Correlation between locally versus centrally processed serum procalcitonin during emergency department research evaluation of febrile infants aged 0-60 days.

Introduction: Procalcitonin (PCT) is a useful biomarker in the initial evaluation of febrile infants for serious bacterial infections (SBIs). However, PCT is not always available locally and must at times be frozen and shipped to a reference laboratory for research studies. We sought to compare PCT measured locally versus centrally at a reference laboratory during a research study. Materials and methods: This was a secondary analysis of a multicenter study of febrile infants ≤60 days evaluated for SBIs from June 2016 to April 2019. A PCT cutoff value of 0.5 ng/mL was used to stratify infants at low-versus high-risk of SBIs. Statistical analyses consisted of Spearman's correlation, Bland-Altman difference plotting, Passing-Bablok regression, Deming regression, and Fisher's exact testing at the 0.5 ng/mL threshold. Results: 241 febrile infants had PCT levels measured both locally and at the reference laboratory. PCT levels measured locally on 5 different platforms and from the frozen research samples demonstrated strong Spearman's correlation (ρ = 0.83) and had similar mean PCT values with an average relative difference of 0.02%. Eleven infants with SBIs had PCT values < 0.5 ng/mL in both the clinical and research samples. Six other infants had differences in SBI prediction based on PCT values at the 0.5 ng/mL threshold between the clinical and research platforms. Conclusions: We found no significant differences in detection of febrile infants at high risk for SBI based on locally (on multiple platforms) versus centrally processed PCT. Testing at a central reference laboratory after freezing and shipping is an accurate and reliable alternative for research studies or when rapid turnaround is not required.

Commutability and Uncertainty of Blood Hemoglobin A1c Testing Materials.

BACKGROUND: Hemoglobin A1C (HbA1C) is used to evaluate glycemic control over a three-month period. Blood matrix-based HbA1C materials are needed for quality control and evaluation of HbA1C measurements. This study investigated the commutability of blood materials (BMs) and aimed to upgrade BMs for HbA1C testing for use as proficiency test (PT) material. METHODS: We measured BMs from a DM blood donor (n = 1), an in vitro glycation procedure (n = 3), and from commercial sources (n = 2) for HbA1C in parallel with fresh unprocessed BMs (n = 3) and clinical blood samples (n = 25). Two NGSP-certified methods, including a turbidimetric and an enzymatic immunoassay, were used for HbA1C determinations. Commutability as investigated according to CLSI EP14-Ed4 guidelines. RESULTS: The commutable BMs exhibited a mean paired difference of 0% to 9% when compared to reference methods, whereas the non-commutable BMs represented a mean paired difference of 3% to 11%. Fresh, unprocessed BMs with a low HbA1C of 6.0% were more commutable than BMs with a high HbA1C. The values of HbA1C in BMs (mean and uncertainty following ISO Guide 35 for RM production) were applied to upgrade the PT material to be used as a reference material. The relative uncertainty of BM-Ndm-1 and BM-Gcb-3 were 1 and 0.4%, respectively. CONCLUSIONS: The commutability of hemoglobin in BMs is dependent on the preparation process. Blood materials with a high HbA1C content are usually less commutable versus materials with low HbA1C content when prepared by the same process. Our study showed BMs can be successfully used as quality control or PT materials.

Not Carfentanil-A Case of Unexpected Xylazine Detection.

Historically, xylazine has been utilized in veterinary medicine for decades as an anesthetic and analgesic sedative to facilitate safe handling, diagnostic testing, and surgical procedures in large animals. Currently, xylazine is an emerging threat to human health. It has been detected in the illicit drug supply chain, often as an adulterant. It has been more commonly added to illicit substances, most notably fentanyl, by drugmakers to enhance drug effect. End users are often unaware of its presence. This is alarming given the large number of xylazine-involved overdose deaths while laboratory detections are deficient and reversal agents are absent. Herein, we present the first documented case of xylazine identified via gas chromatography-tandem mass spectrometry at University of California Davis Health despite a peculiarly mild clinical presentation. We hope to increase awareness of this potentially fatal adulterant that is often missed in evaluation and engender further opportunities to study this ongoing issue.

Comparator Data Characteristics and Testing Procedures for the Clinical Performance Evaluation of Continuous Glucose Monitoring Systems.

Comparing the performance of different continuous glucose monitoring (CGM) systems is challenging due to the lack of comprehensive guidelines for clinical study design. In particular, the absence of concise requirements for the distribution of comparator (reference) blood glucose (BG) concentrations and their rate of change (RoC) that are used to evaluate CGM performance, impairs comparability. For this article, several experts in the field of CGM performance testing have collaborated to propose characteristics of the distribution of comparator measurements that should be collected during CGM performance testing. Specifically, it is proposed that at least 7.5% of comparator BG concentrations are <70 mg/dL (3.9 mmol/L) and >300 mg/dL (16.7 mmol/L), respectively, and that at least 7.5% of BG-RoC combinations indicate fast BG changes with impending hypo- or hyperglycemia, respectively. These proposed characteristics of the comparator data can facilitate the harmonization of testing conditions across different studies and CGM systems and ensure that the most relevant scenarios representing real-life situations are established during performance testing. In addition, a study protocol and testing procedure for the manipulation of glucose levels are suggested that enable the collection of comparator data with these characteristics. This work is an important step toward establishing a future standard for the performance evaluation of CGM systems.

A study to assess the impact of the cobas point-of-care RT-PCR assay (SARS-CoV-2 and Influenza A/B) on patient clinical management in the emergency department of the University of California at Davis Medical Center.

BACKGROUND: Rapid detection of SARS-CoV-2 is crucial for reduction of transmission and clinical decision-making. Several rapid (<30 min) molecular point-of-care (POC) tests based on nucleic acid amplification exist for diagnosis of SARS-CoV-2 & Influenza A/B infections. METHODS: This unblinded, pre-post study enrolled consecutive patients with symptoms/signs consistent with SARS-CoV-2 infection presenting to the University of California, Davis emergency department (ED). Outcomes following implementation of the cobas® SARS-CoV-2 & Influenza A/B test for use on the cobas Liat System (intervention: December 2020-May 2021) were compared with previous standard-of-care using centralized laboratory reverse transcriptase polymerase chain reaction (RT-PCR) methods (control: April 2020-October 2020). RESULTS: Electronic health records of 8879 symptomatic patient visits were analyzed, comprising 4339 and 4540 visits and 538 and 638 positive SARS-CoV-2 PCR test results in the control and intervention periods, respectively. Compared with the control period, turnaround time (TAT) was shorter in the intervention period (median 0.98 vs 12.30 h; p < 0.0001). ED length of stay (LOS) was generally longer in the intervention period compared with the control period, but for those SARS-CoV-2-negative who were admitted, ED LOS was shorter (median 12.53 vs 17.93 h; p < 0.0001). The rate of antibiotic prescribing was lower in the intervention than in the control period (42.86% vs 49.16%; p < 0.0001) and antiviral prescribing was higher (7.64% vs 5.49%; p < 0.0001). CONCLUSION: This real-world study confirms faster TAT with a POC RT-PCR method in an emergency care setting and highlights the importance of rapid SARS-CoV-2 detection to aid patient management and inform treatment decisions.

Oxylipin concentration shift in exhaled breath condensate (EBC) of SARS-CoV-2 infected patients.

Infection of airway epithelial cells with severe acute respiratory coronavirus 2 (SARS-CoV-2) can lead to severe respiratory tract damage and lung injury with hypoxia. It is challenging to sample the lower airways non-invasively and the capability to identify a highly representative specimen that can be collected in a non-invasive way would provide opportunities to investigate metabolomic consequences of COVID-19 disease. In the present study, we performed a targeted metabolomic approach using liquid chromatography coupled with high resolution chromatography (LC-MS) on exhaled breath condensate (EBC) collected from hospitalized COVID-19 patients (COVID+) and negative controls, both non-hospitalized and hospitalized for other reasons (COVID-). We were able to noninvasively identify and quantify inflammatory oxylipin shifts and dysregulation that may ultimately be used to monitor COVID-19 disease progression or severity and response to therapy. We also expected EBC-based biochemical oxylipin changes associated with COVID-19 host response to infection. The results indicated ten targeted oxylipins showing significative differences between SAR-CoV-2 infected EBC samples and negative control subjects. These compounds were prostaglandins A2 and D2, LXA4, 5-HETE, 12-HETE, 15-HETE, 5-HEPE, 9-HODE, 13-oxoODE and 19(20)-EpDPA, which are associated with specific pathways (i.e. P450, COX, 15-LOX) related to inflammatory and oxidative stress processes. Moreover, all these compounds were up-regulated by COVID+, meaning their concentrations were higher in subjects with SAR-CoV-2 infection. Given that many COVID-19 symptoms are inflammatory in nature, this is interesting insight into the pathophysiology of the disease. Breath monitoring of these and other EBC metabolites presents an interesting opportunity to monitor key indicators of disease progression and severity.

Machine learning and artificial intelligence for the diagnosis of infectious diseases in immunocompromised patients.

PURPOSE OF REVIEW: Immunocompromised patients are at high risk for infection. During the coronavirus disease (COVID-19) pandemic, immunocompromised patients exhibited increased odds of intensive care unit admission and death. Early pathogen identification is essential to mitigating infection related risk in immunocompromised patients. Artificial intelligence (AI) and machine learning (ML) have tremendous appeal to address unmet diagnostic needs. These AI/ML tools often rely on the wealth of data found in healthcare to enhance our ability to identify clinically significant patterns of disease. To this end, our review provides an overview of the current AI/ML landscape as it applies to infectious disease testing with emphasis on immunocompromised patients. RECENT FINDINGS: Examples include AI/ML for predicting sepsis in high risk burn patients. Likewise, ML is utilized to analyze complex host-response proteomic data to predict respiratory infections including COVID-19. These same approaches have also been applied for pathogen identification of bacteria, viruses, and hard to detect fungal microbes. Future uses of AI/ML may include integration of predictive analytics in point-of-care (POC) testing and data fusion applications. SUMMARY: Immunocompromised patients are at high risk for infections. AI/ML is transforming infectious disease testing and has great potential to address challenges encountered in the immune compromised population.

Common statistical concepts in the supervised Machine Learning arena.

One of the core elements of Machine Learning (ML) is statistics and its embedded foundational rules and without its appropriate integration, ML as we know would not exist. Various aspects of ML platforms are based on statistical rules and most notably the end results of the ML model performance cannot be objectively assessed without appropriate statistical measurements. The scope of statistics within the ML realm is rather broad and cannot be adequately covered in a single review article. Therefore, here we will mainly focus on the common statistical concepts that pertain to supervised ML (i.e. classification and regression) along with their interdependencies and certain limitations.

Evaluation of pharmacist guided intervention using procalcitonin and respiratory virus testing.

INTRODUCTION: Acute respiratory infections make up a sizable percentage of emergency department (ED) visits and many result in antibiotics being prescribed. Procalcitonin (PCT) has been found to reduce antibiotic use in both outpatient and critical care settings, yet remains underused in the ED. This study aimed to evaluate whether point of care molecular influenza and Respiratory Syncytial Virus (RSV) testing, PCT, and a pharmacist driven educational intervention in aggregate optimizes antibiotic and antiviral prescribing in the ED setting. METHODS: A randomized trial of the Cobas Liat Flu/RSV Assay, procalcitonin, and the use of pharmacist-led education in patients 0-50 years of age being seen in the ED for Influenza Like Illness (ILI) or acute respiratory illness. The study enrolled 200 ED patients between March 2018 and April 2022. RESULTS: There was little difference in antibiotic or antiviral prescribing between the intervention and control groups in this study (39%-32% = 7.0%, 95% CI: -6.2, 20.2, P = 0.30). However, a post-hoc analysis of the use of procalcitonin showed results were used as indicated in the ED (P = 0.001). CONCLUSION: PCT can be used in both adult and pediatric populations to help guide the decision of whether to treat with antibiotics in the ED setting. Pharmacist guided education may not be a driving factor.

Point of care blood glucose devices in the hospital setting.

Dysglycemia is common among hospitalized patients. Accurate point-of-care (POC) glucose monitoring is necessary for the safe administration of insulin. Unfortunately, POC glucose meters are not all created equal. Interfering factors such as abnormal hematocrit, abnormal oxygen tension, and oxidizing/reducing substances can lead to inaccurate glucose measurements and result in inappropriate insulin dosing. The introduction of autocorrecting glucose meters has changed the POC testing landscape. Autocorrecting glucose meters provide more accurate measurements and have been associated with improved glycemic control in hospitalized patients. Continuous glucose monitoring has also created interest in using these platforms in at-risk inpatient populations. Future glucose monitoring technologies such as artificial intelligence/machine learning, wearable smart devices, and closed-loop insulin management systems are poised to transform glycemic management. The goal of this review is to provide an overview of glucose monitoring technology, summarize the clinical impact of glucose monitoring accuracy, and highlight emerging and future POC glucose monitoring technologies.

Innovations in infectious disease testing: Leveraging COVID-19 pandemic technologies for the future.

Innovations in infectious disease testing have improved our abilities to detect and understand the microbial world. The 2019 novel coronavirus infectious disease (COVID-19) pandemic introduced new innovations including non-prescription "over the counter" infectious disease tests, mass spectrometry-based detection of COVID-19 host response, and the implementation of artificial intelligence (AI) and machine learning (ML) to identify individuals infected by the severe acute respiratory syndrome - coronavirus - 2 (SARS-CoV-2). As the world recovers from the COVID-19 pandemic; these innovative solutions will give rise to a new era of infectious disease tests extending beyond the detection of SARS-CoV-2. To this end, the purpose of this review is to summarize current trends in infectious disease testing and discuss innovative applications specifically in the areas of POC testing, MS, molecular diagnostics, sample types, and AI/ML.

Exploring the Past to Inform the Future to Optimize the Pharmacokinetics of Vancomycin in Children With Severe Burn Injuries.

Sepsis remains one of the leading causes of death among pediatric patients with burn injuries. Despite limited vancomycin pharmacokinetic (PK) information within this population, it is widely used to treat severe burn injuries. Those with severe burns are at risk of nephrotoxicity, with an incidence of acute kidney injury (AKI) over 50%. Delivering an effective vancomycin dose and avoiding unnecessary toxicity is essential for improved patient outcomes. This was a retrospective analysis of 115 children aged 0.2 months to 18 years with severe burns, >10% total body surface area. Vancomycin was given via intravenous infusion; blood samples were drawn between 6- and 12-hour postinfusion. A population pharmacokinetic model was developed using nonlinear mixed-effect modeling (Monolix, version 2016R1). A one-compartment model described a steady-state volume of distribution (V), dependent on weight. Vancomycin clearance (CL) was influenced by age and estimated creatinine clearance (CrCL). The study population's (median age = 4 years, median weight = 20 kg, median total body surface area (%TBSA) = 40%) median V and CL were calculated to be 1.25 L/kg (95% CI, 1.04-1.46) and 0.15 L/h/kg (95% CI, 0.126-0.165), respectively. The PK model was explicitly developed to characterize the impact of physiological changes in children under 18 years of age and the percentage of the burn surface area using limited data. The analysis determined that weight, age, and estimated CrCL were important covariates in predicting vancomycin PK with high variability in CL and V.

Predominant SARS-CoV-2 variant impacts accuracy when screening for infection using exhaled breath vapor.

BACKGROUND: New technologies with novel and ambitious approaches are being developed to diagnose or screen for SARS-CoV-2, including breath tests. The US FDA approved the first breath test for COVID-19 under emergency use authorization in April 2022. Most breath-based assays measure volatile metabolites exhaled by persons to identify a host response to infection. We hypothesized that the breathprint of COVID-19 fluctuated after Omicron became the primary variant of transmission over the Delta variant. METHODS: We collected breath samples from 142 persons with and without a confirmed COVID-19 infection during the Delta and Omicron waves. Breath samples were analyzed by gas chromatography-mass spectrometry. RESULTS: Here we show that based on 63 exhaled compounds, a general COVID-19 model had an accuracy of 0.73 ± 0.06, which improved to 0.82 ± 0.12 when modeling only the Delta wave, and 0.84 ± 0.06 for the Omicron wave. The specificity improved for the Delta and Omicron models (0.79 ± 0.21 and 0.74 ± 0.12, respectively) relative to the general model (0.61 ± 0.13). CONCLUSIONS: We report that the volatile signature of COVID-19 in breath differs between the Delta-predominant and Omicron-predominant variant waves, and accuracies improve when samples from these waves are modeled separately rather than as one universal approach. Our findings have important implications for groups developing breath-based assays for COVID-19 and other respiratory pathogens, as the host response to infection may significantly differ depending on variants or subtypes.

In recent decades, scientists have found we exhale thousands of compounds that reveal much about our health, including whether we are sick with COVID-19. Our team asked whether the breath profile of someone infected with the Delta variant of COVID-19 would match the breath profile caused by the Omicron variant­a version of the virus that is more transmissible. We analyzed breath samples from 142 people, some sick with either the Delta or Omicron variant of COVID-19, and others who were negative for COVID-19. Our results indicate that the Delta variant altered the contents of our breath in a different way than the Omicron variant, and breath-based tests improved when optimized to detect only one of the variants. These findings might impact the design of future breath-based tests for COVID-19.

Comparative performance of two automated machine learning platforms for COVID-19 detection by MALDI-TOF-MS.

The 2019 novel coronavirus infectious disease (COVID-19) pandemic has resulted in an unsustainable need for diagnostic tests. Currently, molecular tests are the accepted standard for the detection of SARS-CoV-2. Mass spectrometry (MS) enhanced by machine learning (ML) has recently been postulated to serve as a rapid, high-throughput, and low-cost alternative to molecular methods. Automated ML is a novel approach that could move mass spectrometry techniques beyond the confines of traditional laboratory settings. However, it remains unknown how different automated ML platforms perform for COVID-19 MS analysis. To this end, the goal of our study is to compare algorithms produced by two commercial automated ML platforms (Platforms A and B). Our study consisted of MS data derived from 361 subjects with molecular confirmation of COVID-19 status including SARS-CoV-2 variants. The top optimized ML model with respect to positive percent agreement (PPA) within Platforms A and B exhibited an accuracy of 94.9%, PPA of 100%, negative percent agreement (NPA) of 93%, and an accuracy of 91.8%, PPA of 100%, and NPA of 89%, respectively. These results illustrate the MS method's robustness against SARS-CoV-2 variants and highlight similarities and differences in automated ML platforms in producing optimal predictive algorithms for a given dataset.

Comparative performance of COVID-19 serology testing.

Background: The 2019 novel coronavirus infectious disease (COVID-19) pandemic resulted in a surge of assays aimed at detecting severe acute respiratory syndrome (SARS) - coronavirus (CoV) - 2 infection and prior exposure. Although both molecular and antigen testing have clearly defined uses, the utility of serology remains uncertain and is presently not recommended for assessing immunity. Methods: We conducted a pragmatic, observational study evaluating four commercially available emergency use authorized laboratory-based COVID-19 serology assays (Assays A-D). Remnant samples from hospitalized, and non-hospitalized SARS-CoV-2 PCR positive patients, as well as vaccinated and unvaccinated individuals were collected and tested. Positive percent agreement (PPA) and negative percent agreement (NPA) were calculated. Antibody concentrations were compared across the platforms and populations. Results: A total of 588 remnant samples derived from 500 patients were tested. PPA at 5-12 weeks post-PCR positive results for Assays A-D was 98.3, 97.4, 99.2, and 95.8% respectively. NPA was 100% across all platforms. Mean antibody concentrations at 2-4 weeks post-PCR positive result were significantly higher in hospitalized versus non-hospitalized patients, respectively, for Assay A (131.8 [101.7] vs. 95.6 [100.3] AU/mL, P < 0.001), B (61.7 [62.4] vs. 38.1 [40.5] AU/mL, P < 0.001), and C (157.6 [105.3] vs. 133.3 [100.7] AU/mL, P < 0.001). For individuals receiving two vaccine doses mean antibody concentrations were respectively 169.6 (104.4), 27.3 (50.8), 189.6 (120.9), 21.19 (13.1) AU/mL for Assays A-D. Conclusions: Overall, PPA and NPA differed across the four assays. Assays A and C produced higher PPA and NPA and detected larger concentrations of antibodies following vaccination.

Identification of Endogenous Peptides in Nasal Swab Transport Media used in MALDI-TOF-MS Based COVID-19 Screening.

Mass spectrometry (MS) based diagnostic detection of 2019 novel coronavirus infectious disease (COVID-19) has been postulated to be a useful alternative to classical PCR based diagnostics. These MS based approaches have the potential to be both rapid and sensitive and can be done on-site without requiring a dedicated laboratory or depending on constrained supply chains (i.e., reagents and consumables). Matrix-assisted laser desorption ionization (MALDI)-time-of-flight (TOF) MS has a long and established history of microorganism detection and systemic disease assessment. Previously, we have shown that automated machine learning (ML) enhanced MALDI-TOF-MS screening of nasal swabs can be both sensitive and specific for COVID-19 detection. The underlying molecules responsible for this detection are generally unknown nor are they required for this automated ML platform to detect COVID-19. However, the identification of these molecules is important for understanding both the mechanism of detection and potentially the biology of the underlying infection. Here, we used nanoscale liquid chromatography tandem MS to identify endogenous peptides found in nasal swab saline transport media to identify peptides in the same the mass over charge (m/z) values observed by the MALDI-TOF-MS method. With our peptidomics workflow, we demonstrate that we can identify endogenous peptides and endogenous protease cut sites. Further, we show that SARS-CoV-2 viral peptides were not readily detected and are highly unlikely to be responsible for the accuracy of MALDI based SARS-CoV-2 diagnostics. Further analysis with more samples will be needed to validate our findings, but the methodology proves to be promising.

Traumatic injury clinical trial evaluating tranexamic acid in children (TIC-TOC): a pilot randomized trial.

BACKGROUND: The antifibrinolytic drug tranexamic acid (TXA) improves survival in adults with traumatic hemorrhage; however, the drug has not been evaluated in a trial in injured children. We evaluated the feasibility of a large-scale trial evaluating the effects of TXA in children with severe hemorrhagic injuries. METHODS: Severely injured children (0 up to 18th birthday) were randomized into a double-blind randomized trial of 1) TXA 15 mg/kg bolus dose, followed by 2 mg/kg/hr infusion over 8 hours, 2) TXA 30 mg/kg bolus dose, followed by 4 mg/kg/hr infusion over 8 hours, or 3) normal saline placebo bolus and infusion. The trial was conducted at 4 pediatric Level I trauma centers in the United States between June 2018 and March 2020. We enrolled patients under federal exception from informed consent (EFIC) procedures when parents were unable to provide informed consent. Feasibility outcomes included the rate of enrollment, adherence to intervention arms, and ability to measure the primary clinical outcome. Clinical outcomes included global functioning (primary), working memory, total amount of blood products transfused, intracranial hemorrhage progression, and adverse events. The target enrollment rate was at least 1.25 patients per site per month. RESULTS: A total of 31 patients were randomized with a mean age of 10.7 years (standard deviation [SD] 5.0 years) and 22 (71%) patients were male. The mean time from injury to randomization was 2.4 hours (SD 0.6 hours). Sixteen (52%) patients had isolated brain injuries and 15 (48%) patients had isolated torso injuries. The enrollment rate using EFIC was 1.34 patients per site per month. All eligible enrolled patients received study intervention (9 patients TXA 15 mg/kg bolus dose, 10 patients TXA 30 mg/kg bolus dose, and 12 patients placebo) and had the primary outcome measured. No statistically significant differences in any of the clinical outcomes were identified. CONCLUSION: Based on enrollment rate, protocol adherence, and measurement of the primary outcome in this pilot trial, we confirmed the feasibility of conducting a large-scale, randomized trial evaluating the efficacy of TXA in severely injured children with hemorrhagic brain and/or torso injuries using EFIC.

Prediction of Tuberculosis Using an Automated Machine Learning Platform for Models Trained on Synthetic Data.

High-quality medical data is critical to the development and implementation of machine learning (ML) algorithms in healthcare; however, security, and privacy concerns continue to limit access. We sought to determine the utility of "synthetic data" in training ML algorithms for the detection of tuberculosis (TB) from inflammatory biomarker profiles. A retrospective dataset (A) comprised of 278 patients was used to generate synthetic datasets (B, C, and D) for training models prior to secondary validation on a generalization dataset. ML models trained and validated on the Dataset A (real) demonstrated an accuracy of 90%, a sensitivity of 89% (95% CI, 83-94%), and a specificity of 100% (95% CI, 81-100%). Models trained using the optimal synthetic dataset B showed an accuracy of 91%, a sensitivity of 93% (95% CI, 87-96%), and a specificity of 77% (95% CI, 50-93%). Synthetic datasets C and D displayed diminished performance measures (respective accuracies of 71% and 54%). This pilot study highlights the promise of synthetic data as an expedited means for ML algorithm development.

Evolving Applications of Artificial Intelligence and Machine Learning in Infectious Diseases Testing.

BACKGROUND: Artificial intelligence (AI) and machine learning (ML) are poised to transform infectious disease testing. Uniquely, infectious disease testing is technologically diverse spaces in laboratory medicine, where multiple platforms and approaches may be required to support clinical decision-making. Despite advances in laboratory informatics, the vast array of infectious disease data is constrained by human analytical limitations. Machine learning can exploit multiple data streams, including but not limited to laboratory information and overcome human limitations to provide physicians with predictive and actionable results. As a quickly evolving area of computer science, laboratory professionals should become aware of AI/ML applications for infectious disease testing as more platforms are become commercially available. CONTENT: In this review we: (a) define both AI/ML, (b) provide an overview of common ML approaches used in laboratory medicine, (c) describe the current AI/ML landscape as it relates infectious disease testing, and (d) discuss the future evolution AI/ML for infectious disease testing in both laboratory and point-of-care applications. SUMMARY: The review provides an important educational overview of AI/ML technique in the context of infectious disease testing. This includes supervised ML approaches, which are frequently used in laboratory medicine applications including infectious diseases, such as COVID-19, sepsis, hepatitis, malaria, meningitis, Lyme disease, and tuberculosis. We also apply the concept of "data fusion" describing the future of laboratory testing where multiple data streams are integrated by AI/ML to provide actionable clinical knowledge.