Use of federated learning to develop an artificial intelligence model predicting usable blastocyst formation from pre-ICSI oocyte images.

Research Question: Can federated learning be used to develop an artificial intelligence (AI) model for evaluating oocyte competence using two-dimensional images of denuded oocytes in metaphase II prior to intracytoplasmic sperm injection (ICSI)?

Results: The oocyte AI model demonstrated area under the curve (AUC) up to 0.65 on two blind test datasets. High sensitivity for predicting competent oocytes (83-88%) was offset by lower specificity (26-36%).

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.

The porosity of felsic pyroclasts: laboratory validation of field-based approaches.

Unlabelled: Volcanic eruptions are driven by magma rising through Earth's crust. The style of an eruption depends on intrinsic and extrinsic parameters and is commonly a dynamic process. Thorough and holistic investigation of the related products is key to understanding eruptive phenomena and assessment of volcano-specific hazards.

An artificial intelligence model correlated with morphological and genetic features of blastocyst quality improves ranking of viable embryos.

Research Question: Can better methods be developed to evaluate the performance and characteristics of an artificial intelligence model for evaluating the likelihood of clinical pregnancy based on analysis of day-5 blastocyst-stage embryos, such that performance evaluation more closely reflects clinical use in IVF procedures, and correlations with known features of embryo quality are identified?

Design: De-identified images were provided retrospectively or collected prospectively by IVF clinics using the artificial intelligence model in clinical practice. A total of 9359 images were provided by 18 IVF clinics across six countries, from 4709 women who underwent IVF between 2011 and 2021. Main outcome measures included clinical pregnancy outcome (fetal heartbeat at first ultrasound scan), embryo morphology score, and/or pre-implantation genetic testing for aneuploidy (PGT-A) results.

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.

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.

The D.A.M.A. Project at Terni Hospital, Italy.

Experience shows how difficult it is for a person with disabilities to cope with the reality of a hospital, especially if he or she has an intellectual disability. The difficulty in carrying out even simple diagnostic and therapeutic manoeuvres, the complexity of the pathologies, the difficulty in relating to the patient all make it a real risk that many medical problems of patients with disabilities are overlooked or denied altogether. The person with a disability has the right to all care, not only that related to his or her particular pathology, but also that required for other specialist or general pathologies.

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.

[A cross-sectional study on the prevalence and incidence of pressure ulcers in an Italian University Hospital-Umbria Region].

Objective: The aim of the present study was to assess the prevalence and incidence of pressure ulcers (PUs) in patients hospitalized in a University Hospital in central Italy.

Methods: We carried out a prevalence and incidence study on PUs and an additional prevalence estimate of PUs was also produced ten days after the first assessment. All data were explored by descriptive statistics, the Chi-square test and a multivariate analysis.

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.

Cooling history and emplacement of a pyroxenitic lava as proxy for understanding Martian lava flows.

Terrestrial analogues are often investigated to get insights into the geological processes occurring on other planetary bodies. Due to its thickness and petrological similarities, the pyroxenitic layer of the 120m-thick magmatic pile Theo's Flow (Archean Abitibi greenstone belt Ontario, Canada), has always been regarded as the terrestrial analogue for Martian nakhlites. However, its origin and cooling history and, as a consequence those of nakhlites, have always been a matter of vigorous debate.

Retrieving magma composition from TIR spectra: implications for terrestrial planets investigations.

Emissivity and reflectance spectra have been investigated on two series of silicate glasses, having compositions belonging to alkaline and subalkaline series, covering the most common terrestrial igneous rocks. Glasses were synthesized starting from natural end-members outcropping at Vulcano Island (Aeolian Islands, Italy) and on Snake River Plain (USA). Results show that the shift of the spectra, by taking Christiansen feature (CF) as a reference point, is correlated with SiO content, the SCFM factor and/or the degree of polymerization state via the NBO/T and temperature.

An experimental device for characterizing degassing processes and related elastic fingerprints: Analog volcano seismo-acoustic observations.

A challenging objective of modern volcanology is to quantitatively characterize eruptive/degassing regimes from geophysical signals (in particular seismic and infrasonic), for both research and monitoring purposes. However, the outcomes of the attempts made so far are still considered very uncertain because volcanoes remain inaccessible when deriving quantitative information on crucial parameters such as plumbing system geometry and magma viscosity. In order to improve our knowledge of volcanic systems, a novel experimental device, which is capable of mimicking volcanic degassing processes with different regimes and gas flow rates, and allowing for the investigation of the related seismo-acoustic emissions, was designed and developed.

Determination of changes in the concentration and distribution of elements within olive drupes (cv. Leccino) from Se biofortified plants, using laser ablation inductively coupled plasma mass spectrometry.

Background: Biofortification of food crops has been used to increase the intake of Se in the human diet, even though this may change the concentration of other elements and modify the nutritional properties of the enriched food. Selenium biofortification programs should include routine assessment of the overall mineral composition of enriched plants.

Results: Laser ablation inductively coupled plasma mass spectrometry (LA ICP-MS) was used for the assessment of mineral composition of table olives.

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 HO 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 CO-bearing magmatic mass stored at mid- to deep-crustal levels in a subduction-related geodynamic setting.

Enhancement of eruption explosivity by heterogeneous bubble nucleation triggered by magma mingling.

We present new evidence that shows magma mingling can be a key process during highly explosive eruptions. Using fractal analysis of the size distribution of trachybasaltic fragments found on the inner walls of bubbles in trachytic pumices, we show that the more mafic component underwent fracturing during quenching against the trachyte. We propose a new mechanism for how this magmatic interaction at depth triggered rapid heterogeneous bubble nucleation and growth and could have enhanced eruption explosivity.

Approximate chemical analysis of volcanic glasses using Raman spectroscopy.

The effect of chemical composition on the Raman spectra of a series of natural calcalkaline silicate glasses has been quantified by performing electron microprobe analyses and obtaining Raman spectra on glassy filaments (~450 µm) derived from a magma mingling experiment. The results provide a robust compositionally-dependent database for the Raman spectra of natural silicate glasses along the calcalkaline series. An empirical model based on both the acquired Raman spectra and an ideal mixing equation between calcalkaline basaltic and rhyolitic end-members is constructed enabling the estimation of the chemical composition and degree of polymerization of silicate glasses using Raman spectra.

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.

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.

Concentration variance decay during magma mixing: a volcanic chronometer.

The mixing of magmas is a common phenomenon in explosive eruptions. Concentration variance is a useful metric of this process and its decay (CVD) with time is an inevitable consequence during the progress of magma mixing. In order to calibrate this petrological/volcanological clock we have performed a time-series of high temperature experiments of magma mixing.

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.

Prospective study of BKV nephropathy in 117 renal transplant recipients.

Nephropathy caused by poliomavirus (BKVAN) in transplant recipients is responsible for the loss of the transplanted organ. In this study we suggest a non-invasive diagnostic protocol for the early identification of BKVAN during follow-up treatments. In 117 kidney transplant recipients follow-up was performed every three months during a two year period after transplantation and a positive screening result was confirmed and assessed by quantitative assays (BKV DNA load in plasma and urine).

A comparative evaluation between real time Roche COBas TAQMAN 48 HCV and bDNA Bayer Versant HCV 3.0.

The HCV virus is a common human pathogen made of a single stranded RNA genome with 9600nt. This work compared two different commercial methods used for HCV viral load, the bDNA Bayer Versant HCV 3.0 and the RealTime Roche COBAS TaqMan 48 HCV.