Sergiusz Wesolowski
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
Sergiusz Wesolowski has a total of 57 co-authors. Here are the top co-authors by number of shared publications:
- Gordon Lemmon
Department of Human Genetics, University of Utah, Salt Lake City, USA
4 shared publications - Mark Yandell
Department of Human Genetics, University of Utah, Salt Lake City, USA
4 shared publications Alex Henrie
Affiliation Department of Human Genetics and Utah Center for Genetic Discovery, University of Utah, Salt Lake City, UT, United States of America
3 shared publications- Martin Tristani-Firouzi
University of Utah
3 shared publications - H. Joseph Yost
Department of Human Genetics, University of Utah and School of Medicine
2 shared publications Michael D. Puchalski
Affiliation Division of Pediatric Cardiology, University of Utah School of Medicine, Salt Lake City, UT, United States of America
2 shared publications
Latest Publications
- Open Access
- 18 January 2022
- Published by Public Library of Science (PLoS) in PLOS Digital Health
- Vol. 1 (1) , e0000004
An explainable artificial intelligence approach for predicting cardiovascular outcomes using electronic health records
Understanding the conditionally-dependent clinical variables that drive cardiovascular health outcomes is a major challenge for precision medicine. Here, we deploy a recently developed massively scalable comorbidity discovery method called Poisson Binomial based Comorbidity discovery (PBC), to analyze Electronic Health Records (EHRs) from the University of Utah and Primary Children’s Hospital (over 1.6 million patients and 77 million visits) for comorbid diagnoses, procedures, and medications. Using explainable Artificial Intelligence (AI) methodologies, we then tease apart the intertwined, conditionally-dependent impacts of comorbid conditions and demography upon cardiovascular health, focusing on the key areas of heart transplant, sinoatrial node dysfunction and various forms of congenital heart disease. The resulting multimorbidity networks make possible wide-ranging explorations of the comorbid and demographic landscapes surrounding these cardiovascular outcomes, and can be distributed as web-based tools for further community-based outcomes research. The ability to transform enormous collections of EHRs into compact, portable tools devoid of Protected Health Information solves many of the legal, technological, and data-scientific challenges associated with large-scale EHR analyses.
- 18 January 2022
- Published by Public Library of Science (PLoS) in PLOS Digital Health
- Vol. 1 (1) , e0000004
Open AccessAn explainable artificial intelligence approach for predicting cardiovascular outcomes using electronic health records
Understanding the conditionally-dependent clinical variables that drive cardiovascular health outcomes is a major challenge for precision medicine. Here, we deploy a recently developed massively scalable comorbidity discovery method called Poisson Binomial based Comorbidity discovery (PBC), to analyze Electronic Health Records (EHRs) from the University of Utah and Primary Children’s Hospital (over 1.6 million patients and 77 million visits) for comorbid diagnoses, procedures, and medications. Using explainable Artificial Intelligence (AI) methodologies, we then tease apart the intertwined, conditionally-dependent impacts of comorbid conditions and demography upon cardiovascular health, focusing on the key areas of heart transplant, sinoatrial node dysfunction and various forms of congenital heart disease. The resulting multimorbidity networks make possible wide-ranging explorations of the comorbid and demographic landscapes surrounding these cardiovascular outcomes, and can be distributed as web-based tools for further community-based outcomes research. The ability to transform enormous collections of EHRs into compact, portable tools devoid of Protected Health Information solves many of the legal, technological, and data-scientific challenges associated with large-scale EHR analyses.
- Open Access
An Explainable Artificial Intelligence Approach for Predicting Cardiovascular Outcomes using Electronic Health Records
Understanding the conditionally-dependent clinical variables that drive cardiovascular health outcomes is a major challenge for precision medicine. Here, we deploy a recently developed massively scalable comorbidity discovery method called Poisson Binomial based Comorbidity discovery (PBC), to analyze Electronic Health Records (EHRs) from the University of Utah and Primary Children’s Hospital (over 1.6 million patients and 77 million visits) for comorbid diagnoses, procedures, and medications. Using explainable Artificial Intelligence (AI) methodologies, we then tease apart the intertwined, conditionally-dependent impacts of comorbid conditions and demography upon cardiovascular health, focusing on the key areas of heart transplant, sinoatrial node dysfunction and various forms of congenital heart disease. The resulting multimorbidity networks make possible wide-ranging explorations of the comorbid and demographic landscapes surrounding these cardiovascular outcomes, and can be distributed as web-based tools for further community-based outcomes research. The ability to transform enormous collections of EHRs into compact, portable tools devoid of Protected Health Information solves many of the legal, technological, and data-scientific challenges associated with large-scale EHR analyzes.
Open AccessAn Explainable Artificial Intelligence Approach for Predicting Cardiovascular Outcomes using Electronic Health Records
Understanding the conditionally-dependent clinical variables that drive cardiovascular health outcomes is a major challenge for precision medicine. Here, we deploy a recently developed massively scalable comorbidity discovery method called Poisson Binomial based Comorbidity discovery (PBC), to analyze Electronic Health Records (EHRs) from the University of Utah and Primary Children’s Hospital (over 1.6 million patients and 77 million visits) for comorbid diagnoses, procedures, and medications. Using explainable Artificial Intelligence (AI) methodologies, we then tease apart the intertwined, conditionally-dependent impacts of comorbid conditions and demography upon cardiovascular health, focusing on the key areas of heart transplant, sinoatrial node dysfunction and various forms of congenital heart disease. The resulting multimorbidity networks make possible wide-ranging explorations of the comorbid and demographic landscapes surrounding these cardiovascular outcomes, and can be distributed as web-based tools for further community-based outcomes research. The ability to transform enormous collections of EHRs into compact, portable tools devoid of Protected Health Information solves many of the legal, technological, and data-scientific challenges associated with large-scale EHR analyzes.
- Open Access
A Poisson binomial based statistical testing framework for comprehensive comorbidity discovery across massive Electronic Health Record datasets
Discovery of comorbidities (the concomitant occurrence of distinct medical conditions in the same patient) is a prerequisite for creating forecasting tools for downstream outcomes research. Current comorbidity discovery applications are designed for small datasets and use stratification to control for confounding variables such as age, sex, or ancestry. Stratification lowers false positive rates, but reduces power, as the size of the study cohort is decreased. Here, we describe a Poisson Binomial based approach to comorbidity discovery (PBC) designed for big-data applications that circumvents the need for stratification. PBC adjusts for confounding demographic variables on a per-patient basis, and models temporal relationships. We benchmark PBC using two datasets, the publicly available MIMIC-IV; and the entire Electronic Health Record (EHR) corpus of the University of Utah Hospital System, encompassing over 1.6 million patients, to compute comorbidity statistics on 4,623,841 pairs of potentially comorbid medical terms. The results of this computation are provided as a searchable web resource. Compared to current methods, the PBC approach reduces false positive associations, while retaining statistical power to discover true comorbidities.
Open AccessA Poisson binomial based statistical testing framework for comprehensive comorbidity discovery across massive Electronic Health Record datasets
Discovery of comorbidities (the concomitant occurrence of distinct medical conditions in the same patient) is a prerequisite for creating forecasting tools for downstream outcomes research. Current comorbidity discovery applications are designed for small datasets and use stratification to control for confounding variables such as age, sex, or ancestry. Stratification lowers false positive rates, but reduces power, as the size of the study cohort is decreased. Here, we describe a Poisson Binomial based approach to comorbidity discovery (PBC) designed for big-data applications that circumvents the need for stratification. PBC adjusts for confounding demographic variables on a per-patient basis, and models temporal relationships. We benchmark PBC using two datasets, the publicly available MIMIC-IV; and the entire Electronic Health Record (EHR) corpus of the University of Utah Hospital System, encompassing over 1.6 million patients, to compute comorbidity statistics on 4,623,841 pairs of potentially comorbid medical terms. The results of this computation are provided as a searchable web resource. Compared to current methods, the PBC approach reduces false positive associations, while retaining statistical power to discover true comorbidities.
- 20 February 2020
- Published by American Society of Clinical Oncology (ASCO) in Journal of Clinical Oncology
- Vol. 38 (6_suppl) , 570
Genomic correlates of response to PD-1 axis inhibitors (IO) in metastatic urothelial cancer (mUC) using explainable artificial intelligence (AI).
570 Background: AI is increasingly being used in clinical cancer genomics research. Probabilistic Graphical Models (PGMs) are AI algorithms that capture multivariate, mutli-level dependencies in complex patterns in large datasets while retaining human interpretability. We hypothesize that PGMs can identify clinical and genomic features that correlate with IO response in patients (pts) with mUC. Methods: In this retrospective study eligibility criteria were: diagnosis of mUC, receipt of IO for mUC, comprehensive genomic profiling data available from CLIA certified labs. The Bayesian Network (BN, PGM based AI) was used to discover clinical characteristics and selected genomic alterations relevant to IO response by RECIST 1.1 (investigator assessed). Results: Overall, 95 pts (73 men) with mUC were evaluated. 45 (47%) were ever smokers.The presented BN correctly captured the clinical landscape of mUC explaining significant relationship between included variables (pde novo metastasis had higher TMB and better response to IO. Inactivating MLL2 alterations were more prevalent in non-smokers, and negatively correlated with response to IO. FGFR3 alterations did not predict response to IO. Significant associations are presented in Table. Conclusions: These hypothesis-generating data (by a novel approach, i.e. PGM based AI) showed that smoking and high-TMB were associated with improved response to IO; in contrast, inactivating MLL2 alternations and visceral metastasis predicted inferior response. FGFR3 alterations did not correlate with response. This model validated previous findings and found new hypothesis-generating relationship, such as altered MLL2 gene; external validation is needed.
- 20 February 2020
- Published by American Society of Clinical Oncology (ASCO) in Journal of Clinical Oncology
- Vol. 38 (6_suppl) , 570
Genomic correlates of response to PD-1 axis inhibitors (IO) in metastatic urothelial cancer (mUC) using explainable artificial intelligence (AI).
570 Background: AI is increasingly being used in clinical cancer genomics research. Probabilistic Graphical Models (PGMs) are AI algorithms that capture multivariate, mutli-level dependencies in complex patterns in large datasets while retaining human interpretability. We hypothesize that PGMs can identify clinical and genomic features that correlate with IO response in patients (pts) with mUC. Methods: In this retrospective study eligibility criteria were: diagnosis of mUC, receipt of IO for mUC, comprehensive genomic profiling data available from CLIA certified labs. The Bayesian Network (BN, PGM based AI) was used to discover clinical characteristics and selected genomic alterations relevant to IO response by RECIST 1.1 (investigator assessed). Results: Overall, 95 pts (73 men) with mUC were evaluated. 45 (47%) were ever smokers.The presented BN correctly captured the clinical landscape of mUC explaining significant relationship between included variables (pde novo metastasis had higher TMB and better response to IO. Inactivating MLL2 alterations were more prevalent in non-smokers, and negatively correlated with response to IO. FGFR3 alterations did not predict response to IO. Significant associations are presented in Table. Conclusions: These hypothesis-generating data (by a novel approach, i.e. PGM based AI) showed that smoking and high-TMB were associated with improved response to IO; in contrast, inactivating MLL2 alternations and visceral metastasis predicted inferior response. FGFR3 alterations did not correlate with response. This model validated previous findings and found new hypothesis-generating relationship, such as altered MLL2 gene; external validation is needed.
- Open Access
- 17 October 2019
- Published by Springer Nature in Nature Communications
- Vol. 10 (1) , 1-12
De novo and recessive forms of congenital heart disease have distinct genetic and phenotypic landscapes
The genetic architecture of sporadic congenital heart disease (CHD) is characterized by enrichment in damaging de novo variants in chromatin-modifying genes. To test the hypothesis that gene pathways contributing to de novo forms of CHD are distinct from those for recessive forms, we analyze 2391 whole-exome trios from the Pediatric Cardiac Genomics Consortium. We deploy a permutation-based gene-burden analysis to identify damaging recessive and compound heterozygous genotypes and disease genes, controlling for confounding effects, such as background mutation rate and ancestry. Cilia-related genes are significantly enriched for damaging rare recessive genotypes, but comparatively depleted for de novo variants. The opposite trend is observed for chromatin-modifying genes. Other cardiac developmental gene classes have less stratification by mode of inheritance than cilia and chromatin-modifying gene classes. Our analyses reveal dominant and recessive CHD are associated with distinct gene functions, with cilia-related genes providing a reservoir of rare segregating variation leading to CHD.
- 17 October 2019
- Published by Springer Nature in Nature Communications
- Vol. 10 (1) , 1-12
Open AccessDe novo and recessive forms of congenital heart disease have distinct genetic and phenotypic landscapes
The genetic architecture of sporadic congenital heart disease (CHD) is characterized by enrichment in damaging de novo variants in chromatin-modifying genes. To test the hypothesis that gene pathways contributing to de novo forms of CHD are distinct from those for recessive forms, we analyze 2391 whole-exome trios from the Pediatric Cardiac Genomics Consortium. We deploy a permutation-based gene-burden analysis to identify damaging recessive and compound heterozygous genotypes and disease genes, controlling for confounding effects, such as background mutation rate and ancestry. Cilia-related genes are significantly enriched for damaging rare recessive genotypes, but comparatively depleted for de novo variants. The opposite trend is observed for chromatin-modifying genes. Other cardiac developmental gene classes have less stratification by mode of inheritance than cilia and chromatin-modifying gene classes. Our analyses reveal dominant and recessive CHD are associated with distinct gene functions, with cilia-related genes providing a reservoir of rare segregating variation leading to CHD.
- 1 October 2017
- Published by Elsevier in Computational Biology and Chemistry
- Vol. 70, 56-64
SRSF shape analysis for sequencing data reveal new differentiating patterns
- 1 October 2017
- Published by Elsevier in Computational Biology and Chemistry
- Vol. 70, 56-64
SRSF shape analysis for sequencing data reveal new differentiating patterns
- Open Access
SRSF shape analysis for sequencing data reveal new differentiating patterns
Motivation: Sequencing-based methods to examine fundamental features of the genome, such as gene expression and chromatin structure, rely on inferences from the abundance and distribution of reads derived from Illumina sequencing. Drawing sound inferences from such experiments relies on appropriate mathematical methods to model the distribution of reads along the genome, which has been challenging due to the scale and nature of these data. Results: We propose a new framework (SRSFseq) based on Square Root Slope Functions shape analysis to analyse Illumina sequencing data. In the new approach the basic unit of information is the density of mapped reads over region of interest located on the known reference genome. The densities are interpreted as shapes and a new shape analysis model is proposed. An equivalent of a Fisher test is used to quantify the significance of shape differences in read distribution patterns between groups of density functions in different experimental conditions. We evaluated the performance of this new framework to analyze RNA-seq data at the exon level, which enabled the detection of variation in read distributions and abundances between experimental conditions not detected by other methods. Thus, the method is a suitable supplement to the state of the are count based techniques. The variety of density representations and flexibility of mathematical design allow the model to be easily adapted to other data types or problems in which the distribution of reads is to be tested. The functional interpretation and SRSF phase-amplitude separation technique gives an efficient noise reduction procedure improving the sensitivity and specificity of the method.
Open AccessSRSF shape analysis for sequencing data reveal new differentiating patterns
Motivation: Sequencing-based methods to examine fundamental features of the genome, such as gene expression and chromatin structure, rely on inferences from the abundance and distribution of reads derived from Illumina sequencing. Drawing sound inferences from such experiments relies on appropriate mathematical methods to model the distribution of reads along the genome, which has been challenging due to the scale and nature of these data. Results: We propose a new framework (SRSFseq) based on Square Root Slope Functions shape analysis to analyse Illumina sequencing data. In the new approach the basic unit of information is the density of mapped reads over region of interest located on the known reference genome. The densities are interpreted as shapes and a new shape analysis model is proposed. An equivalent of a Fisher test is used to quantify the significance of shape differences in read distribution patterns between groups of density functions in different experimental conditions. We evaluated the performance of this new framework to analyze RNA-seq data at the exon level, which enabled the detection of variation in read distributions and abundances between experimental conditions not detected by other methods. Thus, the method is a suitable supplement to the state of the are count based techniques. The variety of density representations and flexibility of mathematical design allow the model to be easily adapted to other data types or problems in which the distribution of reads is to be tested. The functional interpretation and SRSF phase-amplitude separation technique gives an efficient noise reduction procedure improving the sensitivity and specificity of the method.
- 1 June 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Shape-based data analysis for event classification in power systems
Fault classification in power systems is a challenging and complex task as the variety and variability of the electrical parameters of the various network components in spatial and temporal scales. The majority of machine learning methods for event detection require the labeled data sets or examples of previous events. However, the recorded event data happen in different locations, time and system conditions. Therefore, they are not aligned time-series which introduce more challenges for feature selection and signal processing. To perform better feature selection for time-series measurements, shape-based methods along with time alignment (also called registration) are needed. This paper presents the Fisher-Rao Registration Method (FRMM) as a solution for the alignment of different time signals. Amplitude and phase components resulting from the Fisher-Rao registration method provide a means for implementing a hierarchical clustering analysis classifying different fault events by type. The algorithm was tested with the IEEE 13-nodes test feeder simulated in RSCAD environment with over 1500 different fault events presenting an average prediction rate of 98%.
- 1 June 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Shape-based data analysis for event classification in power systems
Fault classification in power systems is a challenging and complex task as the variety and variability of the electrical parameters of the various network components in spatial and temporal scales. The majority of machine learning methods for event detection require the labeled data sets or examples of previous events. However, the recorded event data happen in different locations, time and system conditions. Therefore, they are not aligned time-series which introduce more challenges for feature selection and signal processing. To perform better feature selection for time-series measurements, shape-based methods along with time alignment (also called registration) are needed. This paper presents the Fisher-Rao Registration Method (FRMM) as a solution for the alignment of different time signals. Amplitude and phase components resulting from the Fisher-Rao registration method provide a means for implementing a hierarchical clustering analysis classifying different fault events by type. The algorithm was tested with the IEEE 13-nodes test feeder simulated in RSCAD environment with over 1500 different fault events presenting an average prediction rate of 98%.
- Open Access
- 1 September 2015
- Published by Institute of Mathematical Statistics in The Annals of Applied Statistics
- Vol. 9 (3) , 1278-1297
A new framework for Euclidean summary statistics in the neural spike train space
Statistical analysis and inference on spike trains is one of the central topics in the neural coding. It is of great interest to understand the underlying structure of given neural data. Based on the metric distances between spike trains, recent investigations have introduced the notion of an average or prototype spike train to characterize the template pattern in the neural activity. However, as those metrics lack certain Euclidean properties, the defined averages are nonunique, and do not share the conventional properties of a mean. In this article, we propose a new framework to define the mean spike train where we adopt a Euclidean-like metric from an $L^{p}$ family. We demonstrate that this new mean spike train properly represents the average pattern in the conventional fashion, and can be effectively computed using a theoretically-proven convergent procedure. We compare this mean with other spike train averages and demonstrate its superiority. Furthermore, we apply the new framework in a recording from rodent geniculate ganglion, where background firing activity is a common issue for neural coding. We show that the proposed mean spike train can be utilized to remove the background noise and improve decoding performance.- 1 September 2015
- Published by Institute of Mathematical Statistics in The Annals of Applied Statistics
- Vol. 9 (3) , 1278-1297
Open AccessA new framework for Euclidean summary statistics in the neural spike train space
Statistical analysis and inference on spike trains is one of the central topics in the neural coding. It is of great interest to understand the underlying structure of given neural data. Based on the metric distances between spike trains, recent investigations have introduced the notion of an average or prototype spike train to characterize the template pattern in the neural activity. However, as those metrics lack certain Euclidean properties, the defined averages are nonunique, and do not share the conventional properties of a mean. In this article, we propose a new framework to define the mean spike train where we adopt a Euclidean-like metric from an $L^{p}$ family. We demonstrate that this new mean spike train properly represents the average pattern in the conventional fashion, and can be effectively computed using a theoretically-proven convergent procedure. We compare this mean with other spike train averages and demonstrate its superiority. Furthermore, we apply the new framework in a recording from rodent geniculate ganglion, where background firing activity is a common issue for neural coding. We show that the proposed mean spike train can be utilized to remove the background noise and improve decoding performance. - Open Access
- 28 June 2013
- Published by MDPI AG in Biosensors
- Vol. 3 (3) , 238-258
A Comparison of Methods for RNA-Seq Differential Expression Analysis and a New Empirical Bayes Approach
Transcriptome-based biosensors are expected to have a large impact on the future of biotechnology. However, a central aspect of transcriptomics is differential expression analysis, where, currently, deep RNA sequencing (RNA-seq) has the potential to replace the microarray as the standard assay for RNA quantification. Our contributions here to RNA-seq differential expression analysis are two-fold. First, given the high cost of an RNA-seq run, biological replicates are rare, and therefore, information sharing across genes to obtain variance estimates is crucial. To handle such information sharing in a rigorous manner, we propose an hierarchical, empirical Bayes approach (R-EBSeq) that combines the Cufflinks model for generating relative transcript abundance measurements, known as FPKM (fragments per kilobase of transcript length per million mapped reads) with the EBArrays framework, which was previously developed for empirical Bayes analysis of microarray data. A desirable feature of R-EBSeq is easy-to-implement analysis of more than pairwise comparisons, as we illustrate with experimental data. Secondly, we develop the standard RNA-seq test data set, on the level of reads, where 79 transcripts are artificially differentially expressed and, therefore, explicitly known. This test data set allows us to compare the performance, in terms of the true discovery rate, of R-EBSeq to three other widely used RNAseq data analysis packages: Cuffdiff, DEseq and BaySeq. Our analysis indicates that DESeq identifies the first half of the differentially expressed transcripts well, but then is outperformed by Cuffdiff and R-EBSeq. Cuffdiff and R-EBSeq are the two top performers. Thus, R-EBSeq offers good performance, while allowing flexible and rigorous comparison of multiple biological conditions.
- 28 June 2013
- Published by MDPI AG in Biosensors
- Vol. 3 (3) , 238-258
Open AccessA Comparison of Methods for RNA-Seq Differential Expression Analysis and a New Empirical Bayes Approach
Transcriptome-based biosensors are expected to have a large impact on the future of biotechnology. However, a central aspect of transcriptomics is differential expression analysis, where, currently, deep RNA sequencing (RNA-seq) has the potential to replace the microarray as the standard assay for RNA quantification. Our contributions here to RNA-seq differential expression analysis are two-fold. First, given the high cost of an RNA-seq run, biological replicates are rare, and therefore, information sharing across genes to obtain variance estimates is crucial. To handle such information sharing in a rigorous manner, we propose an hierarchical, empirical Bayes approach (R-EBSeq) that combines the Cufflinks model for generating relative transcript abundance measurements, known as FPKM (fragments per kilobase of transcript length per million mapped reads) with the EBArrays framework, which was previously developed for empirical Bayes analysis of microarray data. A desirable feature of R-EBSeq is easy-to-implement analysis of more than pairwise comparisons, as we illustrate with experimental data. Secondly, we develop the standard RNA-seq test data set, on the level of reads, where 79 transcripts are artificially differentially expressed and, therefore, explicitly known. This test data set allows us to compare the performance, in terms of the true discovery rate, of R-EBSeq to three other widely used RNAseq data analysis packages: Cuffdiff, DEseq and BaySeq. Our analysis indicates that DESeq identifies the first half of the differentially expressed transcripts well, but then is outperformed by Cuffdiff and R-EBSeq. Cuffdiff and R-EBSeq are the two top performers. Thus, R-EBSeq offers good performance, while allowing flexible and rigorous comparison of multiple biological conditions.