Dual glucagon-like peptide-1 and glucagon receptor agonism reduces energy intake in type 2 diabetes with obesity.

AIMS: To establish which components of energy balance mediate the clinically significant weight loss demonstrated with use of cotadutide, a glucagon-like peptide-1 (GLP-1)/glucagon receptor dual agonist, in early-phase studies. MATERIALS AND METHODS: We conducted a phase 2a, single-centre, randomized, placebo-controlled trial in overweight and obese adults with type 2 diabetes. Following a 16-day single-blind placebo run-in, participants were randomized 2:1 to double-blind 42-day subcutaneous treatment with cotadutide (100-300 µg daily) or placebo. The primary outcome was percentage weight change. Secondary outcomes included change in energy intake (EI) and energy expenditure (EE). RESULTS: A total of 12 participants (63%) in the cotadutide group and seven (78%) in the placebo group completed the study. The mean (90% confidence interval [CI]) weight change was -4.0% (-4.9%, -3.1%) and -1.4% (-2.7%, -0.1%) for the cotadutide and placebo groups, respectively (p = 0.011). EI was lower with cotadutide versus placebo (-41.3% [-66.7, -15.9]; p = 0.011). Difference in EE (per kJ/kg lean body mass) for cotadutide versus placebo was 1.0% (90% CI -8.4, 10.4; p = 0.784), assessed by doubly labelled water, and -6.5% (90% CI -9.3, -3.7; p < 0.001), assessed by indirect calorimetry. CONCLUSION: Weight loss with cotadutide is primarily driven by reduced EI, with relatively small compensatory changes in EE.

Environmental drivers of Arctic communities based on metabarcoding of marine sediment eDNA.

Our ability to assess biodiversity at relevant spatial and temporal scales for informing management is of increasing importance given this is foundational to identify and mitigate the impacts of global change. Collecting baseline information and tracking ecological changes are particularly important for areas experiencing rapid changes and representing data gaps such as Arctic marine ecosystems. Environmental DNA has the potential to provide such data. We extracted environmental DNA from 90 surface sediment samples to assess eukaryote diversity around Greenland and Svalbard using two separate primer pairs amplifying different sections of the 18S rRNA gene. We detected 27 different phyla and 99 different orders and found that temperature and the change in temperature explained the most variation in the community in a single linear model, while latitude, sea ice cover and change in temperature explained the most variation in the community when assessed by individual non-linear models. We identified potential indicator taxa for Arctic climate change, including a terebellid annelid worm. In conclusion, our study demonstrates that environmental DNA offers a feasible method to assess biodiversity and identifies warming as a key driver of differences in biodiversity across these remote ecosystems.

Using sequences of life-events to predict human lives.

Here we represent human lives in a way that shares structural similarity to language, and we exploit this similarity to adapt natural language processing techniques to examine the evolution and predictability of human lives based on detailed event sequences. We do this by drawing on a comprehensive registry dataset, which is available for Denmark across several years, and that includes information about life-events related to health, education, occupation, income, address and working hours, recorded with day-to-day resolution. We create embeddings of life-events in a single vector space, showing that this embedding space is robust and highly structured. Our models allow us to predict diverse outcomes ranging from early mortality to personality nuances, outperforming state-of-the-art models by a wide margin. Using methods for interpreting deep learning models, we probe the algorithm to understand the factors that enable our predictions. Our framework allows researchers to discover potential mechanisms that impact life outcomes as well as the associated possibilities for personalized interventions.

Insights into the circular: The cryptic plasmidome and its derived antibiotic resistome in the urban water systems.

Plasmids have been a concern in the dissemination and evolution of antibiotic resistance in the environment. In this study, we investigated the total pool of plasmids (plasmidome) and its derived antibiotic resistance genes (ARGs) in different compartments of urban water systems (UWSs) in three European countries representing different antibiotic usage regimes. We applied a direct plasmidome approach using wet-lab methods to enrich circular DNA in the samples, followed by shotgun sequencing and in silico contig circularisation. We identified 9538 novel sequences in a total of 10,942 recovered circular plasmids. Of these, 66 were identified as conjugative, 1896 mobilisable and 8970 non-mobilisable plasmids. The UWSs' plasmidome was dominated by small plasmids (≤10 Kbp) representing a broad diversity of mobility (MOB) types and incompatibility (Inc) groups. A shared collection of plasmids from different countries was detected in all treatment compartments, and plasmids could be source-tracked in the UWSs. More than half of the ARGs-encoding plasmids carried mobility genes for mobilisation/conjugation. The richness and abundance of ARGs-encoding plasmids generally decreased with the flow, while we observed that non-mobilisable ARGs-harbouring plasmids maintained their abundance in the Spanish wastewater treatment plant. Overall, our work unravels that the UWS plasmidome is dominated by cryptic (i.e., non-mobilisable, non-typeable and previously unknown) plasmids. Considering that some of these plasmids carried ARGs, were prevalent across three countries and could persist throughout the UWSs compartments, these results should alarm and call for attention.

Weighted Burgers Vector analysis of orientation fields from high-angular resolution electron backscatter diffraction.

The Weighted Burgers Vector (WBV) method can extract information about dislocation types and densities present in distorted crystalline materials from electron backscatter diffraction (EBSD) maps, using no assumptions about which slip systems might be present. Furthermore, high-angular resolution EBSD (HR-EBSD) uses a cross-correlation procedure to increase the angular precision of EBSD measurements by an order of magnitude compared to conventional EBSD. However, the WBV technique has not previously been applied to HR-EBSD data and therefore it remains unclear as to which low-angle substructures can be reliably characterised by WBV analysis of conventional EBSD data and which require additional HR-EBSD processing. To establish some practical examples that can be used to guide future data-acquisition strategies, we compare the output of the WBV method when applied to conventional EBSD data and HR-EBSD data collected from the most common minerals in Earth's lower crust (plagioclase feldspar) and upper mantle (olivine). The results demonstrate that HR-EBSD and WBV processing are complementary techniques. The increase in angular precision achieved with HR-EBSD processing allows low-angle (on the order of 0.1°) structures, which are obscured by noise in conventional EBSD data, to be analyzed quantitatively using the WBV method. Combining the WBV and HR-EBSD methods increases the precision of calculated WBV directions, which is essential when using information about active slip systems to infer likely deformation mechanisms from naturally deformed microstructures. This increase in precision is particularly important for low-symmetry crystals, such as plagioclase, that have a wide range of available slip systems that vary in relative activity with changing pressure, temperature and differential stress. Because WBV directions are calculated using no assumptions about which slip systems may be present, combining this technique with HR-EBSD to refine the precision of lattice orientation gradients is ideal for investigating complex natural materials with unknown deformation histories.

Cotadutide promotes glycogenolysis in people with overweight or obesity diagnosed with type 2 diabetes.

Cotadutide is a dual glucagon-like peptide 1 and glucagon receptor agonist under development for the treatment of non-alcoholic steatohepatitis and type 2 diabetes mellitus (T2DM) and chronic kidney disease. Non-alcoholic steatohepatitis is a complex disease with no approved pharmacotherapies, arising from an underlying state of systemic metabolic dysfunction in association with T2DM and obesity. Cotadutide has been shown to improve glycaemic control, body weight, lipids, liver fat, inflammation and fibrosis. We conducted a two-part, randomized phase 2a trial in men and women with overweight or obesity diagnosed with T2DM to evaluate the efficacy and safety of cotadutide compared with placebo and liraglutide. The primary endpoints were change from baseline to day 28 of treatment in postprandial hepatic glycogen (part A) and to day 35 of treatment in fasting hepatic glycogen (part B) with cotadutide versus placebo. Secondary endpoints in part B were changes in fasting hepatic glycogen with cotadutide versus the mono glucagon-like peptide 1 receptor agonist, liraglutide, and change in hepatic fat fraction. The trial met its primary endpoint. We showed that cotadutide promotes greater reductions in liver glycogen and fat compared with placebo and liraglutide. Safety and tolerability findings with cotadutide were comparable to those of previous reports. Thus, this work provides evidence of additional benefits of cotadutide that could be attributed to glucagon receptor engagement. Our results suggest that cotadutide acts on the glucagon receptor in the human liver to promote glycogenolysis and improve the metabolic health of the liver. ClinicalTrials.gov registration: NCT03555994 .

Widespread and largely unknown prophage activity, diversity, and function in two genera of wheat phyllosphere bacteria.

Environmental bacteria host an enormous number of prophages, but their diversity and natural functions remain largely elusive. Here, we investigate prophage activity and diversity in 63 Erwinia and Pseudomonas strains isolated from flag leaves of wheat grown in a single field. Introducing and validating Virion Induction Profiling Sequencing (VIP-Seq), we identify and quantify the activity of 120 spontaneously induced prophages, discovering that some phyllosphere bacteria produce more than 108 virions/mL in overnight cultures, with significant induction also observed in planta. Sequence analyses and plaque assays reveal E. aphidicola prophages contribute a majority of intraspecies genetic diversity and divide their bacterial hosts into antagonistic factions engaged in widespread microbial warfare, revealing the importance of prophage-mediated microdiversity. When comparing spontaneously active prophages with predicted prophages we also find insertion sequences are strongly correlated with non-active prophages. In conclusion, we discover widespread and largely unknown prophage diversity and function in phyllosphere bacteria.

Cessation of grazing causes biodiversity loss and homogenization of soil food webs.

There is widespread concern that cessation of grazing in historically grazed ecosystems is causing biotic homogenization and biodiversity loss. We used 12 montane grassland sites along an 800 km north-south gradient across the UK, to test whether cessation of grazing affects local α- and ß-diversity of below-ground food webs. We show cessation of grazing leads to strongly decreased α-diversity of most groups of soil microbes and fauna, particularly of relatively rare taxa. By contrast, the ß-diversity varied between groups of soil organisms. While most soil microbial communities exhibited increased homogenization after cessation of grazing, we observed decreased homogenization for soil fauna after cessation of grazing. Overall, our results indicate that exclusion of domesticated herbivores from historically grazed montane grasslands has far-ranging negative consequences for diversity of below-ground food webs. This underscores the importance of grazers for maintaining the diversity of below-ground communities, which play a central role in ecosystem functioning.

Machine-learning vs. logistic regression for preoperative prediction of medical morbidity after fast-track hip and knee arthroplasty-a comparative study.

BACKGROUND: Machine-learning models may improve prediction of length of stay (LOS) and morbidity after surgery. However, few studies include fast-track programs, and most rely on administrative coding with limited follow-up and information on perioperative care. This study investigates potential benefits of a machine-learning model for prediction of postoperative morbidity in fast-track total hip (THA) and knee arthroplasty (TKA). METHODS: Cohort study in consecutive unselected primary THA/TKA between 2014-2017 from seven Danish centers with established fast-track protocols. Preoperative comorbidity and prescribed medication were recorded prospectively and information on length of stay and readmissions was obtained through the Danish National Patient Registry and medical records. We used a machine-learning model (Boosted Decision Trees) based on boosted decision trees with 33 preoperative variables for predicting "medical" morbidity leading to LOS > 4 days or 90-days readmissions and compared to a logistical regression model based on the same variables. We also evaluated two parsimonious models, using the ten most important variables in the full machine-learning and logistic regression models. Data collected between 2014-2016 (n:18,013) was used for model training and data from 2017 (n:3913) was used for testing. Model performances were analyzed using precision, area under receiver operating (AUROC) and precision recall curves (AUPRC), as well as the Mathews Correlation Coefficient. Variable importance was analyzed using Shapley Additive Explanations values. RESULTS: Using a threshold of 20% "risk-patients" (n:782), precision, AUROC and AUPRC were 13.6%, 76.3% and 15.5% vs. 12.4%, 74.7% and 15.6% for the machine-learning and logistic regression model, respectively. The parsimonious machine-learning model performed better than the full logistic regression model. Of the top ten variables, eight were shared between the machine-learning and logistic regression models, but with a considerable age-related variation in importance of specific types of medication. CONCLUSION: A machine-learning model using preoperative characteristics and prescriptions slightly improved identification of patients in high-risk of "medical" complications after fast-track THA and TKA compared to a logistic regression model. Such algorithms could help find a manageable population of patients who may benefit most from intensified perioperative care.

Field and laboratory guidelines for reliable bioinformatic and statistical analysis of bacterial shotgun metagenomic data.

Shotgun metagenomics is an increasingly cost-effective approach for profiling environmental and host-associated microbial communities. However, due to the complexity of both microbiomes and the molecular techniques required to analyze them, the reliability and representativeness of the results are contingent upon the field, laboratory, and bioinformatic procedures employed. Here, we consider 15 field and laboratory issues that critically impact downstream bioinformatic and statistical data processing, as well as result interpretation, in bacterial shotgun metagenomic studies. The issues we consider encompass intrinsic properties of samples, study design, and laboratory-processing strategies. We identify the links of field and laboratory steps with downstream analytical procedures, explain the means for detecting potential pitfalls, and propose mitigation measures to overcome or minimize their impact in metagenomic studies. We anticipate that our guidelines will assist data scientists in appropriately processing and interpreting their data, while aiding field and laboratory researchers to implement strategies for improving the quality of the generated results.

Genetic rearrangements in Pseudomonas amygdali pathovar aesculi shape coronatine plasmids.

Plant pathogenic Pseudomonas species use multiple classes of toxins and virulence factors during host infection. The genes encoding these pathogenicity factors are often located on plasmids and other mobile genetic elements, suggesting that they are acquired through horizontal gene transfer to confer an evolutionary advantage for successful adaptation to host infection. However, the genetic rearrangements that have led to mobilization of the pathogenicity genes are not fully understood. In this study, we have sequenced and analyzed the complete genome sequences of four Pseudomonas amygdali pv. aesculi (Pae), which infect European horse chestnut trees (Aesculus hippocastanum) and belong to phylogroup 3 of the P. syringae species complex. The four investigated genomes contain six groups of plasmids that all encode pathogenicity factors. Effector genes were found to be mostly associated with insertion sequence elements, suggesting that virulence genes are generally mobilized and potentially undergo horizontal gene transfer after transfer to a conjugative plasmid. We show that the biosynthetic gene cluster encoding the phytotoxin coronatine was recently transferred from a chromosomal location to a mobilizable plasmid that subsequently formed a co-integrate with a conjugative plasmid.

CUX1-related neurodevelopmental disorder: deep insights into phenotype-genotype spectrum and underlying pathology.

Heterozygous, pathogenic CUX1 variants are associated with global developmental delay or intellectual disability. This study delineates the clinical presentation in an extended cohort and investigates the molecular mechanism underlying the disorder in a Cux1+/- mouse model. Through international collaboration, we assembled the phenotypic and molecular information for 34 individuals (23 unpublished individuals). We analyze brain CUX1 expression and susceptibility to epilepsy in Cux1+/- mice. We describe 34 individuals, from which 30 were unrelated, with 26 different null and four missense variants. The leading symptoms were mild to moderate delayed speech and motor development and borderline to moderate intellectual disability. Additional symptoms were muscular hypotonia, seizures, joint laxity, and abnormalities of the forehead. In Cux1+/- mice, we found delayed growth, histologically normal brains, and increased susceptibility to seizures. In Cux1+/- brains, the expression of Cux1 transcripts was half of WT animals. Expression of CUX1 proteins was reduced, although in early postnatal animals significantly more than in adults. In summary, disease-causing CUX1 variants result in a non-syndromic phenotype of developmental delay and intellectual disability. In some individuals, this phenotype ameliorates with age, resulting in a clinical catch-up and normal IQ in adulthood. The post-transcriptional balance of CUX1 expression in the heterozygous brain at late developmental stages appears important for this favorable clinical course.

Geochemical landscapes as drivers of wildlife reproductive success: Insights from a high-Arctic ecosystem.

The bioavailability of essential and non-essential elements in vegetation is expected to influence the performance of free-ranging terrestrial herbivores. However, attempts to relate the use of geochemical landscapes by animal populations directly to reproductive output are currently lacking. Here we measured concentrations of 14 essential and non-essential elements in soil and vegetation samples collected in the Zackenberg valley, northeast Greenland, and linked these to environmental conditions to spatially predict and map geochemical landscapes. We then used long-term (1996-2021) survey data of muskoxen (Ovibos moschatus) to quantify annual variation in the relative use of essential and non-essential elements in vegetated sites and their relationship to calf recruitment the following year. Results showed that the relative use of the geochemical landscape by muskoxen varied substantially between years and differed among elements. Selection for vegetated sites with higher levels of the essential elements N, Cu, Se, and Mo was positively linked to annual calf recruitment. In contrast, selection for vegetated sites with higher concentrations of the non-essential elements As and Pb was negatively correlated to annual calf recruitment. Based on the concentrations measured in our study, we found no apparent associations between annual calf recruitment and levels of C, Mn, Co, Zn, Cd, Ba, Hg, and C:N ratio in the vegetation. We conclude that the spatial distribution and access to essential and non-essential elements are important drivers of reproductive output in muskoxen, which may also apply to other wildlife populations. The value of geochemical landscapes to assess habitat-performance relationships is likely to increase under future environmental change.

Pheno- and Genotyping of Three Novel Bacteriophage Genera That Target a Wheat Phyllosphere Sphingomonas Genus.

Bacteriophages are viral agents that infect and replicate within bacterial cells. Despite the increasing importance of phage ecology, environmental phages-particularly those targeting phyllosphere-associated bacteria-remain underexplored, and current genomic databases lack high-quality phage genome sequences linked to specific environmentally important bacteria, such as the ubiquitous sphingomonads. Here, we isolated three novel phages from a Danish wastewater treatment facility. Notably, these phages are among the first discovered to target and regulate a Sphingomonas genus within the wheat phyllosphere microbiome. Two of the phages displayed a non-prolate Siphovirus morphotype and demonstrated a narrow host range when tested against additional Sphingomonas strains. Intergenomic studies revealed limited nucleotide sequence similarity within the isolated phage genomes and to publicly available metagenome data of their closest relatives. Particularly intriguing was the limited homology observed between the DNA polymerase encoding genes of the isolated phages and their closest relatives. Based on these findings, we propose three newly identified genera of viruses: Longusvirus carli, Vexovirus birtae, and Molestusvirus kimi, following the latest ICTV binomial nomenclature for virus species. These results contribute to our current understanding of phage genetic diversity in natural environments and hold promising implications for phage applications in phyllosphere microbiome manipulation strategies.

Little directional change in the timing of Arctic spring phenology over the past 25 years.

With the global change in climate, the Arctic has been pinpointed as the region experiencing the fastest rates of change. As a result, Arctic biological responses-such as shifts in phenology-are expected to outpace those at lower latitudes. 15 years ago, a decade-long dataset from Zackenberg in High Arctic Greenland revealed rapid rates of phenological change.1 To explore how the timing of spring phenology has developed since, we revisit the Zackenberg time series on flowering plants, arthropods, and birds. Drawing on the full 25-year period of 1996-2020, we find little directional change in the timing of events despite ongoing climatic change. We attribute this finding to a shift in the temporal patterns of climate conditions, from previous directional change to current high inter-annual variability. Additionally, some taxa appear to have reached the limits of their phenological responses, resulting in a leveling off in their phenological responses in warm years. Our findings demonstrate the importance of long-term monitoring of taxa from across trophic levels within the community, allowing for detecting shifts in sensitivities and responses and thus for updated inference in the light of added information.

Accounting for behaviour in fine-scale habitat selection: A case study highlighting methodological intricacies.

Animal habitat selection-central in both theoretical and applied ecology-may depend on behavioural motivations such as foraging, predator avoidance, and thermoregulation. Step-selection functions (SSFs) enable assessment of fine-scale habitat selection as a function of an animal's movement capacities and spatiotemporal variation in extrinsic conditions. If animal location data can be associated with behaviour, SSFs are an intuitive approach to quantify behaviour-specific habitat selection. Fitting SSFs separately for distinct behavioural states helped to uncover state-specific selection patterns. However, while the definition of the availability domain has been highlighted as the most critical aspect of SSFs, the influence of accounting for behaviour in the use-availability design has not been quantified yet. Using a predator-free population of high-arctic muskoxen Ovibos moschatus as a case study, we aimed to evaluate how (1) defining behaviour-specific availability domains, and/or (2) fitting separate behaviour-specific models impacts (a) model structure, (b) estimated selection coefficients and (c) model predictive performance as opposed to behaviour-unspecific approaches. To do so, we first applied hidden Markov models to infer different behavioural modes (resting, foraging, relocating) from hourly GPS positions (19 individuals, 153-1062 observation days/animal). Using SSFs, we then compared behaviour-specific versus behaviour-unspecific habitat selection in relation to terrain features, vegetation and snow conditions. Our results show that incorporating behaviour into the definition of the availability domain primarily impacts model structure (i.e. variable selection), whereas fitting separate behaviour-specific models mainly influences selection strength. Behaviour-specific availability domains improved predictive performance for foraging and relocating models (i.e. behaviours with medium to large spatial displacement), but decreased performance for resting models. Thus, even for a predator-free population subject to only negligible interspecific competition and human disturbance we found that accounting for behaviour in SSFs impacted model structure, selection coefficients and predictive performance. Our results indicate that for robust inference, both a behaviour-specific availability domain and behaviour-specific model fitting should be explored, especially for populations where strong spatiotemporal selection trade-offs are expected. This is particularly critical if wildlife habitat preferences are estimated to inform management and conservation initiatives.

A novel Queuovirinae lineage of Pseudomonas aeruginosa phages encode dPreQ0 DNA modifications with a single GA motif that provide restriction and CRISPR Cas9 protection in vitro.

Deazaguanine DNA modifications are widespread in phages, particularly in those with pathogenic hosts. Pseudomonas phage iggy substitutes ∼16.5% of its genomic 2'-deoxyguanosine (G) with dPreQ0, and the iggy deazaguanine transglycosylase (DpdA) is unique in having a strict GA target motif, not observed previously. The iggy PreQ0 modification is shown to provide protection against both restriction endonucleases and Cas9 (when present in PAM), thus expanding our understanding of the deazaguanine modification system, its potential, and diversity. Phage iggy represents a new genus of Pseudomonas phages within the Queuovirinae subfamily; which have very little in common with other published phage genomes in terms of nucleotide similarity (<10%) and common proteins (<2%). Interestingly, shared similarity is concentrated in dpdA and preQ0 biosynthesis genes. TEM imaging confirmed a siphovirus morphology with a prolate icosahedral head and a non-contractile flexible tail with one long central tail spike. The observed protective effect of the deazaguanine modification on the iggy DNA may contribute to its broad within-species host range. Phage iggy was isolated on Pseudomonas aeruginosa PAO1, but also infects PDO300, PAK, PA14, as well as 10 of 27 tested environmental isolates and 13 of 20 tested clinical isolates of P. aeruginosa from patients with cystic fibrosis.

Demineralized cortical fibers are associated with a low pseudarthrosis rate in patients undergoing surgery for adult spinal deformity without three-column osteotomy.

Introduction: Following surgical treatment for adult spinal deformity (ASD) there is an increased risk of revision surgery due to mechanical failure or pseudarthrosis. Demineralized cortical fibers (DCF) were introduced at our institution aiming to reduce the risk of pseudarthrosis after ASD surgery. Research question: We wanted to investigate the effect of DCF on postoperative pseudarthrosis compared with allogenic bone graft in ASD surgery without three-column osteotomies (3CO). Materials & Methods: All patients undergoing ASD surgery between January 1, 2010 to June 31, 2020 were included in this interventional study with historical controls. Patients with current or previous 3CO were excluded. Before February 1, 2017, patients undergoing surgery received auto- and allogenic bone graft (non-DCF group) whilst patients after received DCF in addition to autologous bone graft (DCF group). Patients were followed for at least two years. The primary outcome was radiographic or CT-verified postoperative pseudarthrosis requiring revision surgery. Results: We included 50 patients in the DCF group and 85 patients in the non-DCF group for final analysis. Pseudarthrosis requiring revision surgery at two-year follow-up occurred in seven (14%) patients in the DCF group compared with 28 (33%) patients in the non-DCF group (p â€‹= â€‹0.016). The difference was statistically significant, corresponding to a relative risk of 0.43 (95%CI: 0.21-0.94) in favor of the DCF group. Conclusion: We assessed the use of DCF in patients undergoing ASD surgery without 3CO. Our results suggest that the use of DCF was associated with a considerable decreased risk of postoperative pseudarthrosis requiring revision surgery.

Applying Machine Learning to the Visual Inspection of Filled Injectable Drug Products.

With machine learning (ML), we see the potential to better harness the intelligence and decision-making abilities of human inspectors performing manual visual inspection (MVI) and apply this to automated visual inspection (AVI) with the inherent improvements in throughput and consistency. This article is intended to capture current experience with this new technology and provides points to consider for successful application to AVI of injectable drug products. The technology is available today for such AVI applications. Machine vision companies have integrated ML as an additional visual inspection tool with minimal upgrades to existing hardware. Studies have demonstrated superior results in defect detection and reduction in false rejects, when compared with conventional inspection tools. ML implementation does not require modifications to current AVI qualification strategies. The utilization of this technology for AVI will accelerate recipe development by use of faster computers rather than by direct human configuration and coding of vision tools. By freezing the model developed with artificial intelligence tools and subjecting it to current validation strategies, assurance of reliable performance in the production environment can be achieved.