tiles analyzed had a prediction probability of 0.75 or higher (136,109 tiles). The Response tiles analyzed had a prediction probability of 0.25 or lower (51,220 tiles). Student's t-test was used to compare basic features of the segmented nuclei including area, density, and eccentricity. Supplemental Figure 6. Value importance of DCNN prediction, ECOG performance status, and treatment category was calculated as the absolute value of their Z-scores.
- Open Access
- 31 March 2023
- Published by American Association for Cancer Research (AACR)
Supplementary Tables 1-11 from Using Machine Learning Algorithms to Predict Immunotherapy Response in Patients with Advanced Melanoma
Supplemental Table 1. Patient, slide, and tile distribution during the 5-fold cross validation for training the neural network on the NYU dataset. Supplemental Table 2. Odds Ratios (OR) and 95% Confidence Intervals (CI) from univariate analyses of baseline clinical and demographic variables. Supplemental Table 3. AUC for each of 5 independent test runs and the average AUC for both classifiers when applied to Vanderbilt slides scanned with the Aperio AT2. Supplemental Table 4. AUC for each of 5 independent test runs and the average AUC for both classifiers when applied to Vanderbilt slides scanned with the Leica SCN400. Supplemental Table 5. AUC with 95% confidence intervals for the DCNN and multivariable classifiers when applied exclusively to lymph node or soft tissue from the Vanderbilt dataset. Supplemental Table 6. Results of 3 independent test runs and the average performance of the DCNN classifier on slides from Vanderbilt scanned at 10x magnification. Shown are area under the curve (AUC) and 95% confidence intervals (CI). Supplemental Table 7. Hazard Ratios (HR) with 95% Confidence Intervals (CI) for the clinical variables used in the multivariable prediction model. Supplemental Table 8. AUC and 95% confidence intervals for the neural network prediction, ECOG performance status, treatment category, and each combination of the variables. Supplemental Table 9. Value importance of treatment category, baseline ECOG, and DCNN are reported as the absolute value of the Z-score. Supplemental Table 10. Confusion matrix for predictions of PFS on the cohort of Vanderbilt patients when slides were scanned with an Aperio AT2 scanner. Supplemental Table 11. Confusion matrix for predictions of PFS on the cohort of Vanderbilt patients when slides were scanned with a Leica SCN400 scanner.
- 31 March 2023
- Published by American Association for Cancer Research (AACR)
Open AccessSupplementary Tables 1-11 from Using Machine Learning Algorithms to Predict Immunotherapy Response in Patients with Advanced Melanoma
Supplemental Table 1. Patient, slide, and tile distribution during the 5-fold cross validation for training the neural network on the NYU dataset. Supplemental Table 2. Odds Ratios (OR) and 95% Confidence Intervals (CI) from univariate analyses of baseline clinical and demographic variables. Supplemental Table 3. AUC for each of 5 independent test runs and the average AUC for both classifiers when applied to Vanderbilt slides scanned with the Aperio AT2. Supplemental Table 4. AUC for each of 5 independent test runs and the average AUC for both classifiers when applied to Vanderbilt slides scanned with the Leica SCN400. Supplemental Table 5. AUC with 95% confidence intervals for the DCNN and multivariable classifiers when applied exclusively to lymph node or soft tissue from the Vanderbilt dataset. Supplemental Table 6. Results of 3 independent test runs and the average performance of the DCNN classifier on slides from Vanderbilt scanned at 10x magnification. Shown are area under the curve (AUC) and 95% confidence intervals (CI). Supplemental Table 7. Hazard Ratios (HR) with 95% Confidence Intervals (CI) for the clinical variables used in the multivariable prediction model. Supplemental Table 8. AUC and 95% confidence intervals for the neural network prediction, ECOG performance status, treatment category, and each combination of the variables. Supplemental Table 9. Value importance of treatment category, baseline ECOG, and DCNN are reported as the absolute value of the Z-score. Supplemental Table 10. Confusion matrix for predictions of PFS on the cohort of Vanderbilt patients when slides were scanned with an Aperio AT2 scanner. Supplemental Table 11. Confusion matrix for predictions of PFS on the cohort of Vanderbilt patients when slides were scanned with a Leica SCN400 scanner.
- Open Access
- 31 March 2023
- Published by American Association for Cancer Research (AACR)
Supplementary Tables 1-11 from Using Machine Learning Algorithms to Predict Immunotherapy Response in Patients with Advanced Melanoma
Supplemental Table 1. Patient, slide, and tile distribution during the 5-fold cross validation for training the neural network on the NYU dataset. Supplemental Table 2. Odds Ratios (OR) and 95% Confidence Intervals (CI) from univariate analyses of baseline clinical and demographic variables. Supplemental Table 3. AUC for each of 5 independent test runs and the average AUC for both classifiers when applied to Vanderbilt slides scanned with the Aperio AT2. Supplemental Table 4. AUC for each of 5 independent test runs and the average AUC for both classifiers when applied to Vanderbilt slides scanned with the Leica SCN400. Supplemental Table 5. AUC with 95% confidence intervals for the DCNN and multivariable classifiers when applied exclusively to lymph node or soft tissue from the Vanderbilt dataset. Supplemental Table 6. Results of 3 independent test runs and the average performance of the DCNN classifier on slides from Vanderbilt scanned at 10x magnification. Shown are area under the curve (AUC) and 95% confidence intervals (CI). Supplemental Table 7. Hazard Ratios (HR) with 95% Confidence Intervals (CI) for the clinical variables used in the multivariable prediction model. Supplemental Table 8. AUC and 95% confidence intervals for the neural network prediction, ECOG performance status, treatment category, and each combination of the variables. Supplemental Table 9. Value importance of treatment category, baseline ECOG, and DCNN are reported as the absolute value of the Z-score. Supplemental Table 10. Confusion matrix for predictions of PFS on the cohort of Vanderbilt patients when slides were scanned with an Aperio AT2 scanner. Supplemental Table 11. Confusion matrix for predictions of PFS on the cohort of Vanderbilt patients when slides were scanned with a Leica SCN400 scanner.
- 31 March 2023
- Published by American Association for Cancer Research (AACR)
Open AccessSupplementary Tables 1-11 from Using Machine Learning Algorithms to Predict Immunotherapy Response in Patients with Advanced Melanoma
Supplemental Table 1. Patient, slide, and tile distribution during the 5-fold cross validation for training the neural network on the NYU dataset. Supplemental Table 2. Odds Ratios (OR) and 95% Confidence Intervals (CI) from univariate analyses of baseline clinical and demographic variables. Supplemental Table 3. AUC for each of 5 independent test runs and the average AUC for both classifiers when applied to Vanderbilt slides scanned with the Aperio AT2. Supplemental Table 4. AUC for each of 5 independent test runs and the average AUC for both classifiers when applied to Vanderbilt slides scanned with the Leica SCN400. Supplemental Table 5. AUC with 95% confidence intervals for the DCNN and multivariable classifiers when applied exclusively to lymph node or soft tissue from the Vanderbilt dataset. Supplemental Table 6. Results of 3 independent test runs and the average performance of the DCNN classifier on slides from Vanderbilt scanned at 10x magnification. Shown are area under the curve (AUC) and 95% confidence intervals (CI). Supplemental Table 7. Hazard Ratios (HR) with 95% Confidence Intervals (CI) for the clinical variables used in the multivariable prediction model. Supplemental Table 8. AUC and 95% confidence intervals for the neural network prediction, ECOG performance status, treatment category, and each combination of the variables. Supplemental Table 9. Value importance of treatment category, baseline ECOG, and DCNN are reported as the absolute value of the Z-score. Supplemental Table 10. Confusion matrix for predictions of PFS on the cohort of Vanderbilt patients when slides were scanned with an Aperio AT2 scanner. Supplemental Table 11. Confusion matrix for predictions of PFS on the cohort of Vanderbilt patients when slides were scanned with a Leica SCN400 scanner.
- Open Access
- 7 October 2022
- Published by Elsevier in European Journal of Cancer
- Vol. 176, 121-132
Real-world outcomes with ipilimumab and nivolumab in advanced melanoma: a multicentre retrospective study
- 7 October 2022
- Published by Elsevier in European Journal of Cancer
- Vol. 176, 121-132
Open AccessReal-world outcomes with ipilimumab and nivolumab in advanced melanoma: a multicentre retrospective study
- 19 August 2021
- Published by Wiley in Microcirculation
- Vol. 28 (8) , e12725
Guideline for in vivo assessment of adherent and rolling leukocytes in human skin microvasculature via reflectance confocal videomicroscopy
Objective: To develop a guideline that reliably identifies cutaneous adherent and rolling leukocytes from mimicking scenarios via in vivo reflectance confocal videomicroscopy.Methods: We used a clinical reflectance confocal microscope, the VivaScope 1500, to acquire 1522 videos of the upper dermal microcirculation from 12 healthy subjects and 60 patients after allogeneic hematopoietic cell transplantation. Blinded to clinical information, two trained raters independently counted the number of adherent and rolling leukocytes in 88 videos. Based on discrepancies in the initial assessments, we developed a guideline to identify both types of leukocyte‐endothelial interactions via a modified Delphi method (without anonymity). To test the guideline's ability to improve the inter‐rater reliability, the two raters assessed the remaining 1434 videos by using the guideline.Results: We demonstrate a guideline that consists of definitions, a step‐by‐step flowchart, and corresponding visuals of adherent and rolling leukocytes and mimicking scenarios. The guideline improved the inter‐rater reliability of the manual assessment of both interactions. The intraclass correlation coefficient (ICC) of adherent leukocyte counts increased from 0.056 (95% confidence interval: 0–0.236, n = 88 videos, N = 10 subjects) to 0.791 (0.770–0.809, n = 1434, N = 67). The ICC of rolling leukocyte counts increased from 0.385 (0.191–0.550, n = 88, N = 10) to 0.626 (0.593–0.657, n = 1434, N = 67). Intra‐rater ICC post‐guideline was 0.953 (0.886–0.981, n = 20, N = 12) and 0.956 (0.894–0.983, n = 20, N = 12) for adherent and rolling, respectively.Conclusion: The guideline aids in the manual identification of adherent and rolling leukocytes via in vivo reflectance confocal videomicroscopy.
- 19 August 2021
- Published by Wiley in Microcirculation
- Vol. 28 (8) , e12725
Guideline for in vivo assessment of adherent and rolling leukocytes in human skin microvasculature via reflectance confocal videomicroscopy
Objective: To develop a guideline that reliably identifies cutaneous adherent and rolling leukocytes from mimicking scenarios via in vivo reflectance confocal videomicroscopy.Methods: We used a clinical reflectance confocal microscope, the VivaScope 1500, to acquire 1522 videos of the upper dermal microcirculation from 12 healthy subjects and 60 patients after allogeneic hematopoietic cell transplantation. Blinded to clinical information, two trained raters independently counted the number of adherent and rolling leukocytes in 88 videos. Based on discrepancies in the initial assessments, we developed a guideline to identify both types of leukocyte‐endothelial interactions via a modified Delphi method (without anonymity). To test the guideline's ability to improve the inter‐rater reliability, the two raters assessed the remaining 1434 videos by using the guideline.Results: We demonstrate a guideline that consists of definitions, a step‐by‐step flowchart, and corresponding visuals of adherent and rolling leukocytes and mimicking scenarios. The guideline improved the inter‐rater reliability of the manual assessment of both interactions. The intraclass correlation coefficient (ICC) of adherent leukocyte counts increased from 0.056 (95% confidence interval: 0–0.236, n = 88 videos, N = 10 subjects) to 0.791 (0.770–0.809, n = 1434, N = 67). The ICC of rolling leukocyte counts increased from 0.385 (0.191–0.550, n = 88, N = 10) to 0.626 (0.593–0.657, n = 1434, N = 67). Intra‐rater ICC post‐guideline was 0.953 (0.886–0.981, n = 20, N = 12) and 0.956 (0.894–0.983, n = 20, N = 12) for adherent and rolling, respectively.Conclusion: The guideline aids in the manual identification of adherent and rolling leukocytes via in vivo reflectance confocal videomicroscopy.