Ethical Considerations in the Use of Artificial Intelligence and Machine Learning in Health Care: A Comprehensive Review.

Artificial intelligence (AI) and machine learning (ML) technologies are revolutionizing health care by offering unprecedented opportunities to enhance patient care, optimize clinical workflows, and advance medical research. However, the integration of AI and ML into healthcare systems raises significant ethical considerations that must be carefully addressed to ensure responsible and equitable deployment. This comprehensive review explored the multifaceted ethical considerations surrounding the use of AI and ML in health care, including privacy and data security, algorithmic bias, transparency, clinical validation, and professional responsibility. By critically examining these ethical dimensions, stakeholders can navigate the ethical complexities of AI and ML integration in health care, while safeguarding patient welfare and upholding ethical principles. By embracing ethical best practices and fostering collaboration across interdisciplinary teams, the healthcare community can harness the full potential of AI and ML technologies to usher in a new era of personalized data-driven health care that prioritizes patient well-being and equity.

Clinical validation of two volumetric absorptive microsampling devices to support home-based therapeutic drug monitoring of immunosuppression.

AIMS: Dried blood volumetric absorptive microsamples (VAMS) may facilitate home-based sampling to enhance therapeutic drug monitoring after transplantation. This study aimed to clinically validate a liquid chromatography-tandem mass spectrometry assay using 2 VAMS devices with different sampling locations (Tasso-M20 for the upper arm and Mitra for the finger). Patient preferences were also evaluated. METHODS: Clinical validation was performed for tacrolimus and mycophenolic acid by comparison of paired VAMS and venipuncture samples using Passing-Bablok regression and Bland-Altman analysis. Conversion of mycophenolic acid VAMS to serum concentrations was evaluated using haematocrit-dependent formulas and fixed correction factors defined a priori. Patients' perspectives, including useability, acceptability and feasibility, were also investigated using established questionnaires. RESULTS: Paired samples (n = 50) were collected from 25 kidney transplant recipients. Differences for tacrolimus whole-blood concentration were within ±20% for 86 and 88% of samples from the upper arm and fingerstick, respectively. Using correction factors of 1.3 for the upper-arm and 1.47 for finger-prick samples, 84 and 76% of the paired samples, respectively, were within ±20% for mycophenolic acid serum concentration. Patient experience surveys demonstrated limited pain and acceptable useability of the upper-arm device. CONCLUSIONS: Tacrolimus and mycophenolic acid can be measured using 2 common VAMS devices with similar analytical performance. Patients are supportive of home-based monitoring with a preference for the Tasso-M20 device.

Establishing and clinically validating a machine learning model for predicting unplanned reoperation risk in colorectal cancer.

BACKGROUND: Colorectal cancer significantly impacts global health, with unplanned reoperations post-surgery being key determinants of patient outcomes. Existing predictive models for these reoperations lack precision in integrating complex clinical data. AIM: To develop and validate a machine learning model for predicting unplanned reoperation risk in colorectal cancer patients. METHODS: Data of patients treated for colorectal cancer (n = 2044) at the First Affiliated Hospital of Wenzhou Medical University and Wenzhou Central Hospital from March 2020 to March 2022 were retrospectively collected. Patients were divided into an experimental group (n = 60) and a control group (n = 1984) according to unplanned reoperation occurrence. Patients were also divided into a training group and a validation group (7:3 ratio). We used three different machine learning methods to screen characteristic variables. A nomogram was created based on multifactor logistic regression, and the model performance was assessed using receiver operating characteristic curve, calibration curve, Hosmer-Lemeshow test, and decision curve analysis. The risk scores of the two groups were calculated and compared to validate the model. RESULTS: More patients in the experimental group were ≥ 60 years old, male, and had a history of hypertension, laparotomy, and hypoproteinemia, compared to the control group. Multiple logistic regression analysis confirmed the following as independent risk factors for unplanned reoperation (P < 0.05): Prognostic Nutritional Index value, history of laparotomy, hypertension, or stroke, hypoproteinemia, age, tumor-node-metastasis staging, surgical time, gender, and American Society of Anesthesiologists classification. Receiver operating characteristic curve analysis showed that the model had good discrimination and clinical utility. CONCLUSION: This study used a machine learning approach to build a model that accurately predicts the risk of postoperative unplanned reoperation in patients with colorectal cancer, which can improve treatment decisions and prognosis.

Clinical Validation of Digital Healthcare Solutions: State of the Art, Challenges and Opportunities.

Digital health technologies (DHTs) at the intersection of health, medical informatics, and business aim to enhance patient care through personalised digital approaches. Ensuring the efficacy and reliability of these innovations demands rigorous clinical validation. A PubMed literature review (January 2006 to July 2023) identified 1250 papers, highlighting growing academic interest. A focused narrative review (January 2018 to July 2023) delved into challenges, highlighting issues such as diverse regulatory landscapes, adoption issues in complex healthcare systems, and a plethora of evaluation frameworks lacking pragmatic guidance. Existing frameworks often omit crucial criteria, neglect empirical evidence, and clinical effectiveness is rarely included as a criterion for DHT quality. The paper underscores the urgency of addressing challenges in accreditation, adoption, business models, and integration to safeguard the quality, efficacy, and safety of DHTs. A pivotal illustration of collaborative efforts to address these challenges is exemplified by the Digital Health Validation Center, dedicated to generating clinical evidence of innovative healthcare technologies and facilitating seamless technology transfer. In conclusion, it is necessary to harmonise evaluation approaches and frameworks, improve regulatory clarity, and commit to collaboration to integrate rigorous clinical validation and empirical evidence throughout the DHT life cycle.

Data-driven prediction model for periodontal disease based on correlational feature analysis and clinical validation.

Objectives: This study aimed to investigate the performance and reliability of data-driven models employing correlational feature analysis and clinical validation for predicting periodontal disease. Methods: The 7th Korea National Health and Nutrition Examination Survey (n = 10,654) was used for correlation analysis to identify significant risk factors for periodontitis. Periodontal prediction models were developed with the selected factors and database, followed by internal validation with 5-fold cross-validation and 1000 bootstrap resampling. External validation was conducted with clinical data (n = 120) collected through self-reported questionnaires, clinical periodontal parameters, and radiographic image analysis. Predictive performance was assessed for logistics regression, support vector machine, random forest, XGBoost, and neural network algorithms using the area under the receiver operating characteristic curves (AUC) and other performance metrics. Results: Correlation analysis identified 16 features from over 1000 potential risk factors for periodontitis. The best data-driven model (XGBoost) showed AUC values of 0.823 and 0.796 for internal and external validations, respectively. Modeling with clinical data revealed those same measures to be 0.836 and 0.649, respectively. In addition, the data-driven model could predict other clinical periodontal parameters including severe bone loss (AUC = 0.813), gingival bleeding (AUC = 0.694), and tooth loss (AUC = 0.734). A patient case study about prognostic predictions revealed that the probability of periodontitis can be reduced by 6.0 % (stop smoking) and 0.6 % (stop drinking) on average. Conclusions: Data-driven models for predicting periodontitis and other periodontal parameters were developed from 16 risk factors, demonstrating enhanced prediction performance and reproducibility in internal-external validations.

Clinical Validation of Digitally Acquired Clinical Data and Machine Learning Models for Remote Measurement of Psoriasis and Psoriatic Arthritis: A Proof-of-Concept Study.

OBJECTIVE: Psoriatic disease remains underdiagnosed and undertreated. We developed and validated a suite of novel, sensor-based smartphone assessments (Psorcast app) that can be self-administered to measure cutaneous and musculoskeletal signs and symptoms of psoriatic disease. METHODS: Participants with psoriasis (PsO) or psoriatic arthritis (PsA) and healthy controls were recruited between June 5, 2019, and November 10, 2021, at 2 academic medical centers. Concordance and accuracy of digital measures and image-based machine learning models were compared to their analogous clinical measures from trained rheumatologists and dermatologists. RESULTS: Of 104 study participants, 51 (49%) were female and 53 (51%) were male, with a mean age of 42.3 years (SD 12.6). Seventy-nine (76%) participants had PsA, 16 (15.4%) had PsO, and 9 (8.7%) were healthy controls. Digital patient assessment of percent body surface area (BSA) affected with PsO demonstrated very strong concordance (Lin concordance correlation coefficient [CCC] 0.94 [95% CI 0.91-0.96]) with physician-assessed BSA. The in-clinic and remote target plaque physician global assessments showed fair-to-moderate concordance (CCCerythema 0.72 [0.59-0.85]; CCCinduration 0.72 [0.62-0.82]; CCCscaling 0.60 [0.48-0.72]). Machine learning models of hand photos taken by patients accurately identified clinically diagnosed nail PsO with an accuracy of 0.76. The Digital Jar Open assessment categorized physician-assessed upper extremity involvement, considering joint tenderness or enthesitis (AUROC 0.68 [0.47-0.85]). CONCLUSION: The Psorcast digital assessments achieved significant clinical validity, although they require further validation in larger cohorts before use in evidence-based medicine or clinical trial settings. The smartphone software and analysis pipelines from the Psorcast suite are open source and freely available.

A Targeted LC-MRM3 Proteomic Approach for the Diagnosis of SARS-CoV-2 Infection in Nasopharyngeal Swabs.

Since its first appearance, severe acute respiratory syndrome coronavirus 2 quickly spread around the world and the lack of adequate PCR testing capacities, especially during the early pandemic, led the scientific community to explore new approaches such as mass spectrometry (MS). We developed a proteomics workflow to target several tryptic peptides of the nucleocapsid protein. A highly selective multiple reaction monitoring-cubed (MRM3) strategy provided a sensitivity increase in comparison to conventional MRM acquisition. Our MRM3 approach was first tested on an Amsterdam public health cohort (alpha-variant, 760 participants) detecting viral nucleocapsid protein peptides from nasopharyngeal swabs samples presenting a cycle threshold value down to 35 with sensitivity and specificity of 94.2% and 100.0%, without immunopurification. A second iteration of the MS-diagnostic test, able to analyze more than 400 samples per day, was clinically validated on a Leiden-Rijswijk public health cohort (delta-variant, 2536 participants) achieving 99.9% specificity and 93.1% sensitivity for patients with cycle threshold values up to 35. In this manuscript, we also developed and brought the first proof of the concept of viral variant monitoring in a complex matrix using targeted MS.

Clinical validation of the Ion Torrent Oncomine Myeloid Assay GX v2 on the Genexus Integrated Sequencer as a stand-alone assay for single-nucleotide variants, insertions/deletions, and fusion genes: Challenges, performance, and perspectives.

OBJECTIVES: Myeloid neoplasms require comprehensive characterization of genetic abnormalities, including single-nucleotide variants, small insertions and deletions, and fusions and translocations for management. The Oncomine Myeloid Assay GX v2 (Thermo Fisher Scientific) analyzes 17 full genes, 28 hotspot genes, 30 fusion driver genes, and 5 expression genes. METHODS: The validation set included 192 DNA samples, 28 RNA samples, and 9 cell lines and contrived controls. The DNA and RNA were extracted from both peripheral blood and bone marrow. Library preparation, templating, and sequencing was performed on the fully automated Genexus Integrated Sequencer (Thermo Fisher Scientific). The sequencing data were analyzed by manual curation, default Oncomine filters and the Oncomine Reporter (Thermo Fisher Scientific). RESULTS: Of the 600 reference pathogenic DNA variants targeted by the assay, concordance was seen in 98.3% of unfiltered variant call format files. Precision and reproducibility were 100%, and the lower limit of detection was 2% variant allele frequency for DNA. Inability to detect variants in long homopolymer regions intrinsic to the Ion Torrent chemistry led to 7 missed variants; 100% concordance was seen with reference RNA samples. CONCLUSIONS: This extensive clinical validation of the Oncomine Myeloid Assay GX v2 on the Genexus Integrated Sequencer with its built-in bioinformatics pipeline and Ion Torrent Oncomine Reporter shows robust performance in terms of variant calling accuracy, precision, and reproducibility, with the advantage of a rapid turnaround time of 2 days. The greatest limitation is the inability to detect variants in long homopolymer regions.

Clinical evaluation of droplet digital PCR in the early identification of suspected sepsis patients in the emergency department: a prospective observational study.

Background: Rapid and accurate diagnosis of the causative agents is essential for clinical management of bloodstream infections (BSIs) that might induce sepsis/septic shock. A considerable number of suspected sepsis patients initially enter the health-care system through an emergency department (ED), hence it is vital to establish an early strategy to recognize sepsis and initiate prompt care in ED. This study aimed to evaluate the diagnostic performance and clinical value of droplet digital PCR (ddPCR) assay in suspected sepsis patients in the ED. Methods: This was a prospective single-centered observational study including patients admitted to the ED from 25 October 2022 to 3 June 2023 with suspected BSIs screened by Modified Shapiro Score (MSS) score. The comparison between ddPCR and blood culture (BC) was performed to evaluate the diagnostic performance of ddPCR for BSIs. Meanwhile, correlative analysis between ddPCR and the inflammatory and prognostic-related biomarkers were conducted to explore the relevance. Further, the health economic evaluation of the ddPCR was analyzed. Results: 258 samples from 228 patients, with BC and ddPCR performed simultaneously, were included in this study. We found that ddPCR results were positive in 48.13% (103 of 214) of episodes, with identification of 132 pathogens. In contrast, BC only detected 18 positives, 88.89% of which were identified by ddPCR. When considering culture-proven BSIs, ddPCR shows an overall sensitivity of 88.89% and specificity of 55.61%, the optimal diagnostic power for quantifying BSI through ddPCR is achieved with a copy cutoff of 155.5. We further found that ddPCR exhibited a high accuracy especially in liver abscess patients. Among all the identified virus by ddPCR, EBV has a substantially higher positive rate with a link to immunosuppression. Moreover, the copies of pathogens in ddPCR were positively correlated with various markers of inflammation, coagulation, immunity as well as prognosis. With high sensitivity and specificity, ddPCR facilitates precision antimicrobial stewardship and reduces health care costs. Conclusions: The multiplexed ddPCR delivers precise and quantitative load data on the causal pathogen, offers the ability to monitor the patient's condition and may serve as early warning of sepsis in time-urgent clinical situations as ED. Importance: Early detection and effective administration of antibiotics are essential to improve clinical outcomes for those with life-threatening infection in the emergency department. ddPCR, an emerging tool for rapid and sensitive pathogen identification used as a precise bedside test, has developed to address the current challenges of BSI diagnosis and precise treatment. It characterizes sensitivity, specificity, reproducibility, and absolute quantifications without a standard curve. ddPCR can detect causative pathogens and related resistance genes in patients with suspected BSIs within a span of three hours. In addition, it can identify polymicrobial BSIs and dynamically monitor changes in pathogenic microorganisms in the blood and can be used to evaluate antibiotic efficacy and survival prognosis. Moreover, the copies of pathogens in ddPCR were positively correlated with various markers of inflammation, coagulation, immunity. With high sensitivity and specificity, ddPCR facilitates precision antimicrobial stewardship and reduces health care costs.

Unlocking the full potential of digital endpoints for decision making: a novel modular evidence concept enabling re-use and advancing collaboration.

INTRODUCTION: Over the last decade increasing examples indicate opportunities to measure patient functioning and its relevance for clinical and regulatory decision making via endpoints collected through digital health technologies. More recently, we have seen such measures support primary study endpoints and enable smaller trials. The field is advancing fast: validation requirements have been proposed in the literature and regulators are releasing new guidances to review these endpoints. Pharmaceutical companies are embracing collaborations to develop them and working with academia and patient organizations in their development. However, the road to validation and regulatory acceptance is lengthy. The full value of digital endpoints cannot be unlocked until better collaboration and modular evidence frameworks are developed enabling re-use of evidence and repurposing of digital endpoints. AREAS COVERED: This paper proposes a solution by presenting a novel modular evidence framework -the Digital Evidence Ecosystem and Protocols (DEEP)- enabling repurposing of measurement solutions, re-use of evidence, application of standards and also facilitates collaboration with health technology assessment bodies. EXPERT OPINION: The integration of digital endpoints in healthcare, essential for personalized and remote care, requires harmonization and transparency. The proposed novel stack model offers a modular approach, fostering collaboration and expediting the adoption in patient care.

Hydrogen Sulfide-Induced Activatable Photodynamic Therapy Adjunct to Disruption of Subcellular Glycolysis in Cancer Cells by a Fluorescence-SERS Bimodal Iridium Metal-Organic Hybrid.

The practical application of photodynamic therapy (PDT) demands targeted and activatable photosensitizers to mitigate off-target phototoxicity common in "always on" photosensitizers during light exposure. Herein, a cyclometalated iridium complex-based activatable photodynamic molecular hybrid, Cy-Ir-7-nitrobenzofurazan (NBD), is demonstrated as a biomedicine for molecular precision. This design integrates a hydrogen sulfide (H2S)-responsive NBD unit with a hydroxy-appended iridium complex, Cy-Ir-OH. In normal physiological conditions, the electron-rich Ir metal center exerts electron transfer to the NBD unit, quenches the excited state dynamics, and establishes a PDT-off state. Upon exposure to H2S, Cy-Ir-NBD activates into the potent photosensitizer Cy-Ir-OH through nucleophilic substitution. This mechanism ensures exceptional specificity, enabling targeted phototherapy in H2S-rich cancer cells. Additionally, we observed that Cy-Ir-NBD-induced H2S depletion disrupts S-sulfhydration of the glyceraldehyde-3-phosphate dehydrogenase enzyme, impairing glycolysis and ATP production in the cellular milieu. This sequential therapeutic process of Cy-Ir-NBD is governed by the positively charged central iridium ion that ensures mitochondria-mediated apoptosis in cancer cells. Dual-modality SERS and fluorescence imaging validate apoptotic events, highlighting Cy-Ir-NBD as an advanced theranostic molecular entity for activatable PDT. Finally, as a proof of concept, clinical assessment is evaluated with the blood samples of breast cancer patients and healthy volunteers, based on their H2S overexpression capability through SERS and fluorescence, revealing Cy-Ir-NBD to be a promising predictor for PDT activation in advanced cancer phototherapy.

Validation of Becton Dickinson Barricor™ tubes for use with Abbott Alinity™ and Siemens Atellica® highly sensitive cardiac troponin I measuring systems.

BACKGROUND: BD Barricor™ tubes have been proposed to decrease laboratory turnaround time (TAT). We analytically validated and then clinically verified these tubes for use with Abbott Alinity™ and Siemens Atellica® highly sensitive cardiac troponin I (hs-cTnI) assays. METHODS: hs-cTnI measurements were undertaken in paired Barricor™ and in-use PSTII™ tubes on both systems. 359 matched samples with hs-cTnI levels between 3 and 15,000 ng/L (Atellica® values) were used to assess the hemolysis rate and make method comparisons. 599 paired patient samples were collected on emergency department (ED) admission to compare the performance of the rapid acute myocardial infarction (AMI) rule-out strategy based on hs-cTnI concentrations lower than recommended thresholds (<4 ng/L Alinity™; <5 ng/L Atellica®) when different tubes and systems were employed. RESULTS: No between-tube differences in hemolysis rate were seen when free hemoglobin concentrations in plasma samples were ≥0.25 g/L, even if PSTII™ showed a significant increase of hemolysis rate vs. Barricor™ (31% vs. 22%, p=0.007) when a lower cut-off for hemolysis (≥0.11 g/L) was employed on the Atellica® detection system. The alternate use of these tubes did not influence the hs-cTnI results obtained from either of the two assays, which remained markedly biased (~40%) irrespective of the tube used. The expected optimal ability of very low hs-cTnI values on ED admission for ruling out AMI was confirmed by using both systems regardless of the tube type. CONCLUSIONS: Barricor™ and PSTII™ tubes can provide analytically equivalent hs-cTnI results when used on either Alinity™ or Atellica® hs-cTnI assays.

Clinical validation of SARS-CoV-2 electrochemical immunosensor based on the spike-ACE2 complex.

BACKGROUND AND AIMS: Advances in health, especially in prevention, diagnosis, and treatment, have significantly impacted the way of facing emerging infectious diseases. Yet, events such as the COVID-19 pandemic have shown that there is still a long way to go. Therefore, an urgent need exists for portable and easily deployable point-of-care (POC) detection tools. Biosensors at the POC remain in the laboratory in an analytical characterization step and are not yet mature enough to reach the market massively. In this context, it is necessary to progress in validating these devices to demonstrate their relevance in detecting different disease biomarkers. This work reports on the clinical validation of an electrochemical immunosensor for detecting SARS-CoV-2. METHODS: A monocentric retrospective cohort study was conducted with 150 random nasopharyngeal swabs or tracheal aspiration samples tested by RT-PCR. The immunosensor based on magnetic beads and chronoamperometry detected SARS-CoV-2 through the spike-angiotensin-converting protein (ACE2) immunocomplex. RESULTS: This biosensor demonstrated 96.04 % clinical sensitivity and 87.75 % clinical specificity in detecting SARS-CoV-2 in the samples, highly correlated with the RT-PCR gold standard. CONCLUSIONS: It demonstrates the potential of electrochemical biosensors to be implemented as highly sensitive and easily deployable detection strategies even in remote locations.

An LC-MS/MS Method for Quantification of Lamotrigine and Its Main Metabolite in Dried Blood Spots.

BACKGROUND: The antiepileptic drug lamotrigine (LTG) shows high pharmacokinetic variability due to genotype influence and concomitant use of glucuronidation inducers and inhibitors, both of which may be frequently taken by elderly patients. Our goal was to develop a reliable quantification method for lamotrigine and its main glucuronide metabolite lamotrigine-N2-glucuronide (LTG-N2-GLU) in dried blood spots (DBS) to enable routine therapeutic drug monitoring and to identify altered metabolic activity for early detection of drug interactions possibly leading to suboptimal drug response. RESULTS: The analytical method was validated in terms of selectivity, accuracy, precision, matrix effects, haematocrit, blood spot volume influence, and stability. It was applied to a clinical study, and the DBS results were compared to the concentrations determined in plasma samples. A good correlation was established for both analytes in DBS and plasma samples, taking into account the haematocrit and blood cell-to-plasma partition coefficients. It was demonstrated that the method is suitable for the determination of the metabolite-to-parent ratio to reveal the metabolic status of individual patients. CONCLUSIONS: The clinical validation performed confirmed that the DBS technique is a reliable alternative for plasma lamotrigine and its glucuronide determination.

Urine high-risk human papillomavirus testing as an alternative to routine cervical screening: A comparative diagnostic accuracy study of two urine collection devices using a randomised study design trial.

OBJECTIVE: To evaluate the sensitivity of human papillomavirus (HPV) tested urine to detect high-grade cervical precancer (cervical intraepithelial neoplasia grade 2+ [CIN2+]) using two urine collection devices. DESIGN: Randomised controlled trial. SETTING: St Mary's Hospital, Manchester, UK. POPULATION: Colposcopy attendees with abnormal cervical screening; a total of 480 participants were randomised. Matched urine and cervical samples were available for 235 and 230 participants using a first-void urine (FVU)-collection device and standard pot, respectively. METHODS: Urine was self-collected and mixed with preservative - randomised 1:1 to FVU-collection device (Novosanis Colli-pee® 10 mL with urine conservation medium [UCM]) or standard pot. Matched clinician-collected cervical samples were taken before colposcopy. HPV testing used Roche cobas® 8800. A questionnaire evaluated urine self-sampling acceptability. MAIN OUTCOME MEASURES: The primary outcome measured sensitivity of HPV-tested urine (FVU-collection device and standard pot) for CIN2+ detection. Secondary outcomes compared HPV-tested cervical and urine samples for CIN2+ and evaluated the acceptability of urine self-sampling. RESULTS: Urine HPV test sensitivity for CIN2+ was higher with the FVU-collection device (90.3%, 95% CI 83.7%-94.9%, 112/124) than the standard pot (73.4%, 95% CI 64.7%-80.9%, 91/124, p = 0.0005). The relative sensitivity of FVU-device-collected urine was 0.92 (95% CI 0.87-0.97, pMcN = 0.004) compared with cervical, considering that all women were referred after a positive cervical HPV test. Urine-based sampling was acceptable to colposcopy attendees. CONCLUSIONS: Testing of FVU-device-collected urine for HPV was superior to standard-pot-collected urine in colposcopy attendees and has promising sensitivity for CIN2+ detection. General population HPV testing of FVU-device-collected urine will establish its clinical performance and acceptability as an alternative to routine cervical screening.

The first clinical validation of whole-genome screening on standard trophectoderm biopsies of preimplantation embryos.

Objective: To validate the performance of our laboratory-developed whole-genome screening assay within clinical preimplantation genetic testing environments. Design: Perform a laboratory-developed whole-genome assay on both cell lines and trophectoderm biopsies, subsequently employing the next-generation sequencing procedure to reach a sequencing depth of 30X. Adhere to the Genome Analysis Toolkit best practices for accuracy, sensitivity, specificity, and precision calculations by comparing samples with references. Our assay was then applied to cell lines and biopsies harboring known pathogenic variants, aiming to ascertain these changes solely from the next-generation sequencing data, independent of parental genome information. Settings: Clinical laboratory. Patients: Coriell cell lines and research embryos with known chromosomal or genetic variants. Research trophectoderm biopsies from a couple that are heterozygous carriers for distinct variants in the same autosomal recessive gene (HOGA1). Intervention: Not applicable. Main Outcome Measures: Accuracy, sensitivity, specificity, and precision were assessed by comparing the samples to their references. For samples with known variants, we calculated our sensitivity to detecting established variants. For the research embryos, noncarrier, carrier, and compound heterozygous states of inherited HOGA1 variants were distinguished independently of parental samples. Results: Amplification of DNA from cell lines and embryos yielded success rates exceeding 99.9% and 98.2%, respectively, although maintaining an accuracy of >99.9% for aneuploidy assessment. The accuracy (99.99%), specificity (99.99%), sensitivity (98.0%), and precision (98.1%) of amplified genome in the bottle (reference NA12878) and embryo biopsies were comparable to results on genomic DNA, including mitochondrial heteroplasmy. Using our assay, we achieved >99.99% sensitivity when examining samples with known chromosomal and genetic variants. This encompassed pathogenic CFTR, BRCA1, and other variants, along with uniparental isodisomies and microdeletions such as DiGeorge syndrome. Our research study identified noncarrier, carrier, and compound heterozygous states within trophectoderm biopsies while simultaneously screening for 1,300 other severe monogenic diseases. Conclusion: To our knowledge, this is the first clinical validation of whole-genome embryo screening. In this study, we demonstrated high accuracy for aneuploidy calls (>99.9%) and genetic variants (99.99%), even in the absence of parental genomes. This assay demonstrates advancements in genomic screening and an extended scope for testing capabilities in the realm of preimplantation genetic testing.

Retrospective validation of MetaSystems' deep-learning-based digital microscopy platform with assistance compared to manual fluorescence microscopy for detection of mycobacteria.

This study aimed to validate Metasystems' automated acid-fast bacilli (AFB) smear microscopy scanning and deep-learning-based image analysis module (Neon Metafer) with assistance on respiratory and pleural samples, compared to conventional manual fluorescence microscopy (MM). Analytical parameters were assessed first, followed by a retrospective validation study. In all, 320 archived auramine-O-stained slides selected non-consecutively [85 originally reported as AFB-smear-positive, 235 AFB-smear-negative slides; with an overall mycobacterial culture positivity rate of 24.1% (77/320)] underwent whole-slide imaging and were analyzed by the Metafer Neon AFB Module (version 4.3.130) using a predetermined probability threshold (PT) for AFB detection of 96%. Digital slides were then examined by a trained reviewer blinded to previous AFB smear and culture results, for the final interpretation of assisted digital microscopy (a-DM). Paired results from both microscopic methods were compared to mycobacterial culture. A scanning failure rate of 10.6% (34/320) was observed, leaving 286 slides for analysis. After discrepant analysis, concordance, positive and negative agreements were 95.5% (95%CI, 92.4%-97.6%), 96.2% (95%CI, 89.2%-99.2%), and 95.2% (95%CI, 91.3%-97.7%), respectively. Using mycobacterial culture as reference standard, a-DM and MM had comparable sensitivities: 90.7% (95%CI, 81.7%-96.2%) versus 92.0% (95%CI, 83.4%-97.0%) (P-value = 1.00); while their specificities differed 91.9% (95%CI, 87.4%-95.2%) versus 95.7% (95%CI, 92.1%-98.0%), respectively (P-value = 0.03). Using a PT of 96%, MetaSystems' platform shows acceptable performance. With a national laboratory staff shortage and a local low mycobacterial infection rate, this instrument when combined with culture, can reliably triage-negative AFB-smear respiratory slides and identify positive slides requiring manual confirmation and semi-quantification. IMPORTANCE: This manuscript presents a full validation of MetaSystems' automated acid-fast bacilli (AFB) smear microscopy scanning and deep-learning-based image analysis module using a probability threshold of 96% including accuracy, precision studies, and evaluation of limit of AFB detection on respiratory samples when the technology is used with assistance. This study is complementary to the conversation started by Tomasello et al. on the use of image analysis artificial intelligence software in routine mycobacterial diagnostic activities within the context of high-throughput laboratories with low incidence of tuberculosis.

Performance of a multigene genomic classifier and clinical parameters in predicting malignancy in a Southeast Asian cohort of patients with cytologically indeterminate thyroid nodules.

BACKGROUND: Most thyroid nodules are benign. It is important to determine the likelihood of malignancy in such nodules to avoid unnecessary surgery. The primary objective of this study was to characterize the genetic landscape and the performance of a multigene genomic classifier in fine-needle aspiration (FNA) biopsies of cytologically indeterminate thyroid nodules in a Southeast Asian cohort. The secondary objective was to assess the predictive contribution of clinical characteristics to thyroid malignancy. METHODS: This prospective, multicenter, blinded study included 132 patients with 134 nodules. Molecular testing (MT) with ThyroSeq v3 was performed on clinical or ex-vivo FNA samples. Centralized pathology review also was performed. RESULTS: Of 134 nodules, consisting of 61% Bethesda category III, 20% category IV, and 19% category V cytology, and 56% were histologically malignant. ThyroSeq yielded negative results in 37.3% of all FNA samples and in 42% of Bethesda category III-IV cytology nodules. Most positive samples had RAS-like (41.7%), followed by BRAF-like (22.6%), and high-risk (17.9%) alterations. Compared with North American patients, the authors observed a higher proportion of RAS-like mutations, specifically NRAS, in Bethesda categories III and IV and more BRAF-like mutations in Bethesda category III. The test had sensitivity, specificity, negative predictive value, and positive predictive value of 89.6%, 73.7%, 84.0%, and 82.1%, respectively. The risk of malignancy was predicted by positive MT and high-suspicion ultrasound characteristics according to American Thyroid Association criteria. CONCLUSIONS: Even in the current Southeast Asian cohort with nodules that had a high pretest cancer probability, MT could lead to potential avoidance of diagnostic surgery in 42% of patients with Bethesda category III-IV nodules. MT positivity was a stronger predictor of malignancy than clinical parameters.

Analytical performances of a point-of-care loop-mediated isothermal amplification assay to detect Group B Streptococcus in intrapartum pregnant women living in the Democratic Republic of the Congo.

OBJECTIVES: Group B Streptococcus (GBS) is the leading infectious cause of stillbirth and neonatal morbidity and mortality in sub-Saharan Africa. METHODS: Vaginal and rectovaginal swab samples were obtained from 274 intrapartum pregnant women in the Democratic Republic of the Congo to be analyzed for GBS DNA detection in parallel by the point-of-care BIOSYNEX AMPLIFLASH® GBS assay (Biosynex SA, Illkirch-Graffenstaden, France) and by reference quantitative polymerase chain reaction (qPCR). RESULTS: Rectovaginal swabbing, nearly two-fold more positive for GBS than vaginal swabbing alone, showed a high prevalence of GBS DNA positivity in 20.1% of eligible intrapartum pregnant women. In the event of significant bacterial carriage (i.e., cycle threshold ≤33 by reference qPCR), the AMPLIFLASH® GBS assay with rectovaginal swabbing showed high sensitivity (98.1%) and specificity (100.0%) for GBS DNA detection, with excellent concordance, reliability, and accuracy with the reference qPCR, and positive predictive values and negative predictive values above 99.0%. CONCLUSIONS: The study demonstrates a high rate of female rectogenital GBS colonization in pregnant Congolese women. The AMPLIFLASH® GBS assay harbored excellent analytical performances in the field, which makes it suitable to be used as point-of-care molecular assay in various hospital and non-hospital settings where rapid diagnosis of GBS is necessary.

Age shock index and age-modified shock index are valuable bedside prognostic tools for postdischarge mortality in ST-elevation myocardial infarction patients.

BACKGROUND: The incidence of mortality is considerable after ST-elevation myocardial infarction (STEMI) hospitalization; risk assessment is needed to guide postdischarge management. Age shock index (SI) and age modified shock index (MSI) were described as useful prognosis instruments; nevertheless, their predictive effect on short and long-term postdischarge mortality has not yet been sufficiently confirmed. METHODS: This analysis included 3389 prospective patients enrolled from 2016 to 2018. Endpoints were postdischarge mortality within 30 days and from 30 days to 1 year. Hazard ratios (HRs) were evaluated by Cox proportional-hazards regression. Predictive performances were assessed by area under the curve (AUC), integrated discrimination improvement (IDI), net reclassification improvement (NRI) and decision curve analysis (DCA) and compared with TIMI risk score and GRACE score. RESULTS: The AUCs were 0.753, 0.746 for age SI and 0.755, 0.755 for age MSI for short- and long-term postdischarge mortality. No significant AUC differences and NRI were observed compared with the classic scores; decreased IDI was observed especially for long-term postdischarge mortality. Multivariate analysis revealed significantly higher short- and long-term postdischarge mortality for patients with high age SI (HR: 5.44 (2.73-10.85), 5.34(3.18-8.96)), high age MSI (HR: 4.17(1.78-9.79), 5.75(3.20-10.31)) compared to counterparts with low indices. DCA observed comparable clinical usefulness for predicting short-term postdischarge mortality. Furthermore, age SI and age MSI were not significantly associated with postdischarge prognosis for patients who received fibrinolysis. CONCLUSIONS: Age SI and age MSI were valuable instruments to identify high postdischarge mortality with comparable predictive ability compared with the classic scores, especially for events within 30 days after hospitalization.