Efficient automated error detection in medical data using deep-learning and label-clustering.

Medical datasets inherently contain errors from subjective or inaccurate test results, or from confounding biological complexities. It is difficult for medical experts to detect these elusive errors manually, due to lack of contextual information, limiting data privacy regulations, and the sheer scale of data to be reviewed. Current methods for training robust artificial intelligence (AI) models on data containing mislabeled examples generally fall into one of several categories-attempting to improve the robustness of the model architecture, the regularization techniques used, the loss function used during training, or selecting a subset of data that contains cleaner labels. This last category requires the ability to efficiently detect errors either prior to or during training, either relabeling them or removing them completely. More recent progress in error detection has focused on using multi-network learning to minimize deleterious effects of errors on training, however, using many neural networks to reach a consensus on which data should be removed can be computationally intensive and inefficient. In this work, a deep-learning based algorithm was used in conjunction with a label-clustering approach to automate error detection. For dataset with synthetic label flips added, these errors were identified with an accuracy of up to 85%, while requiring up to 93% less computing resources to complete compared to a previous model consensus approach developed previously. The resulting trained AI models exhibited greater training stability and up to a 45% improvement in accuracy, from 69 to over 99% compared to the consensus approach, at least 10% improvement on using noise-robust loss functions in a binary classification problem, and a 51% improvement for multi-class classification. These results indicate that practical, automated a priori detection of errors in medical data is possible, without human oversight.

Development of an artificial intelligence model for predicting the likelihood of human embryo euploidy based on blastocyst images from multiple imaging systems during IVF.

STUDY QUESTION: Can an artificial intelligence (AI) model predict human embryo ploidy status using static images captured by optical light microscopy? SUMMARY ANSWER: Results demonstrated predictive accuracy for embryo euploidy and showed a significant correlation between AI score and euploidy rate, based on assessment of images of blastocysts at Day 5 after IVF. WHAT IS KNOWN ALREADY: Euploid embryos displaying the normal human chromosomal complement of 46 chromosomes are preferentially selected for transfer over aneuploid embryos (abnormal complement), as they are associated with improved clinical outcomes. Currently, evaluation of embryo genetic status is most commonly performed by preimplantation genetic testing for aneuploidy (PGT-A), which involves embryo biopsy and genetic testing. The potential for embryo damage during biopsy, and the non-uniform nature of aneuploid cells in mosaic embryos, has prompted investigation of additional, non-invasive, whole embryo methods for evaluation of embryo genetic status. STUDY DESIGN, SIZE, DURATION: A total of 15 192 blastocyst-stage embryo images with associated clinical outcomes were provided by 10 different IVF clinics in the USA, India, Spain and Malaysia. The majority of data were retrospective, with two additional prospectively collected blind datasets provided by IVF clinics using the genetics AI model in clinical practice. Of these images, a total of 5050 images of embryos on Day 5 of in vitro culture were used for the development of the AI model. These Day 5 images were provided for 2438 consecutively treated women who had undergone IVF procedures in the USA between 2011 and 2020. The remaining images were used for evaluation of performance in different settings, or otherwise excluded for not matching the inclusion criteria. PARTICIPANTS/MATERIALS, SETTING, METHODS: The genetics AI model was trained using static 2-dimensional optical light microscope images of Day 5 blastocysts with linked genetic metadata obtained from PGT-A. The endpoint was ploidy status (euploid or aneuploid) based on PGT-A results. Predictive accuracy was determined by evaluating sensitivity (correct prediction of euploid), specificity (correct prediction of aneuploid) and overall accuracy. The Matthew correlation coefficient and receiver-operating characteristic curves and precision-recall curves (including AUC values), were also determined. Performance was also evaluated using correlation analyses and simulated cohort studies to evaluate ranking ability for euploid enrichment. MAIN RESULTS AND THE ROLE OF CHANCE: Overall accuracy for the prediction of euploidy on a blind test dataset was 65.3%, with a sensitivity of 74.6%. When the blind test dataset was cleansed of poor quality and mislabeled images, overall accuracy increased to 77.4%. This performance may be relevant to clinical situations where confounding factors, such as variability in PGT-A testing, have been accounted for. There was a significant positive correlation between AI score and the proportion of euploid embryos, with very high scoring embryos (9.0-10.0) twice as likely to be euploid than the lowest-scoring embryos (0.0-2.4). When using the genetics AI model to rank embryos in a cohort, the probability of the top-ranked embryo being euploid was 82.4%, which was 26.4% more effective than using random ranking, and ∼13-19% more effective than using the Gardner score. The probability increased to 97.0% when considering the likelihood of one of the top two ranked embryos being euploid, and the probability of both top two ranked embryos being euploid was 66.4%. Additional analyses showed that the AI model generalized well to different patient demographics and could also be used for the evaluation of Day 6 embryos and for images taken using multiple time-lapse systems. Results suggested that the AI model could potentially be used to differentiate mosaic embryos based on the level of mosaicism. LIMITATIONS, REASONS FOR CAUTION: While the current investigation was performed using both retrospectively and prospectively collected data, it will be important to continue to evaluate real-world use of the genetics AI model. The endpoint described was euploidy based on the clinical outcome of PGT-A results only, so predictive accuracy for genetic status in utero or at birth was not evaluated. Rebiopsy studies of embryos using a range of PGT-A methods indicated a degree of variability in PGT-A results, which must be considered when interpreting the performance of the AI model. WIDER IMPLICATIONS OF THE FINDINGS: These findings collectively support the use of this genetics AI model for the evaluation of embryo ploidy status in a clinical setting. Results can be used to aid in prioritizing and enriching for embryos that are likely to be euploid for multiple clinical purposes, including selection for transfer in the absence of alternative genetic testing methods, selection for cryopreservation for future use or selection for further confirmatory PGT-A testing, as required. STUDY FUNDING/COMPETING INTEREST(S): Life Whisperer Diagnostics is a wholly owned subsidiary of the parent company, Presagen Holdings Pty Ltd. Funding for the study was provided by Presagen with grant funding received from the South Australian Government: Research, Commercialisation, and Startup Fund (RCSF). 'In kind' support and embryology expertise to guide algorithm development were provided by Ovation Fertility. 'In kind' support in terms of computational resources provided through the Amazon Web Services (AWS) Activate Program. J.M.M.H., D.P. and M.P. are co-owners of Life Whisperer and Presagen. S.M.D., M.A.D. and T.V.N. are employees or former employees of Life Whisperer. S.M.D, J.M.M.H, M.A.D, T.V.N., D.P. and M.P. are listed as inventors of patents relating to this work, and also have stock options in the parent company Presagen. M.V. sits on the advisory board for the global distributor of the technology described in this study and also received support for attending meetings. TRIAL REGISTRATION NUMBER: N/A.

A novel decentralized federated learning approach to train on globally distributed, poor quality, and protected private medical data.

Training on multiple diverse data sources is critical to ensure unbiased and generalizable AI. In healthcare, data privacy laws prohibit data from being moved outside the country of origin, preventing global medical datasets being centralized for AI training. Data-centric, cross-silo federated learning represents a pathway forward for training on distributed medical datasets. Existing approaches typically require updates to a training model to be transferred to a central server, potentially breaching data privacy laws unless the updates are sufficiently disguised or abstracted to prevent reconstruction of the dataset. Here we present a completely decentralized federated learning approach, using knowledge distillation, ensuring data privacy and protection. Each node operates independently without needing to access external data. AI accuracy using this approach is found to be comparable to centralized training, and when nodes comprise poor-quality data, which is common in healthcare, AI accuracy can exceed the performance of traditional centralized training.

Automated detection of poor-quality data: case studies in healthcare.

The detection and removal of poor-quality data in a training set is crucial to achieve high-performing AI models. In healthcare, data can be inherently poor-quality due to uncertainty or subjectivity, but as is often the case, the requirement for data privacy restricts AI practitioners from accessing raw training data, meaning manual visual verification of private patient data is not possible. Here we describe a novel method for automated identification of poor-quality data, called Untrainable Data Cleansing. This method is shown to have numerous benefits including protection of private patient data; improvement in AI generalizability; reduction in time, cost, and data needed for training; all while offering a truer reporting of AI performance itself. Additionally, results show that Untrainable Data Cleansing could be useful as a triage tool to identify difficult clinical cases that may warrant in-depth evaluation or additional testing to support a diagnosis.

Development of an artificial intelligence-based assessment model for prediction of embryo viability using static images captured by optical light microscopy during IVF.

STUDY QUESTION: Can an artificial intelligence (AI)-based model predict human embryo viability using images captured by optical light microscopy? SUMMARY ANSWER: We have combined computer vision image processing methods and deep learning techniques to create the non-invasive Life Whisperer AI model for robust prediction of embryo viability, as measured by clinical pregnancy outcome, using single static images of Day 5 blastocysts obtained from standard optical light microscope systems. WHAT IS KNOWN ALREADY: Embryo selection following IVF is a critical factor in determining the success of ensuing pregnancy. Traditional morphokinetic grading by trained embryologists can be subjective and variable, and other complementary techniques, such as time-lapse imaging, require costly equipment and have not reliably demonstrated predictive ability for the endpoint of clinical pregnancy. AI methods are being investigated as a promising means for improving embryo selection and predicting implantation and pregnancy outcomes. STUDY DESIGN, SIZE, DURATION: These studies involved analysis of retrospectively collected data including standard optical light microscope images and clinical outcomes of 8886 embryos from 11 different IVF clinics, across three different countries, between 2011 and 2018. PARTICIPANTS/MATERIALS, SETTING, METHODS: The AI-based model was trained using static two-dimensional optical light microscope images with known clinical pregnancy outcome as measured by fetal heartbeat to provide a confidence score for prediction of pregnancy. Predictive accuracy was determined by evaluating sensitivity, specificity and overall weighted accuracy, and was visualized using histograms of the distributions of predictions. Comparison to embryologists' predictive accuracy was performed using a binary classification approach and a 5-band ranking comparison. MAIN RESULTS AND THE ROLE OF CHANCE: The Life Whisperer AI model showed a sensitivity of 70.1% for viable embryos while maintaining a specificity of 60.5% for non-viable embryos across three independent blind test sets from different clinics. The weighted overall accuracy in each blind test set was >63%, with a combined accuracy of 64.3% across both viable and non-viable embryos, demonstrating model robustness and generalizability beyond the result expected from chance. Distributions of predictions showed clear separation of correctly and incorrectly classified embryos. Binary comparison of viable/non-viable embryo classification demonstrated an improvement of 24.7% over embryologists' accuracy (P = 0.047, n = 2, Student's t test), and 5-band ranking comparison demonstrated an improvement of 42.0% over embryologists (P = 0.028, n = 2, Student's t test). LIMITATIONS, REASONS FOR CAUTION: The AI model developed here is limited to analysis of Day 5 embryos; therefore, further evaluation or modification of the model is needed to incorporate information from different time points. The endpoint described is clinical pregnancy as measured by fetal heartbeat, and this does not indicate the probability of live birth. The current investigation was performed with retrospectively collected data, and hence it will be of importance to collect data prospectively to assess real-world use of the AI model. WIDER IMPLICATIONS OF THE FINDINGS: These studies demonstrated an improved predictive ability for evaluation of embryo viability when compared with embryologists' traditional morphokinetic grading methods. The superior accuracy of the Life Whisperer AI model could lead to improved pregnancy success rates in IVF when used in a clinical setting. It could also potentially assist in standardization of embryo selection methods across multiple clinical environments, while eliminating the need for complex time-lapse imaging equipment. Finally, the cloud-based software application used to apply the Life Whisperer AI model in clinical practice makes it broadly applicable and globally scalable to IVF clinics worldwide. STUDY FUNDING/COMPETING INTEREST(S): Life Whisperer Diagnostics, Pty Ltd is a wholly owned subsidiary of the parent company, Presagen Pty Ltd. Funding for the study was provided by Presagen with grant funding received from the South Australian Government: Research, Commercialisation and Startup Fund (RCSF). 'In kind' support and embryology expertise to guide algorithm development were provided by Ovation Fertility. J.M.M.H., D.P. and M.P. are co-owners of Life Whisperer and Presagen. Presagen has filed a provisional patent for the technology described in this manuscript (52985P pending). A.P.M. owns stock in Life Whisperer, and S.M.D., A.J., T.N. and A.P.M. are employees of Life Whisperer.

Timescales of water accumulation in magmas and implications for short warning times of explosive eruptions.

Water plays a key role in magma genesis, differentiation, ascent and, finally, eruption. Despite the recognized crucial function of water, there are still several issues that continue to blur our view about its role in magmatic systems. What are the timescales of H2O accumulation in crystallizing magmas? What are the ascent rates of water-rich residual melts leading to explosive eruptions? Here, we track the timescale of water accumulation in a residual melt resulting from crystallization of a hydrous CO2-bearing magmatic mass stored at mid- to deep-crustal levels in a subduction-related geodynamic setting. Our results indicate that, after a repose period ranging from few to several thousand years, water-rich melts with water concentrations larger than 6-9 wt.% can migrate towards the Earth surface in very short timescales, on the order of days or even hours, possibly triggering explosive eruptions with short warning times and devoid of long-term geophysical precursors.

Early cytomegalovirus-specific T-cell response and estimated glomerular filtration rate identify patients at high risk of infection after renal transplantation.

BACKGROUND: Assessing the risk of cytomegalovirus (CMV) viremia in kidney transplant recipients (KTR) may be helpful to indicate in which patient it is worth starting antiviral treatment during preemptive strategy. METHODS: In 40 CMV-seropositive KTR preemptively treated with ganciclovir, we used interferon (IFN)-γ ELISpot test to evaluate whether monitoring T cells directed against phosphoprotein (pp) 65 and immediate early (IE)-1 antigens could predict the onset of viremia. RESULTS: CMV viremia occurred in 24 patients (60%) within 120 days after transplantation. Non-viremic patients had higher anti-pp65, anti-IE-1 T cells, and estimated glomerular filtration rate (eGFR) in the first 90 days after transplantation. At logistic regression, anti-pp65, anti-IE-1 T cells, and eGFR measured at day 30 were significantly associated with CMV infection. Cutoff values of 15 spot-forming cells (SFCs)/200,000 peripheral blood mononuclear cells (PBMCs) for anti-IE, 40 SFCs/200,000 PBMCs for anti-pp65, and 46.6 mL/min/1.73 m(2) for eGFR, respectively, predicted the risk of CMV infection with high sensitivity and specificity (area under the receiver operating characteristic curve >0.75). Using a classification tree model, we identified as high-risk patients those showing anti-pp65 <42 SFCs/200,000 PBMCs and eGFR <62 mL/min/1.73 m(2) , as well as anti-pp65 ≥42 and anti-IE-1 <6.5 SFCs/200,000 PBMCs. CONCLUSION: Monitoring CMV-specific T-cell responses and eGFR in the first month post transplant can identify patients at high risk of CMV infection, for whom preemptive antiviral therapy is recommended.

High-temperature apparatus for chaotic mixing of natural silicate melts.

A unique high-temperature apparatus was developed to trigger chaotic mixing at high-temperature (up to 1800 °C). This new apparatus, which we term Chaotic Magma Mixing Apparatus (COMMA), is designed to carry out experiments with high-temperature and high-viscosity (up to 10(6) Pa s) natural silicate melts. This instrument allows us to follow in time and space the evolution of the mixing process and the associated modulation of chemical composition. This is essential to understand the dynamics of magma mixing and related chemical exchanges. The COMMA device is tested by mixing natural melts from Aeolian Islands (Italy). The experiment was performed at 1180 °C using shoshonite and rhyolite melts, resulting in a viscosity ratio of more than three orders of magnitude. This viscosity ratio is close to the maximum possible ratio of viscosity between high-temperature natural silicate melts. Results indicate that the generated mixing structures are topologically identical to those observed in natural volcanic rocks highlighting the enormous potential of the COMMA to replicate, as a first approximation, the same mixing patterns observed in the natural environment. COMMA can be used to investigate in detail the space and time development of magma mixing providing information about this fundamental petrological and volcanological process that would be impossible to investigate by direct observations. Among the potentials of this new experimental device is the construction of empirical relationships relating the mixing time, obtained through experimental time series, and chemical exchanges between the melts to constrain the mixing-to-eruption time of volcanic systems, a fundamental topic in volcanic hazard assessment.

Diagnostic utility of LightCycler SeptiFast and procalcitonin assays in the diagnosis of bloodstream infection in immunocompromised patients.

Sepsis is an increasingly prevalent cause of death, and management in the early stage is a critical issue. However, microbiological findings are generally obtained late during the course of the disease. In this study, we evaluated the clinical utility of procalcitonin (PCT) in improving the diagnosis of bloodstream infections and the potential utility of the SeptiFast (SF) test, a multiplex pathogen detection system, in the etiological diagnosis of immunocompromised patients. Seventy-nine hospitalized immunocompromised patients were included in this study. Our results demonstrate that while the PCT value correlates highly with sepsis, the results do not discriminate adequately enough to justify its independent use as a diagnostic tool. The SF test, combined with blood cultures, improves microbiological data in immunocompromised patients, especially in cases of previous antibiotic therapy and invasive fungal infection.

[Polyomavirus BK nephropathy in renal transplant: 2 cases with different clinical expressions and review of the literature]. / Nefropatia da Poliomavirus BK nel trapianto renale: 2 casi con espressione clinica diversa e revisione della letteratura.

INTRODUCTION: Polyomavirus BK nephropathy is emerging as a significant cause of interstitial nephritis and allograft dysfunction (1-2). CASE REPORT: Two patients with renal transplants from cadaveric kidneys were treated with Tacrolimus plus Mycophenolate Mofetil (MMF) and Cyclosporine plus MMF, respectively. Their renal function gradually deteriorated eight to twelve months after the transplant. The renal biopsy of the first patient showed signs of significant interstitial tubulite, which necessitated the anti-rejection therapy with intravenous steroid pulses. After the pulses there was an additional dramatic increase in plasmatic creatinine, which suggested a revaluation of the kidney biopsy because of suspected Polyomavirus BK (BKV) nephropathy. In fact, after a more careful review, the suspicion of BKV infection was confirmed by the presence of intranuclear inclusions of tubular epithelium cells and marked denudation of the tubular basal membrane. The subsequent screening in both cases confirmed the presence of decoy cells in the urine, while the immunohistochemical analysis of the renal biopsy was strongly positive for the SV40 antigen. Our diagnosis was that of interstitial nephritis due to Polyomavirus BK that, in the first patient, was expressed by more aggressive clinical progress, probably due to enhanced immunosuppression from incorrect diagnosis of the interstitial rejection. The pre-transplant clinical outcome of the first patient was characterised by proteinuric nephropathy without any histological confirmation. Furthermore, we observed abundant pre-transplant residual diuresis and glucose intolerance. All these elements led us to hypothesise that native kidneys could have a fundamental role as viral reservoirs. CONCLUSION: Even though we reconfirm the decisive role of the immunosuppressive therapy and of the donor s kidney as the fundamental causes of Polyomavirus reactivation, we believe that it cannot be the result of a possible active role by the native kidney. In fact, as already noted, the SV40 genome is important in the pathogenesis of focal gomerulosclerosis. Furthermore, reports of polyoma nephropathy in not-yet-transplanted patients could accredit the role of the native kidneys as important viral reservoirs capable of inducing nephropathy in renal transplant patients.

Neonatal screening for 21-hydroxylase deficiency: a microfilter paper method for 17-alpha-hydroxyprogesterone assay.

A micromethod for measuring 17 alpha-hydroxyprogesterone in blood collected on filter paper has been developed. Our method is rapid, easy and has the specificity, accuracy and precision of the radioimmunoassay in whole blood. The method has been applied for screening patients with congenital adrenal hyperplasia (CAH) due to 21-hydroxylase deficiency. Fifty samples collected on filter paper were assayed by our method, using 125I as tracer, and results were compared with those obtained for the same samples using a tritium tracer. The agreement between the two methods was particularly good in the area ranging from 15 to 100 pg/disc. In one neonate the diagnosis of CAH was made utilizing the microfilter paper method. Our method is a promising screening test for CAH. An indication of the advantages or disadvantages of this type of screening will become available when an adequate number of infants has been examined.