Patryk Orzechowski
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
Patryk Orzechowski has a total of 47 co-authors. Here are the top co-authors by number of shared publications:
- Jason H. Moore
Department of Computational Biomedicine, Cedars-Sinai Medical Center, West Hollywood, USA
14 shared publications Jason H. Moore
University of Pennsylvania
4 shared publicationsArtur Pańszczyk
Department of Automatics and Biomedical Engineering, AGH University of Science and Technology, Krakow, Poland
3 shared publications- Moshe Sipper
Ben-Gurion University of the Negev
3 shared publications Xiuzhen Huang
Department of Computer Science Arkansas State University 72467 Jonesboro AR USA
3 shared publications- Dawid Storman
Chair of Epidemiology and Preventive Medicine, Department of Hygiene and Dietetics; Jagiellonian University Medical College; Krakow Poland
2 shared publications
Latest Publications
- Top Cited PapersOpen Access
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- Vol. 2025, 5367-5378
MentalChat16K: A Benchmark Dataset for Conversational Mental Health Assistance
We introduce MentalChat16K, an English benchmark dataset combining a synthetic mental health counseling dataset and a dataset of anonymized transcripts from interventions between Behavioral Health Coaches and Caregivers of patients in palliative or hospice care. Covering a diverse range of conditions like depression, anxiety, and grief, this curated dataset is designed to facilitate the development and evaluation of large language models for conversational mental health assistance. By providing a high-quality resource tailored to this critical domain, MentalChat16K aims to advance research on empathetic, personalized AI solutions to improve access to mental health support services. The dataset prioritizes patient privacy, ethical considerations, and responsible data usage. MentalChat16K presents a valuable opportunity for the research community to innovate AI technologies that can positively impact mental well-being. The dataset is available at https://huggingface.co/datasets/ShenLab/MentalChat16K and the code and documentation are hosted on GitHub at https://github.com/PennShenLab/MentalChat16K.
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- Vol. 2025, 5367-5378
Top Cited PapersOpen AccessMentalChat16K: A Benchmark Dataset for Conversational Mental Health Assistance
We introduce MentalChat16K, an English benchmark dataset combining a synthetic mental health counseling dataset and a dataset of anonymized transcripts from interventions between Behavioral Health Coaches and Caregivers of patients in palliative or hospice care. Covering a diverse range of conditions like depression, anxiety, and grief, this curated dataset is designed to facilitate the development and evaluation of large language models for conversational mental health assistance. By providing a high-quality resource tailored to this critical domain, MentalChat16K aims to advance research on empathetic, personalized AI solutions to improve access to mental health support services. The dataset prioritizes patient privacy, ethical considerations, and responsible data usage. MentalChat16K presents a valuable opportunity for the research community to innovate AI technologies that can positively impact mental well-being. The dataset is available at https://huggingface.co/datasets/ShenLab/MentalChat16K and the code and documentation are hosted on GitHub at https://github.com/PennShenLab/MentalChat16K.
- Open Access
Benchmarking AutoML algorithms on a collection of synthetic classification problems
Automated machine learning (AutoML) algorithms have grown in popularity due to their high performance and flexibility to adapt to different problems and data sets. With the increasing number of AutoML algorithms, deciding which would best suit a given problem becomes increasingly more work. Therefore, it is essential to use complex and challenging benchmarks which would be able to differentiate the AutoML algorithms from each other. This paper compares the performance of four different AutoML algorithms: Tree-based Pipeline Optimization Tool (TPOT), Auto-Sklearn, Auto-Sklearn 2, and H2O AutoML. We use the Diverse and Generative ML benchmark (DIGEN), a diverse set of synthetic datasets derived from generative functions designed to highlight the strengths and weaknesses of the performance of common machine learning algorithms. We confirm that AutoML can identify pipelines that perform well on all included datasets. Most AutoML algorithms performed similarly; however, there were some differences depending on the specific dataset and metric used.
Open AccessBenchmarking AutoML algorithms on a collection of synthetic classification problems
Automated machine learning (AutoML) algorithms have grown in popularity due to their high performance and flexibility to adapt to different problems and data sets. With the increasing number of AutoML algorithms, deciding which would best suit a given problem becomes increasingly more work. Therefore, it is essential to use complex and challenging benchmarks which would be able to differentiate the AutoML algorithms from each other. This paper compares the performance of four different AutoML algorithms: Tree-based Pipeline Optimization Tool (TPOT), Auto-Sklearn, Auto-Sklearn 2, and H2O AutoML. We use the Diverse and Generative ML benchmark (DIGEN), a diverse set of synthetic datasets derived from generative functions designed to highlight the strengths and weaknesses of the performance of common machine learning algorithms. We confirm that AutoML can identify pipelines that perform well on all included datasets. Most AutoML algorithms performed similarly; however, there were some differences depending on the specific dataset and metric used.
- Open Access
- 23 November 2022
- Published by American Association for the Advancement of Science (AAAS) in Science Advances
- Vol. 8 (47) , eabl4747
Generative and reproducible benchmarks for comprehensive evaluation of machine learning classifiers
Understanding the strengths and weaknesses of machine learning (ML) algorithms is crucial to determine their scope of application. Here, we introduce the Diverse and Generative ML Benchmark (DIGEN), a collection of synthetic datasets for comprehensive, reproducible, and interpretable benchmarking of ML algorithms for classification of binary outcomes. The DIGEN resource consists of 40 mathematical functions that map continuous features to binary targets for creating synthetic datasets. These 40 functions were found using a heuristic algorithm designed to maximize the diversity of performance among multiple popular ML algorithms, thus providing a useful test suite for evaluating and comparing new methods. Access to the generative functions facilitates understanding of why a method performs poorly compared to other algorithms, thus providing ideas for improvement.
- 23 November 2022
- Published by American Association for the Advancement of Science (AAAS) in Science Advances
- Vol. 8 (47) , eabl4747
Open AccessGenerative and reproducible benchmarks for comprehensive evaluation of machine learning classifiers
Understanding the strengths and weaknesses of machine learning (ML) algorithms is crucial to determine their scope of application. Here, we introduce the Diverse and Generative ML Benchmark (DIGEN), a collection of synthetic datasets for comprehensive, reproducible, and interpretable benchmarking of ML algorithms for classification of binary outcomes. The DIGEN resource consists of 40 mathematical functions that map continuous features to binary targets for creating synthetic datasets. These 40 functions were found using a heuristic algorithm designed to maximize the diversity of performance among multiple popular ML algorithms, thus providing a useful test suite for evaluating and comparing new methods. Access to the generative functions facilitates understanding of why a method performs poorly compared to other algorithms, thus providing ideas for improvement.
- Open Access
- 6 April 2022
- Published by MDPI AG in Journal of Clinical Medicine
- Vol. 11 (7) , 2054
Artificial Intelligence for COVID-19 Detection in Medical Imaging—Diagnostic Measures and Wasting—A Systematic Umbrella Review
The COVID-19 pandemic has sparked a barrage of primary research and reviews. We investigated the publishing process, time and resource wasting, and assessed the methodological quality of the reviews on artificial intelligence techniques to diagnose COVID-19 in medical images. We searched nine databases from inception until 1 September 2020. Two independent reviewers did all steps of identification, extraction, and methodological credibility assessment of records. Out of 725 records, 22 reviews analysing 165 primary studies met the inclusion criteria. This review covers 174,277 participants in total, including 19,170 diagnosed with COVID-19. The methodological credibility of all eligible studies was rated as critically low: 95% of papers had significant flaws in reporting quality. On average, 7.24 (range: 0–45) new papers were included in each subsequent review, and 14% of studies did not include any new paper into consideration. Almost three-quarters of the studies included less than 10% of available studies. More than half of the reviews did not comment on the previously published reviews at all. Much wasting time and resources could be avoided if referring to previous reviews and following methodological guidelines. Such information chaos is alarming. It is high time to draw conclusions from what we experienced and prepare for future pandemics.
- 6 April 2022
- Published by MDPI AG in Journal of Clinical Medicine
- Vol. 11 (7) , 2054
Open AccessArtificial Intelligence for COVID-19 Detection in Medical Imaging—Diagnostic Measures and Wasting—A Systematic Umbrella Review
The COVID-19 pandemic has sparked a barrage of primary research and reviews. We investigated the publishing process, time and resource wasting, and assessed the methodological quality of the reviews on artificial intelligence techniques to diagnose COVID-19 in medical images. We searched nine databases from inception until 1 September 2020. Two independent reviewers did all steps of identification, extraction, and methodological credibility assessment of records. Out of 725 records, 22 reviews analysing 165 primary studies met the inclusion criteria. This review covers 174,277 participants in total, including 19,170 diagnosed with COVID-19. The methodological credibility of all eligible studies was rated as critically low: 95% of papers had significant flaws in reporting quality. On average, 7.24 (range: 0–45) new papers were included in each subsequent review, and 14% of studies did not include any new paper into consideration. Almost three-quarters of the studies included less than 10% of available studies. More than half of the reviews did not comment on the previously published reviews at all. Much wasting time and resources could be avoided if referring to previous reviews and following methodological guidelines. Such information chaos is alarming. It is high time to draw conclusions from what we experienced and prepare for future pandemics.
- Open Access
A Call For Better Methodological Quality Of Reviews On Using Artificial Intelligence For COVID-19 Detection In Medical Imaging – An Umbrella Systematic Review
Objective In this umbrella systematic review, we screen existing reviews on using artificial intelligence (AI) techniques to diagnose COVID-19 in patients of any age and sex (both hospitalised and ambulatory) using medical images and assess their methodological quality. Methods We searched seven databases (MEDLINE, EMBASE, Web of Science, Scopus, dblp, Cochrane Library, IEEE Xplore) and two preprint services (arXiv, OSF Preprints) up to September 1, 2020. Eligible studies were identified as reviews or surveys where any metric of classification of detection of COVID-19 using AI was provided. Two independent reviewers did all steps of identification of records (titles and abstracts screening, full texts assessment, essential data extraction, and quality assessment). Any discrepancies were resolved by discussion. We qualitatively analyse methodological credibility of the reviews using AMSTAR 2 and evaluate reporting using PRISMA-DTA tools, leaving quantitative analysis for further publications. Results We included 22 reviews out of 725 records covering 165 primary studies. This review covers 416,254 participants in total, including 50,022 diagnosed with COVID-19. The methodological quality of all eligible studies was rated as critically low. 91% of papers had significant flaws in reporting quality. More than half of the reviews did not comment on the results of previously published reviews at all. Almost three fourth of the studies included less than 10% of available studies. Discussion In this umbrella review, we focus on the descriptive summary of included papers. Much wasting time and resources could be avoided if referring to previous reviews and following methodological guidelines. Due to the low credibility of evidence and flawed reporting, any recommendation about automated COVID-19 clinical diagnosis from medical images using AI at this point cannot be provided. Funding PO was supported by NIH grant AI116794 (the funding body had no role in the design, in any stage of the review, or in writing the manuscript); PJ and DS did not receive any funding. Registration The protocol of this review was registered on the OSF platform [1].
Open AccessA Call For Better Methodological Quality Of Reviews On Using Artificial Intelligence For COVID-19 Detection In Medical Imaging – An Umbrella Systematic Review
Objective In this umbrella systematic review, we screen existing reviews on using artificial intelligence (AI) techniques to diagnose COVID-19 in patients of any age and sex (both hospitalised and ambulatory) using medical images and assess their methodological quality. Methods We searched seven databases (MEDLINE, EMBASE, Web of Science, Scopus, dblp, Cochrane Library, IEEE Xplore) and two preprint services (arXiv, OSF Preprints) up to September 1, 2020. Eligible studies were identified as reviews or surveys where any metric of classification of detection of COVID-19 using AI was provided. Two independent reviewers did all steps of identification of records (titles and abstracts screening, full texts assessment, essential data extraction, and quality assessment). Any discrepancies were resolved by discussion. We qualitatively analyse methodological credibility of the reviews using AMSTAR 2 and evaluate reporting using PRISMA-DTA tools, leaving quantitative analysis for further publications. Results We included 22 reviews out of 725 records covering 165 primary studies. This review covers 416,254 participants in total, including 50,022 diagnosed with COVID-19. The methodological quality of all eligible studies was rated as critically low. 91% of papers had significant flaws in reporting quality. More than half of the reviews did not comment on the results of previously published reviews at all. Almost three fourth of the studies included less than 10% of available studies. Discussion In this umbrella review, we focus on the descriptive summary of included papers. Much wasting time and resources could be avoided if referring to previous reviews and following methodological guidelines. Due to the low credibility of evidence and flawed reporting, any recommendation about automated COVID-19 clinical diagnosis from medical images using AI at this point cannot be provided. Funding PO was supported by NIH grant AI116794 (the funding body had no role in the design, in any stage of the review, or in writing the manuscript); PJ and DS did not receive any funding. Registration The protocol of this review was registered on the OSF platform [1].
- 9 April 2020
- Published by Springer Nature
- p. 135-150
Benchmarking Manifold Learning Methods on a Large Collection of Datasets
- 9 April 2020
- Published by Springer Nature
- p. 135-150
Benchmarking Manifold Learning Methods on a Large Collection of Datasets
- Open Access
- 9 July 2019
- Published by Springer Nature in BioData Mining
- Vol. 12 (1) , 1-16
Exploration of a diversity of computational and statistical measures of association for genome-wide genetic studies
The principal line of investigation in Genome Wide Association Studies (GWAS) is the identification of main effects, that is individual Single Nucleotide Polymorphisms (SNPs) which are associated with the trait of interest, independent of other factors. A variety of methods have been proposed to this end, mostly statistical in nature and differing in assumptions and type of model employed. Moreover, for a given model, there may be multiple choices for the SNP genotype encoding. As an alternative to statistical methods, machine learning methods are often applicable. Typically, for a given GWAS, a single approach is selected and utilized to identify potential SNPs of interest. Even when multiple GWAS are combined through meta-analyses within a consortium, each GWAS is typically analyzed with a single approach and the resulting summary statistics are then utilized in meta-analyses. In this work we use as case studies a Type 2 Diabetes (T2D) and a breast cancer GWAS to explore a diversity of applicable approaches spanning different methods and encoding choices. We assess similarity of these approaches based on the derived ranked lists of SNPs and, for each GWAS, we identify a subset of representative approaches that we use as an ensemble to derive a union list of top SNPs. Among these are SNPs which are identified by multiple approaches as well as several SNPs identified by only one or a few of the less frequently used approaches. The latter include SNPs from established loci and SNPs which have other supporting lines of evidence in terms of their potential relevance to the traits. Not every main effect analysis method is suitable for every GWAS, but for each GWAS there are typically multiple applicable methods and encoding options. We suggest a workflow for a single GWAS, extensible to multiple GWAS from consortia, where representative approaches are selected among a pool of suitable options, to yield a more comprehensive set of SNPs, potentially including SNPs that would typically be missed with the most popular analyses, but that could provide additional valuable insights for follow-up.
- 9 July 2019
- Published by Springer Nature in BioData Mining
- Vol. 12 (1) , 1-16
Open AccessExploration of a diversity of computational and statistical measures of association for genome-wide genetic studies
The principal line of investigation in Genome Wide Association Studies (GWAS) is the identification of main effects, that is individual Single Nucleotide Polymorphisms (SNPs) which are associated with the trait of interest, independent of other factors. A variety of methods have been proposed to this end, mostly statistical in nature and differing in assumptions and type of model employed. Moreover, for a given model, there may be multiple choices for the SNP genotype encoding. As an alternative to statistical methods, machine learning methods are often applicable. Typically, for a given GWAS, a single approach is selected and utilized to identify potential SNPs of interest. Even when multiple GWAS are combined through meta-analyses within a consortium, each GWAS is typically analyzed with a single approach and the resulting summary statistics are then utilized in meta-analyses. In this work we use as case studies a Type 2 Diabetes (T2D) and a breast cancer GWAS to explore a diversity of applicable approaches spanning different methods and encoding choices. We assess similarity of these approaches based on the derived ranked lists of SNPs and, for each GWAS, we identify a subset of representative approaches that we use as an ensemble to derive a union list of top SNPs. Among these are SNPs which are identified by multiple approaches as well as several SNPs identified by only one or a few of the less frequently used approaches. The latter include SNPs from established loci and SNPs which have other supporting lines of evidence in terms of their potential relevance to the traits. Not every main effect analysis method is suitable for every GWAS, but for each GWAS there are typically multiple applicable methods and encoding options. We suggest a workflow for a single GWAS, extensible to multiple GWAS from consortia, where representative approaches are selected among a pool of suitable options, to yield a more comprehensive set of SNPs, potentially including SNPs that would typically be missed with the most popular analyses, but that could provide additional valuable insights for follow-up.
- Open Access
- 28 June 2019
- Published by Oxford University Press (OUP) in GigaScience
- Vol. 8 (7)
Scalable biclustering — the future of big data exploration?
Biclustering is a technique of discovering local similarities within data. For many years the complexity of the methods and parallelization issues limited its application to big data problems. With the development of novel scalable methods, biclustering has finally started to close this gap. In this paper we discuss the caveats of biclustering and present its current challenges and guidelines for practitioners. We also try to explain why biclustering may soon become one of the standards for big data analytics.
- 28 June 2019
- Published by Oxford University Press (OUP) in GigaScience
- Vol. 8 (7)
Open AccessScalable biclustering — the future of big data exploration?
Biclustering is a technique of discovering local similarities within data. For many years the complexity of the methods and parallelization issues limited its application to big data problems. With the development of novel scalable methods, biclustering has finally started to close this gap. In this paper we discuss the caveats of biclustering and present its current challenges and guidelines for practitioners. We also try to explain why biclustering may soon become one of the standards for big data analytics.