Ping Lin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Ping Lin has a total of 59 co-authors. Here are the top co-authors by number of shared publications:
- Yi Cao
The First Affiliated Hospital of Zhejiang Chinese Medical University (Zhejiang Provincial Hospital of Chinese Medicine)
6 shared publications Zheng Lin
Dermatology department, The First Affiliated Hospital of Zhejiang Chinese Medical University, Hangzhou, China
6 shared publicationsChengcheng Kong
2 shared publicationsChuan Sun
Zhejiang Key Laboratory of Geriatrics and Geriatrics Institute of Zhejiang Province, Zhejiang Hospital, Hangzhou, P. R. China
2 shared publications- Genxiang Mao
Zhejiang Hospital
2 shared publications Hongfei Wang
Dermatology department, The First Affiliated Hospital of Zhejiang Chinese Medical University, Hangzhou, China
2 shared publications
Latest Publications
- Open Access
- 11 August 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1) , 24897
Construction and validation of a prediction system for postherpetic neuralgia: based on meta-analysis
Postherpetic neuralgia (PHN) is a chronic and intractable pain disorder. Existing PHN prediction systems have limited clinical applicability. A systematic search of the literature was conducted in PubMed, Web of Science, Embase and the Cochrane Library between 1950 and 2025, finally 44 studies were included (PROSPERO: CRD420251011300). Training (n = 417) and validation (n = 228) datasets were obtained from First Affiliated Hospital of Zhejiang Chinese Medical University and Third People’s Hospital of Hangzhou. Based on the effect sizes from the meta-analysis, a linear regression model was fitted using the training set to develop the PHN Prediction Scoring Scale (PPSS), which was subsequently validated in the independent validation set. Seven key risk factors identified from the meta-analysis were selected for scoring,, including age (odds ratio(OR) (95% confidence interval): 1.66 (1.47, 1.88)), acute pain (OR: 2.61 (2.24, 3.05)), prodromal pain (OR: 1.79 (1.38, 2.31)), severe rash (OR: 2.64 (1.95, 3.56)), rash on the head(OR: 1.96 (1.8, 2.13)), diabetes (OR: 1.34 (1.24, 1.44)), immunosuppression (OR: 2.23 (1.95, 2.56)). Based on the above factors and weights, the PPSS were constructed. The results showed that on the validation set the area under curve of PPSS was 0.759 (0.693–0.824), accuracy was 0.684 (0.624–0.745), precision was 0.515 (0.417–0.612), recall was 0.693 (0.589–0.798), specificity was 0.680 (0.606–0.754). These findings suggest that the PPSS holds promise for generalization and application in clinical practice.
- 11 August 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1) , 24897
Open AccessConstruction and validation of a prediction system for postherpetic neuralgia: based on meta-analysis
Postherpetic neuralgia (PHN) is a chronic and intractable pain disorder. Existing PHN prediction systems have limited clinical applicability. A systematic search of the literature was conducted in PubMed, Web of Science, Embase and the Cochrane Library between 1950 and 2025, finally 44 studies were included (PROSPERO: CRD420251011300). Training (n = 417) and validation (n = 228) datasets were obtained from First Affiliated Hospital of Zhejiang Chinese Medical University and Third People’s Hospital of Hangzhou. Based on the effect sizes from the meta-analysis, a linear regression model was fitted using the training set to develop the PHN Prediction Scoring Scale (PPSS), which was subsequently validated in the independent validation set. Seven key risk factors identified from the meta-analysis were selected for scoring,, including age (odds ratio(OR) (95% confidence interval): 1.66 (1.47, 1.88)), acute pain (OR: 2.61 (2.24, 3.05)), prodromal pain (OR: 1.79 (1.38, 2.31)), severe rash (OR: 2.64 (1.95, 3.56)), rash on the head(OR: 1.96 (1.8, 2.13)), diabetes (OR: 1.34 (1.24, 1.44)), immunosuppression (OR: 2.23 (1.95, 2.56)). Based on the above factors and weights, the PPSS were constructed. The results showed that on the validation set the area under curve of PPSS was 0.759 (0.693–0.824), accuracy was 0.684 (0.624–0.745), precision was 0.515 (0.417–0.612), recall was 0.693 (0.589–0.798), specificity was 0.680 (0.606–0.754). These findings suggest that the PPSS holds promise for generalization and application in clinical practice.
- 14 May 2026
- Published by Elsevier in Journal of the Neurological Sciences
- Vol. 487, 126001
Comment on “Instrumental assessment of movement series reflects scored improvement of patients with Parkinson's disease”
- 14 May 2026
- Published by Elsevier in Journal of the Neurological Sciences
- Vol. 487, 126001
Comment on “Instrumental assessment of movement series reflects scored improvement of patients with Parkinson's disease”
- 5 April 2026
- Published by Wiley in Geriatrics & Gerontology International
- Vol. 26 (4) , e70459
Comment on “The Effects of Concurrent Training Under Hypoxia on Physical Function and Metabolic Syndrome in Obese Elderly Women in Korea”
- 5 April 2026
- Published by Wiley in Geriatrics & Gerontology International
- Vol. 26 (4) , e70459
Comment on “The Effects of Concurrent Training Under Hypoxia on Physical Function and Metabolic Syndrome in Obese Elderly Women in Korea”
- Open Access
- 2 March 2026
- Published by Springer Nature in Virology Journal
- Vol. 23 (1)
Inhibitory effect of three components derived from Salvia miltiorrhiza against human cytomegalovirus
Human cytomegalovirus (HCMV) infection is responsible for congenital infections and poses a significant health risk to immunocompromised individuals. To da
- 2 March 2026
- Published by Springer Nature in Virology Journal
- Vol. 23 (1)
Open AccessInhibitory effect of three components derived from Salvia miltiorrhiza against human cytomegalovirus
Human cytomegalovirus (HCMV) infection is responsible for congenital infections and poses a significant health risk to immunocompromised individuals. To da
- 31 October 2025
- Published by S. Karger AG in Complementary Medicine Research
- Vol. 32 (6) , 485-494
Effectiveness of Electroacupuncture Combined with Pregabalin in the Treatment of Trigeminal Herpetic Neuralgia: A Multicenter Randomized Controlled Trial Study Protocol
Background: Trigeminal herpetic neuralgia, a common type of Zoster-associated pain (ZAP), affects individuals across all ages groups and poses a significant societal burden all over the world. Electroacupuncture (EA) is increasingly used in the treatment of ZAP due to its affordability, high safety profile, absence of adverse reactions, and high patient acceptance. Consequently, it is essential to conduct randomized controlled trials to evaluate the effectiveness and safety of EA in treating ZAP and to determine if EA can be used as an alternative to pregabalin. Patients and Methods: A total of 102 patients with trigeminal herpetic neuralgia will be enrolled from 2 hospitals and randomly assigned to the EA group, pregabalin group, or EA + pregabalin group in a 1:1:1 ratio using a simple random number table. The study will consist of a 4-week treatment period followed by a 4-week follow-up period. The primary outcome measure will be pain intensity, while secondary outcomes will include mood state, sleep quality, and quality of life. Adverse reactions will be thoroughly evaluated. Conclusion: This study aims to elucidate the clinical effectiveness of EA combined with pregabalin for trigeminal herpetic neuralgia and to objectively compare the effectiveness and safety of EA versus oral pregabalin in the treatment of trigeminal herpetic neuralgia.
- 31 October 2025
- Published by S. Karger AG in Complementary Medicine Research
- Vol. 32 (6) , 485-494
Effectiveness of Electroacupuncture Combined with Pregabalin in the Treatment of Trigeminal Herpetic Neuralgia: A Multicenter Randomized Controlled Trial Study Protocol
Background: Trigeminal herpetic neuralgia, a common type of Zoster-associated pain (ZAP), affects individuals across all ages groups and poses a significant societal burden all over the world. Electroacupuncture (EA) is increasingly used in the treatment of ZAP due to its affordability, high safety profile, absence of adverse reactions, and high patient acceptance. Consequently, it is essential to conduct randomized controlled trials to evaluate the effectiveness and safety of EA in treating ZAP and to determine if EA can be used as an alternative to pregabalin. Patients and Methods: A total of 102 patients with trigeminal herpetic neuralgia will be enrolled from 2 hospitals and randomly assigned to the EA group, pregabalin group, or EA + pregabalin group in a 1:1:1 ratio using a simple random number table. The study will consist of a 4-week treatment period followed by a 4-week follow-up period. The primary outcome measure will be pain intensity, while secondary outcomes will include mood state, sleep quality, and quality of life. Adverse reactions will be thoroughly evaluated. Conclusion: This study aims to elucidate the clinical effectiveness of EA combined with pregabalin for trigeminal herpetic neuralgia and to objectively compare the effectiveness and safety of EA versus oral pregabalin in the treatment of trigeminal herpetic neuralgia.
- Open Access
- 15 September 2025
- Published by Frontiers Media SA in Frontiers in Neurology
- Vol. 16, 1632682
Evaluating the efficacy of machine learning in predicting postherpetic neuralgia: a systematic review and meta-analysis
Introduction: The prediction of postherpetic neuralgia (PHN) is of great clinical significance. PHN prediction based on machine learning have received extensive attention in recent years. This study aims to conduct a comprehensive evaluation of machine learning in PHN prediction and provide guidance for the future models.Method: The system retrieved the relevant literatures published in the PubMed, Web of Science, Embase and Cochrane Library databases from the establishment of the database to May 2025. Literature screening and data extraction were conducted in accordance with the PRISMA guidelines. According to the heterogeneity, the fixed-effect or the random-effect model was selected for data synthesis. The potential sources of heterogeneity were further explored through subgroup analysis, sensitivity tests and meta-regression. Funnel plots and Deeks’ tests were used to evaluate the possible publication biases.Result: The main meta-analysis included 41 models from 14 studies. The results showed that machine learning demonstrated excellent performance in predicting PHN (sensitivity: 0.81, 95% confidence interval (CI): 0.74–0.86; specificity: 0.84, 95% CI: 0.79–0.88; area under the curve: 0.90, 95% CI: 0.87–0.92). Meta-regression analysis indicates that the source of the data set, model selection, and the choice of predictors are the main reasons leading to heterogeneity. Subgroup analysis showed that the training set model outperformed the validation set model. Logistic regression and other machine learning had varying strengths and weaknesses. Serum data or omics analysis did not significantly enhance model performance.Conclusion: Machine learning represents a promising approach for the prediction of PHN. However, most of the existing models face issues like lack of external validation, overfitting, and insufficient reporting standardization. This has raised doubts about whether the current PHN prediction models can still maintain a high prediction accuracy when extended to external data. To improve future models, we recommend conducting strict external validation, clearly reporting cutoff values (balanced, positive, and negative), and adhering to international predictive model reporting standards. When applicable, ensemble learning and pain trajectory analyses should also be considered.Systematic review registration: This study was registered in the Prospective Register of Systematic Reviews (PROSPERO; CRD420251054364).
- 15 September 2025
- Published by Frontiers Media SA in Frontiers in Neurology
- Vol. 16, 1632682
Open AccessEvaluating the efficacy of machine learning in predicting postherpetic neuralgia: a systematic review and meta-analysis
Introduction: The prediction of postherpetic neuralgia (PHN) is of great clinical significance. PHN prediction based on machine learning have received extensive attention in recent years. This study aims to conduct a comprehensive evaluation of machine learning in PHN prediction and provide guidance for the future models.Method: The system retrieved the relevant literatures published in the PubMed, Web of Science, Embase and Cochrane Library databases from the establishment of the database to May 2025. Literature screening and data extraction were conducted in accordance with the PRISMA guidelines. According to the heterogeneity, the fixed-effect or the random-effect model was selected for data synthesis. The potential sources of heterogeneity were further explored through subgroup analysis, sensitivity tests and meta-regression. Funnel plots and Deeks’ tests were used to evaluate the possible publication biases.Result: The main meta-analysis included 41 models from 14 studies. The results showed that machine learning demonstrated excellent performance in predicting PHN (sensitivity: 0.81, 95% confidence interval (CI): 0.74–0.86; specificity: 0.84, 95% CI: 0.79–0.88; area under the curve: 0.90, 95% CI: 0.87–0.92). Meta-regression analysis indicates that the source of the data set, model selection, and the choice of predictors are the main reasons leading to heterogeneity. Subgroup analysis showed that the training set model outperformed the validation set model. Logistic regression and other machine learning had varying strengths and weaknesses. Serum data or omics analysis did not significantly enhance model performance.Conclusion: Machine learning represents a promising approach for the prediction of PHN. However, most of the existing models face issues like lack of external validation, overfitting, and insufficient reporting standardization. This has raised doubts about whether the current PHN prediction models can still maintain a high prediction accuracy when extended to external data. To improve future models, we recommend conducting strict external validation, clearly reporting cutoff values (balanced, positive, and negative), and adhering to international predictive model reporting standards. When applicable, ensemble learning and pain trajectory analyses should also be considered.Systematic review registration: This study was registered in the Prospective Register of Systematic Reviews (PROSPERO; CRD420251054364).
- Open Access
- 9 May 2025
- Published by Springer Nature in Virology Journal
- Vol. 22 (1) , 1-12
Inhibitory effect of Alantolactone against varicella-zoster virus in vitro
Varicella-zoster virus (VZV), a member of the α-herpesvirus family, is known for causing two distinct diseases: chickenpox (varicella) during the primary infection and shingles (zoster) due to reactivation of the virus later in life. Although there are vaccines available to prevent VZV infection, it is still not universally effective, and antiviral treatments for VZV are limited and may come with significant side effects. Thus, development of novel therapeutics is urgently needed. We identified a naturally occurring Alantolactone (ALT) that inhibited replication of recombinant VZV in human diploid fibroblast (WI-38 cells) and Adult Retinal Pigment Epithelial cell line-19 (ARPE-19 cells) through Western blotting, qPCR and plaque assays. Subsequently, we explored the mechanism underlying the anti-VZV activity of ALT using time-of-addition experiments and transcriptomic analyses. A screening model was established for anti-VZV compounds, and we screened ALT was with good anti-VZV efficacy. Our findings revealed that ALT alleviated cytopathic changes, reduced viral titres, and inhibited the expression of viral genes and proteins in WI-38 cells and ARPE-19 cells. Furthermore, our data showed that ALT inhibited VZV infection in intracellular viral replication. Finally, multiple inflammatory pathways were involved in the antiviral role of ALT, and IL-6 was one of the most critical hub genes. Together, our findings identify ALT as an anti-VZV agent that may prove useful in the treatment of VZV replication.
- 9 May 2025
- Published by Springer Nature in Virology Journal
- Vol. 22 (1) , 1-12
Open AccessInhibitory effect of Alantolactone against varicella-zoster virus in vitro
Varicella-zoster virus (VZV), a member of the α-herpesvirus family, is known for causing two distinct diseases: chickenpox (varicella) during the primary infection and shingles (zoster) due to reactivation of the virus later in life. Although there are vaccines available to prevent VZV infection, it is still not universally effective, and antiviral treatments for VZV are limited and may come with significant side effects. Thus, development of novel therapeutics is urgently needed. We identified a naturally occurring Alantolactone (ALT) that inhibited replication of recombinant VZV in human diploid fibroblast (WI-38 cells) and Adult Retinal Pigment Epithelial cell line-19 (ARPE-19 cells) through Western blotting, qPCR and plaque assays. Subsequently, we explored the mechanism underlying the anti-VZV activity of ALT using time-of-addition experiments and transcriptomic analyses. A screening model was established for anti-VZV compounds, and we screened ALT was with good anti-VZV efficacy. Our findings revealed that ALT alleviated cytopathic changes, reduced viral titres, and inhibited the expression of viral genes and proteins in WI-38 cells and ARPE-19 cells. Furthermore, our data showed that ALT inhibited VZV infection in intracellular viral replication. Finally, multiple inflammatory pathways were involved in the antiviral role of ALT, and IL-6 was one of the most critical hub genes. Together, our findings identify ALT as an anti-VZV agent that may prove useful in the treatment of VZV replication.
- Open Access
- 11 February 2025
- Published by Springer Nature in Immunity & Ageing
- Vol. 22 (1) , 1-23
The relationship between biological aging and psoriasis: evidence from three observational studies
The relationship between psoriasis and aging remains unclear. Biological age is considered as a tool for strong association with aging, but there is a lack of reports on the relationship between biological age and psoriasis. Therefore, this study aimed to explore the relationship between biological age and psoriasis. Patients with psoriasis and non-psoriasis were recruited from National Health and Nutrition Examination Survey (NHANES) (12,973 cases), Medical Information Mart for Intensive Care (MIMIC-IV) (558 cases) and The First Clinical Medical College of Zhejiang Chinese Medical University (206 cases). Biological age was calculated using Klemera-Doubal method age (KDM-age) and phenotypic age (PhenoAge). Linear regression and logistic regression were used to explore the association between psoriasis and biological age advance. Cox regression was used to investigate the association between biological age advance and mortality. Finally, biological age advance was used to predict the death of psoriasis patients. In NHANES, linear regression showed that psoriasis led to a 0.54 advance in PhenoAge (Adjust Beta: 0.54, 95CI: 0.12–0.97, p = 0.018). The KDM-age advance due to psoriasis was not statistically significant (p = 0.754). Using data from China, we came to the new conclusion that for every unit rise in Psoriasis Area and Severity Index, PhenoAge advance rose by 0.12 (Beta: 0.12, 95CI: 0.01–0.22, p = 0.031). Using NHANES data, cox regression shows for every unit rise in PhenoAge advance patients had an 8% rise in mortality (Adjust hazard ratio: 1.08, 95CI: 1.04–1.12, p < 0.001). Using MIMIC-IV, logistic regression showed a 13% increase in mortality within 28 days of admission for every 1 unit rise in PhenoAge advance (odds ratio: 1.13, 95CI: 1.09–1.18, P < 0.001). Finally, we used PhenoAge advance to predict death, with an AUC of 0.71 in the NHANES, an ACU of 0.79 for predicting death within 1 years in the general ward of MIMIC-IV. In the ICU of MIMIC-IV, the AUC for predicting death within 28 days was 0.71. Psoriasis leads to accelerated biological aging in patients, which is associated with the severity of psoriasis and more comorbidities. In addition, PhenoAge has the potential to monitor the health status of patients with psoriasis.
- 11 February 2025
- Published by Springer Nature in Immunity & Ageing
- Vol. 22 (1) , 1-23
Open AccessThe relationship between biological aging and psoriasis: evidence from three observational studies
The relationship between psoriasis and aging remains unclear. Biological age is considered as a tool for strong association with aging, but there is a lack of reports on the relationship between biological age and psoriasis. Therefore, this study aimed to explore the relationship between biological age and psoriasis. Patients with psoriasis and non-psoriasis were recruited from National Health and Nutrition Examination Survey (NHANES) (12,973 cases), Medical Information Mart for Intensive Care (MIMIC-IV) (558 cases) and The First Clinical Medical College of Zhejiang Chinese Medical University (206 cases). Biological age was calculated using Klemera-Doubal method age (KDM-age) and phenotypic age (PhenoAge). Linear regression and logistic regression were used to explore the association between psoriasis and biological age advance. Cox regression was used to investigate the association between biological age advance and mortality. Finally, biological age advance was used to predict the death of psoriasis patients. In NHANES, linear regression showed that psoriasis led to a 0.54 advance in PhenoAge (Adjust Beta: 0.54, 95CI: 0.12–0.97, p = 0.018). The KDM-age advance due to psoriasis was not statistically significant (p = 0.754). Using data from China, we came to the new conclusion that for every unit rise in Psoriasis Area and Severity Index, PhenoAge advance rose by 0.12 (Beta: 0.12, 95CI: 0.01–0.22, p = 0.031). Using NHANES data, cox regression shows for every unit rise in PhenoAge advance patients had an 8% rise in mortality (Adjust hazard ratio: 1.08, 95CI: 1.04–1.12, p < 0.001). Using MIMIC-IV, logistic regression showed a 13% increase in mortality within 28 days of admission for every 1 unit rise in PhenoAge advance (odds ratio: 1.13, 95CI: 1.09–1.18, P < 0.001). Finally, we used PhenoAge advance to predict death, with an AUC of 0.71 in the NHANES, an ACU of 0.79 for predicting death within 1 years in the general ward of MIMIC-IV. In the ICU of MIMIC-IV, the AUC for predicting death within 28 days was 0.71. Psoriasis leads to accelerated biological aging in patients, which is associated with the severity of psoriasis and more comorbidities. In addition, PhenoAge has the potential to monitor the health status of patients with psoriasis.
- Open Access
- 10 December 2024
- Published by Frontiers Media SA in Frontiers in Immunology
- Vol. 15, 1497713
Psoriatic arthritis in psoriasis: optimizing the current screening system for psoriatic arthritis based on serum data from U.S. and Chinese populations
Background: Psoriatic arthritis (PSA) is an inflammatory joint disease associated with psoriasis (PSO) that can be easily missed. Existing PSA screening tools ignore objective serologic indicators. The aim of this study was to develop a disease screening model and the Psoriatic Arthritis Inflammation Index (PSAII) based on serologic data to enhance the efficiency of PSA screening.Method: A total of 719 PSO and PSA patients from the National Health and Nutrition Examination Survey (NHANES) (as training set and test set) and 135 PSO and PSA patients who were seen at The First Affiliated Hospital of Zhejiang Chinese Medical University (as external validation set) were selected, 31 indicators for these patients were collected as potential input features for the model. Least Absolute Shrinkage and Selection Operator (LASSO) was used to identify PSA-related features. Five models of logistic regression (LR), random forest, k-nearest neighbor, gradient augmentation and neural network were developed in the training set using quintuple cross validation. And we developed PSAII based on the results of LASSO regression and weights of logistic model parameters. All performance metrics are derived on the test set and the external validation set.Results: Five variables were selected to build models, including age, lymphocyte percentage, neutrophil count, eosinophilic count, and C-reactive protein. In all established models, the LR model performed the best, with an Area Under Curve (AUC) of 0.87 (95% confidence interval (CI): 0.83-0.90) on the test set; on the external validation set the AUC was 0.82 (95%CI: 0.74-0.90). The PSAII formula was PSAII = percentage of lymphocytes × C-reactive protein/(neutrophil count × eosinophilic count × 10). The AUC of PSAII in the test is 0.93 (95%CI: 0.88-0.97), and the cutoff value is 18. The AUC of the external validation set is 0.81 (95%CI: 0.72-0.89).Conclusions: This study developed and validated five models to assist screening for PSA by analyzing serum data from NHANES and Chinese populations. The LR model demonstrated the best performance. We created PSAII for PSA screening. However, the high false positive rate of PSAII makes it necessary to combine it with other PSA screening tools when applied.
- 10 December 2024
- Published by Frontiers Media SA in Frontiers in Immunology
- Vol. 15, 1497713
Open AccessPsoriatic arthritis in psoriasis: optimizing the current screening system for psoriatic arthritis based on serum data from U.S. and Chinese populations
Background: Psoriatic arthritis (PSA) is an inflammatory joint disease associated with psoriasis (PSO) that can be easily missed. Existing PSA screening tools ignore objective serologic indicators. The aim of this study was to develop a disease screening model and the Psoriatic Arthritis Inflammation Index (PSAII) based on serologic data to enhance the efficiency of PSA screening.Method: A total of 719 PSO and PSA patients from the National Health and Nutrition Examination Survey (NHANES) (as training set and test set) and 135 PSO and PSA patients who were seen at The First Affiliated Hospital of Zhejiang Chinese Medical University (as external validation set) were selected, 31 indicators for these patients were collected as potential input features for the model. Least Absolute Shrinkage and Selection Operator (LASSO) was used to identify PSA-related features. Five models of logistic regression (LR), random forest, k-nearest neighbor, gradient augmentation and neural network were developed in the training set using quintuple cross validation. And we developed PSAII based on the results of LASSO regression and weights of logistic model parameters. All performance metrics are derived on the test set and the external validation set.Results: Five variables were selected to build models, including age, lymphocyte percentage, neutrophil count, eosinophilic count, and C-reactive protein. In all established models, the LR model performed the best, with an Area Under Curve (AUC) of 0.87 (95% confidence interval (CI): 0.83-0.90) on the test set; on the external validation set the AUC was 0.82 (95%CI: 0.74-0.90). The PSAII formula was PSAII = percentage of lymphocytes × C-reactive protein/(neutrophil count × eosinophilic count × 10). The AUC of PSAII in the test is 0.93 (95%CI: 0.88-0.97), and the cutoff value is 18. The AUC of the external validation set is 0.81 (95%CI: 0.72-0.89).Conclusions: This study developed and validated five models to assist screening for PSA by analyzing serum data from NHANES and Chinese populations. The LR model demonstrated the best performance. We created PSAII for PSA screening. However, the high false positive rate of PSAII makes it necessary to combine it with other PSA screening tools when applied.
- Open Access
- 6 November 2024
- Published by Frontiers Media SA in Frontiers in Medicine
- Vol. 11, 1454057
Construction of a disease risk prediction model for postherpetic pruritus by machine learning
Background: Postherpetic itch (PHI) is an easily overlooked complication of herpes zoster that greatly affects patients' quality of life. Studies have shown that early intervention can reduce the occurrence of itch. The aim of this study was to develop and validate a predictive model through a machine learning approach to identify patients at risk of developing PHI among patients with herpes zoster, making PHI prevention a viable clinical option.Method: We conducted a retrospective review of 488 hospitalized patients with herpes zoster at The First Affiliated Hospital of Zhejiang Chinese Medical University and classified according to whether they had PHI. Fifty indicators of these participants were collected as potential input features for the model. Features associated with PHI were identified for inclusion in the model using the least absolute shrinkage selection operator (LASSO). Divide all the data into five pieces, and then use each piece as a verification set and the others as a training set for training and verification, this process is repeated 100 times. Five models, logistic regression, random forest (RF), k-nearest neighbor, gradient boosting decision tree and neural network, were built in the training set using machine learning methods, and the performance of these models was evaluated in the test set.Results: Seven non-zero characteristic variables from the Lasso regression results were selected for inclusion in the model, including age, moderate pain, time to recovery from rash, diabetes, severe pain, rash on the head and face, and basophil ratio. The RF model performs better than other models. On the test set, the AUC of the RF model is 0.84 [(95% confidence interval (CI): 0.80–0.88], an accuracy of 0.78 (95% CI: 0.69–0.86), a precision of 0.61 (95% CI: 0.45–0.77), a recall of 0.73 (95% CI: 0.58–0.89), and a specificity of 0.79 (95% CI: 0.70–0.89).Conclusions: In this study, five machine learning methods were used to build postherpetic itch risk prediction models by analyzing historical case data, and the optimal model was selected through comparative analysis, with the random forest model being the top performing model.
- 6 November 2024
- Published by Frontiers Media SA in Frontiers in Medicine
- Vol. 11, 1454057
Open AccessConstruction of a disease risk prediction model for postherpetic pruritus by machine learning
Background: Postherpetic itch (PHI) is an easily overlooked complication of herpes zoster that greatly affects patients' quality of life. Studies have shown that early intervention can reduce the occurrence of itch. The aim of this study was to develop and validate a predictive model through a machine learning approach to identify patients at risk of developing PHI among patients with herpes zoster, making PHI prevention a viable clinical option.Method: We conducted a retrospective review of 488 hospitalized patients with herpes zoster at The First Affiliated Hospital of Zhejiang Chinese Medical University and classified according to whether they had PHI. Fifty indicators of these participants were collected as potential input features for the model. Features associated with PHI were identified for inclusion in the model using the least absolute shrinkage selection operator (LASSO). Divide all the data into five pieces, and then use each piece as a verification set and the others as a training set for training and verification, this process is repeated 100 times. Five models, logistic regression, random forest (RF), k-nearest neighbor, gradient boosting decision tree and neural network, were built in the training set using machine learning methods, and the performance of these models was evaluated in the test set.Results: Seven non-zero characteristic variables from the Lasso regression results were selected for inclusion in the model, including age, moderate pain, time to recovery from rash, diabetes, severe pain, rash on the head and face, and basophil ratio. The RF model performs better than other models. On the test set, the AUC of the RF model is 0.84 [(95% confidence interval (CI): 0.80–0.88], an accuracy of 0.78 (95% CI: 0.69–0.86), a precision of 0.61 (95% CI: 0.45–0.77), a recall of 0.73 (95% CI: 0.58–0.89), and a specificity of 0.79 (95% CI: 0.70–0.89).Conclusions: In this study, five machine learning methods were used to build postherpetic itch risk prediction models by analyzing historical case data, and the optimal model was selected through comparative analysis, with the random forest model being the top performing model.