{"title":"Robust Diagnosis of Acute Bacterial and Viral Infections via Host Gene Expression Rank-Based Ensemble Machine Learning Algorithm: A Multi-Cohort Model Development and Validation Study.","authors":"Yifei Shen,Dongsheng Han,Wenxin Qu,Fei Yu,Dan Zhang,Yifan Xu,Enhui Shen,Qinjie Chu,Michael P Timko,Longjiang Fan,Shufa Zheng,Yu Chen","doi":"10.1093/clinchem/hvae220","DOIUrl":"https://doi.org/10.1093/clinchem/hvae220","url":null,"abstract":"BACKGROUNDThe accurate and prompt diagnosis of infections is essential for improving patient outcomes and preventing bacterial drug resistance. Host gene expression profiling as an approach to infection diagnosis holds great potential in assisting early and accurate diagnosis of infection.METHODSTo improve the precision of infection diagnosis, we developed InfectDiagno, a rank-based ensemble machine learning algorithm for infection diagnosis via host gene expression patterns. Eleven data sets were used as training data sets for the method development, and the InfectDiagno algorithm was optimized by multi-cohort training samples. Nine data sets were used as independent validation data sets for the method. We further validated the diagnostic capacity of InfectDiagno in a prospective clinical cohort.RESULTSAfter selecting 100 feature genes based on their gene expression ranks for infection prediction, we trained a classifier using both a noninfected-vs-infected area under the receiver-operating characteristic curve (area under the curve [AUC] 0.95 [95% CI, 0.93-0.97]) and a bacterial-vs-viral AUC 0.95 (95% CI, 0.93-0.97). We then used the noninfected/infected classifier together with the bacterial/viral classifier to build a discriminating infection diagnosis model. The sensitivity was 0.931 and 0.872, and specificity 0.963 and 0.929, for bacterial and viral infections, respectively. We then applied InfectDiagno to a prospective clinical cohort (n = 517), and found it classified 95% of the samples correctly.CONCLUSIONSOur study shows that the InfectDiagno algorithm is a powerful and robust tool to accurately identify infection in a real-world patient population, which has the potential to profoundly improve clinical care in the field of infection diagnosis.","PeriodicalId":10690,"journal":{"name":"Clinical chemistry","volume":"10 1","pages":""},"PeriodicalIF":9.3,"publicationDate":"2025-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142991730","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Brendan V Graham, Stephen R Master, Amrom E Obstfeld, Robert B Wilson
{"title":"A Multianalyte Machine Learning Model to Detect Wrong Blood in Complete Blood Count Tube Errors in a Pediatric Setting","authors":"Brendan V Graham, Stephen R Master, Amrom E Obstfeld, Robert B Wilson","doi":"10.1093/clinchem/hvae210","DOIUrl":"https://doi.org/10.1093/clinchem/hvae210","url":null,"abstract":"Background Multianalyte machine learning (ML) models can potentially identify previously undetectable wrong blood in tube (WBIT) errors, improving upon current single-analyte delta check methodology. However, WBIT detection model performance has not been assessed in a real-world, low-prevalence context. To estimate real-world positive predictive values, we propose a methodology to assess WBIT detection models by evaluating the impact of missing data and by using a “low prevalence” validation data set. Methods We trained a range of model specifications using various predictors in a pediatric setting. We assessed the top-performing model on a modified, “low prevalence” validation data set across a range of probability thresholds. Model performance was also compared to a pre-positive patient identification (pre-PPID) dataset. Results An Extreme Gradient Boosting (XGBoost) model with minimal preprocessing performed the best for both complete blood count with differential white cell count (CBC with Diff) tests (accuracy 0.9715) and complete blood count without differential white cell count (CBC without Diff) tests (accuracy 0.9647). Assessment on a downsampled, “low prevalence” validation data set resulted in estimated positive predictive values ranging from 0.01 to 0.67 (CBC with Diff) and 0.01 to 0.75 (CBC without Diff), depending on the probability threshold chosen. A comparison of prospective performance to PPID data demonstrated a large decrease in estimated WBIT errors. Conclusions We find that ML models can accurately predict WBITs in a primarily pediatric setting. Evaluating model performance across a range of probability thresholds minimizes the number of false positives while still providing added safety benefits. The decrease in estimated WBITS post-PPID implementation shows the potential safety benefits of a WBIT model for hospitals not using PPID when collecting laboratory specimens.","PeriodicalId":10690,"journal":{"name":"Clinical chemistry","volume":"26 1","pages":""},"PeriodicalIF":9.3,"publicationDate":"2025-01-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142962793","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Mareva Delporte, Laurens Lambrechts, Evy E Blomme, Willem van Snippenberg, Sofie Rutsaert, Maxime Verschoore, Evelien De Smet, Ytse Noppe, Nele De Langhe, Marie-Angélique De Scheerder, Sarah Gerlo, Linos Vandekerckhove, Wim Trypsteen
{"title":"Integrative Assessment of Total and Intact HIV-1 Reservoir by a 5-Region Multiplexed Rainbow DNA Digital PCR Assay.","authors":"Mareva Delporte, Laurens Lambrechts, Evy E Blomme, Willem van Snippenberg, Sofie Rutsaert, Maxime Verschoore, Evelien De Smet, Ytse Noppe, Nele De Langhe, Marie-Angélique De Scheerder, Sarah Gerlo, Linos Vandekerckhove, Wim Trypsteen","doi":"10.1093/clinchem/hvae192","DOIUrl":"10.1093/clinchem/hvae192","url":null,"abstract":"<p><strong>Background: </strong>Persistent latent reservoirs of intact HIV-1 proviruses, capable of rebounding despite suppressive antiretroviral therapy (ART), hinder efforts towards an HIV-1 cure. Hence, assays specifically quantifying intact proviruses are crucial to assess the impact of curative interventions. Two recent assays have been utilized in clinical trials: intact proviral DNA assay (IPDA) and quadruplex quantitative PCR (Q4PCR). While IPDA is more sensitive due to amplifying short fragments, it may overestimate intact fractions by relying only on quantification of 2 proviral regions. Q4PCR samples 4 proviral regions, yet is sequencing-based, favoring amplification of shorter, hence non-intact, proviral sequences.</p><p><strong>Methods: </strong>Leveraging digital PCR (dPCR) advancements, we developed the \"Rainbow\" 5-plex proviral HIV-1 DNA assay. This first-in-its-kind assay was evaluated using standard materials and samples from 83 people living with HIV-1, enabling simultaneous quantification of both total and intact HIV-1 DNA levels. HIV proviral unique molecular identifier (UMI)-mediated long-read sequencing (HIV-PULSE) was used to validate the specificity of the Rainbow HIV-1 DNA assay.</p><p><strong>Results: </strong>The Rainbow assay proved equally sensitive but more specific than IPDA and is not subjected to bias against full-length proviruses, enabling high-throughput quantification of total and intact reservoir size. The near full-length sequences allowed validation of the Rainbow specificity and the design of personalized Rainbow primer/probe sets, which enabled the detection of intact HIV-1 DNA.</p><p><strong>Conclusions: </strong>This innovation offers potential for targeted evaluation and monitoring of potential rebound-competent reservoirs, contributing to HIV-1 management and cure strategies. ClinicalTrials.gov Registration Numbers: NCT04553081, NCT04305665.</p>","PeriodicalId":10690,"journal":{"name":"Clinical chemistry","volume":"71 1","pages":"203-214"},"PeriodicalIF":7.1,"publicationDate":"2025-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142920941","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"From the Perspective of the Child: Ethical Considerations for the Implementation of Genomic Sequencing into Neonatal and Pediatric Care.","authors":"Jill L Maron, Sharon F Terry","doi":"10.1093/clinchem/hvae112","DOIUrl":"https://doi.org/10.1093/clinchem/hvae112","url":null,"abstract":"","PeriodicalId":10690,"journal":{"name":"Clinical chemistry","volume":"71 1","pages":"18-20"},"PeriodicalIF":7.1,"publicationDate":"2025-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142921002","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Structural Variation Interpretation in the Genome Sequencing Era: Lessons from Cytogenetics.","authors":"Lucilla Pizzo, M Katharine Rudd","doi":"10.1093/clinchem/hvae186","DOIUrl":"https://doi.org/10.1093/clinchem/hvae186","url":null,"abstract":"<p><strong>Background: </strong>Structural variation (SV), defined as balanced and unbalanced chromosomal rearrangements >1 kb, is a major contributor to germline and neoplastic disease. Large variants have historically been evaluated by chromosome analysis and now are commonly recognized by chromosomal microarray analysis (CMA). The increasing application of genome sequencing (GS) in the clinic and the relatively high incidence of chromosomal abnormalities in sick newborns and children highlights the need for accurate SV interpretation and reporting. In this review, we describe SV patterns of common cytogenetic abnormalities for laboratorians who review GS data.</p><p><strong>Content: </strong>GS has the potential to detect diverse chromosomal abnormalities and sequence breakpoint junctions to clarify variant structure. No single GS analysis pipeline can detect all SV, and visualization of sequence data is crucial to recognize specific patterns. Here we describe genomic signatures of translocations, inverted duplications adjacent to terminal deletions, recombinant chromosomes, marker chromosomes, ring chromosomes, isodicentric and isochromosomes, and mosaic aneuploidy. Distinguishing these more complex abnormalities from simple deletions and duplications is critical for phenotypic interpretation and recurrence risk recommendations.</p><p><strong>Summary: </strong>Unlike single-nucleotide variant calling, identification of chromosome rearrangements by GS requires further processing and multiple callers. SV databases have caveats and limitations depending on the platform (CMA vs sequencing) and resolution (exome vs genome). In the rapidly evolving era of clinical genomics, where a single test can identify both sequence and structural variants, optimal patient care stems from the integration of molecular and cytogenetic expertise.</p>","PeriodicalId":10690,"journal":{"name":"Clinical chemistry","volume":"71 1","pages":"119-128"},"PeriodicalIF":7.1,"publicationDate":"2025-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142920300","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"DNA Sequencing in Newborn Screening: Opportunities, Challenges, and Future Directions.","authors":"Médéric Jeanne, Wendy K Chung","doi":"10.1093/clinchem/hvae180","DOIUrl":"https://doi.org/10.1093/clinchem/hvae180","url":null,"abstract":"<p><strong>Background: </strong>Newborn screening is a public health system designed to identify infants at risk for conditions early in life to facilitate timely intervention and treatment to prevent or mitigate adverse health outcomes. Newborn screening programs use tandem mass spectrometry as a platform to detect several treatable inborn errors of metabolism, and the T-cell receptor excision circle assay to detect some inborn errors of the immune system. Recent advancements in DNA sequencing have decreased the cost of sequencing and allow us to consider DNA sequencing as an additional platform to complement other newborn screening methods.</p><p><strong>Content: </strong>This review provides an overview of DNA-based newborn screening, including its applications, opportunities, challenges, and future directions. We discuss the potential benefits of expanded DNA sequencing in newborn screening, such as expanding conditions screened and improved specificity and sensitivity of currently screened conditions. Additionally, we examine the ethical, legal, and social implications of implementing genomic sequencing in newborn screening programs, including issues related to consent, privacy, equity, data interpretation, scalability, and psychosocial impact on families. Additionally, we explore emerging strategies for addressing current limitations and advancing the field of newborn screening.</p><p><strong>Summary: </strong>DNA sequencing in newborn screening has the potential to improve the diagnosis and management of rare diseases but also presents significant challenges that need to be addressed before implementation at the population level.</p>","PeriodicalId":10690,"journal":{"name":"Clinical chemistry","volume":"71 1","pages":"77-86"},"PeriodicalIF":7.1,"publicationDate":"2025-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142920999","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Virus Evolution in Prolonged Infections of Immunocompromised Individuals.","authors":"Zoe Raglow, Adam S Lauring","doi":"10.1093/clinchem/hvae150","DOIUrl":"10.1093/clinchem/hvae150","url":null,"abstract":"<p><strong>Background: </strong>Many viruses can cause persistent infection and/or viral shedding in immunocompromised hosts. This is a well-described occurrence not only with SARS-CoV-2 but for many other viruses as well. Understanding how viruses evolve and mutate in these patients and the global impact of this phenomenon is critical as the immunocompromised population expands.</p><p><strong>Content: </strong>In this review, we provide an overview of populations at risk for prolonged viral shedding, clinical manifestations of persistent viral infection, and methods of assessing viral evolution. We then review the literature on viral evolution in immunocompromised patients across an array of RNA viruses, including SARS-CoV-2, norovirus, influenza, and poliovirus, and discuss the global implications of persistent viral infections in these hosts.</p><p><strong>Summary: </strong>There is significant evidence for accelerated viral evolution and accumulation of mutations in antigenic sites in immunocompromised hosts across many viral pathogens. However, the implications of this phenomenon are not clear; while there are rare reports of transmission of these variants, they have not clearly been shown to predict disease outbreaks or have significant global relevance. Emerging methods including wastewater monitoring may provide a more sophisticated understanding of the impact of variants that evolve in immunocompromised hosts on the wider host population.</p>","PeriodicalId":10690,"journal":{"name":"Clinical chemistry","volume":"71 1","pages":"109-118"},"PeriodicalIF":7.1,"publicationDate":"2025-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11822857/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142920627","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Brianna Guarino, Adam S Ptolemy, Michelle A Baum, Melinda J Palma, Mark D Kellogg, Roy W A Peake
{"title":"Diagnostic Odyssey in a Child with Red-Colored Urine and Proteinuria.","authors":"Brianna Guarino, Adam S Ptolemy, Michelle A Baum, Melinda J Palma, Mark D Kellogg, Roy W A Peake","doi":"10.1093/clinchem/hvae090","DOIUrl":"https://doi.org/10.1093/clinchem/hvae090","url":null,"abstract":"","PeriodicalId":10690,"journal":{"name":"Clinical chemistry","volume":"71 1","pages":"31-34"},"PeriodicalIF":7.1,"publicationDate":"2025-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142920994","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Polygenic Risk Scores in Human Disease.","authors":"Dimitri J Maamari, Roukoz Abou-Karam, Akl C Fahed","doi":"10.1093/clinchem/hvae190","DOIUrl":"https://doi.org/10.1093/clinchem/hvae190","url":null,"abstract":"<p><strong>Background: </strong>Polygenic risk scores (PRS) are measures of genetic susceptibility to human health traits. With the advent of large data repositories combining genetic data and phenotypic information, PRS are providing valuable insights into the genetic architecture of complex diseases and are transforming the landscape of precision medicine.</p><p><strong>Content: </strong>PRS have emerged as tools with clinical utility in human disease. Herein, details on how to develop PRS are provided, followed by 5 areas in which they can be used to improve human health: (a) augmenting risk prediction, (b) refining diagnosis, (c) guiding treatment choices, (d) making clinical trials more efficient, and (e) improving public health. Finally, some of the ongoing challenges to the clinical implementation of PRS are noted.</p><p><strong>Summary: </strong>PRS can offer valuable information for providers and patients, including identifying risk of disease earlier in life and before the onset of clinical risk factors, guiding treatment decisions, improving public health outcomes, and making clinical trials more efficient. The future of genomic-informed risk assessments of disease is through integrated risk models that combine genetic factors including PRS, monogenic, and somatic DNA information with nongenetic risk factors such as clinical risk estimators and multiomic data. However, adopting PRS in a clinical setting at scale faces some challenges, including cross-ancestry performance, standardization and calibration of risk models, downstream clinical decision-making from risk information, and seamless integration into existing health systems.</p>","PeriodicalId":10690,"journal":{"name":"Clinical chemistry","volume":"71 1","pages":"69-76"},"PeriodicalIF":7.1,"publicationDate":"2025-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142921177","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Commentary on Diagnostic Odyssey in a Child with Red-Colored Urine and Proteinuria.","authors":"Marcus J Miller","doi":"10.1093/clinchem/hvae085","DOIUrl":"https://doi.org/10.1093/clinchem/hvae085","url":null,"abstract":"","PeriodicalId":10690,"journal":{"name":"Clinical chemistry","volume":"71 1","pages":"34-35"},"PeriodicalIF":7.1,"publicationDate":"2025-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142920982","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}