Machine learning-based mortality prediction models using national liver transplantation registries are feasible but have limited utility across countries.

Many countries curate national registries of liver transplant (LT) data. These registries are often used to generate predictive models; however, potential performance and transferability of these models remain unclear. We used data from 3 national registries and developed machine learning algorithm (MLA)-based models to predict 90-day post-LT mortality within and across countries. Predictive performance and external validity of each model were assessed. Prospectively collected data of adult patients (aged ≥18 years) who underwent primary LTs between January 2008 and December 2018 from the Canadian Organ Replacement Registry (Canada), National Health Service Blood and Transplantation (United Kingdom), and United Network for Organ Sharing (United States) were used to develop MLA models to predict 90-day post-LT mortality. Models were developed using each registry individually (based on variables inherent to the individual databases) and using all 3 registries combined (variables in common between the registries [harmonized]). The model performance was evaluated using area under the receiver operating characteristic (AUROC) curve. The number of patients included was as follows: Canada, n = 1214; the United Kingdom, n = 5287; and the United States, n = 59,558. The best performing MLA-based model was ridge regression across both individual registries and harmonized data sets. Model performance diminished from individualized to the harmonized registries, especially in Canada (individualized ridge: AUROC, 0.74; range, 0.73-0.74; harmonized: AUROC, 0.68; range, 0.50-0.73) and US (individualized ridge: AUROC, 0.71; range, 0.70-0.71; harmonized: AUROC, 0.66; range, 0.66-0.66) data sets. External model performance across countries was poor overall. MLA-based models yield a fair discriminatory potential when used within individual databases. However, the external validity of these models is poor when applied across countries. Standardization of registry-based variables could facilitate the added value of MLA-based models in informing decision making in future LTs.

Using a machine learning algorithm to predict outcome of primary cytoreductive surgery in advanced ovarian cancer.

OBJECTIVE: To develop a machine learning (ML) algorithm to predict outcome of primary cytoreductive surgery (PCS) in patients with advanced ovarian cancer (AOC) METHODS: This retrospective cohort study included patients with AOC undergoing PCS between January 2017 and February 2021. Using radiologic criteria, patient factors (age, CA-125, performance status, BRCA) and surgical complexity scores, we trained a random forest model to predict the dichotomous outcome of optimal cytoreduction (<1 cm) and no gross residual (RD = 0 mm) using JMP-Pro 15 (SAS). This model is available at https://ipm-ml.ccm.sickkids.ca. RESULTS: One hundred and fifty-one patients underwent PCS and randomly assigned to train (n = 92), validate (n = 30), or test (n = 29) the model. The median age was 58 (27-83). Patients with suboptimal cytoreduction were more likely to have an Eastern Cooperative Oncology Group 3-4 (11% vs. 0.75%, p = 0.004), lower albumin (38 vs. 41, p = 0.02), and higher CA125 (1126 vs. 388, p = 0.012) than patients with optimal cytoreduction (n = 133). There were no significant differences in age, histology, stage, or BRCA status between groups. The bootstrap random forest model had AUCs of 99.8% (training), 89.6%(validation), and 89.0% (test). The top five contributors were CA125, albumin, diaphragmatic disease, age, and ascites. For RD = 0 mm, the AUCs were 94.4%, 52%, and 84%, respectively. CONCLUSION: Our ML algorithm demonstrated high accuracy in predicting optimal cytoreduction in patients with AOC selected for PCS and may assist decision-making.

Genomics4RD: An integrated platform to share Canadian deep-phenotype and multiomic data for international rare disease gene discovery.

Despite recent progress in the understanding of the genetic etiologies of rare diseases (RDs), a significant number remain intractable to diagnostic and discovery efforts. Broad data collection and sharing of information among RD researchers is therefore critical. In 2018, the Care4Rare Canada Consortium launched the project C4R-SOLVE, a subaim of which was to collect, harmonize, and share both retrospective and prospective Canadian clinical and multiomic data. Here, we introduce Genomics4RD, an integrated web-accessible platform to share Canadian phenotypic and multiomic data between researchers, both within Canada and internationally, for the purpose of discovering the mechanisms that cause RDs. Genomics4RD has been designed to standardize data collection and processing, and to help users systematically collect, prioritize, and visualize participant information. Data storage, authorization, and access procedures have been developed in collaboration with policy experts and stakeholders to ensure the trusted and secure access of data by external researchers. The breadth and standardization of data offered by Genomics4RD allows researchers to compare candidate disease genes and variants between participants (i.e., matchmaking) for discovery purposes, while facilitating the development of computational approaches for multiomic data analyses and enabling clinical translation efforts for new genetic technologies in the future.

Genetics, not environment, contributed to winter wheat yield gains in Ontario, Canada.

KEY MESSAGE: Changes in entries' market classes and genetic improvements within classes-not environmental changes-enhanced yields over thirty-one years of wheat trials. Correlations between yields and ancestries drove genomic prediction accuracies. Increasing crop yields is important for enhancing farmers' livelihoods, meeting market demands, and reducing the environmental impact of agriculture. We analyzed the yield trends of Ontario winter wheat variety trials between 1988 and 2018. Over this period, wheat yields steadily increased by 38 kg ha-1 yr-1, or 0.68% yr-1 relative to the mean. While fungicide treatment of trials contributed a one-time 670 kg ha-1 yield increase, yields were otherwise unaffected by long-term changes in agronomic practice, climate, or other non-genetic factors. Genetic improvement entirely accounted for yield improvement. Market class changes over the 31 year span accounted for some yield improvement. More importantly, genetic improvement occurred within each market class. Entry yield estimates calculated from genomic prediction models strongly correlated with field estimated yields with a mean r of 0.68. Genomic prediction accuracies were high because yields differed across genetically distinct subpopulations. Despite environmental changes, genetic improvement will likely increase Ontario winter wheat yields into the future.

Basophil activation test shows high accuracy in the diagnosis of peanut and tree nut allergy: The Markers of Nut Allergy Study.

BACKGROUND: Peanut and tree nut allergies are the most important causes of anaphylaxis. Co-reactivity to more than one nut is frequent, and co-sensitization in the absence of clinical data is often obtained. Confirmatory oral food challenges (OFCs) are inconsistently performed. OBJECTIVE: To investigate the utility of the basophil activation test (BAT) in diagnosing peanut and tree nut allergies. METHODS: The Markers Of Nut Allergy Study (MONAS) prospectively enrolled patients aged 0.5-17 years with confirmed peanut and/or tree nut (almond, cashew, hazelnut, pistachio, walnut) allergy or sensitization from Canadian (n = 150) and Austrian (n = 50) tertiary pediatric centers. BAT using %CD63+ basophils (SSClow/CCR3pos) as outcome was performed with whole blood samples stimulated with allergen extracts of each nut (0.001-1000 ng/mL protein). BAT results were assessed against confirmed allergic status in a blinded fashion to develop a generalizable statistical model for comparison to extract and marker allergen-specific IgE. RESULTS: A mixed effect model integrating BAT results for 10 and 100 ng/mL of peanut and individual tree nut extracts was optimal. The area under the ROC curve (AUROC) was 0.98 for peanut, 0.97 for cashew, 0.92 for hazelnut, 0.95 for pistachio, and 0.97 for walnut. The BAT outperformed sIgE testing for peanut or hazelnut and was comparable for walnut (AUROC 0.95, 0.94, 0.92) in a sub-analysis in sensitized patients undergoing OFC. CONCLUSIONS: Basophil activation test can predict allergic clinical status to peanut and tree nuts in multi-nut-sensitized children and may reduce the need for high-risk OFCs in patients.

Dissemination of Anesthesia Information During the Coronavirus Disease 2019 Pandemic Through Twitter: An Infodemiology Study.

BACKGROUND: Twitter is a web-based social media platform that allows instantaneous sharing of user-generated messages (tweets). We performed an infodemiology study of the coronavirus disease 2019 (COVID-19) Twitter conversation related to anesthesiology to describe how Twitter has been used during the pandemic and ways to optimize Twitter use by anesthesiologists. METHODS: This was a cross-sectional study of tweets related to the specialty of anesthesiology and COVID-19 tweeted between January 21 and October 13, 2020. A publicly available COVID-19 Twitter dataset was filtered for tweets meeting inclusion criteria (tweets including anesthesiology keywords). Using descriptive statistics, tweets were reviewed for tweet and account characteristics. Tweets were filtered for specific topics of interest likely to be impactful or informative to anesthesiologists of COVID-19 practice (airway management, personal protective equipment, ventilators, COVID testing, and pain management). Tweet activity was also summarized descriptively to show temporal profiles over the pandemic. RESULTS: Between January 21 and October 13, 2020, 23,270 of 241,732,881 tweets (0.01%) met inclusion criteria and were generated by 15,770 accounts. The majority (51.9%) of accounts were from the United States. Seven hundred forty-nine (4.8%) of all users self-reported as anesthesiologists. 33.8% of all tweets included at least one word or phrase preceded by the # symbol (hashtag), which functions as a label to search for all tweets including a specific hashtag, with the most frequently used being #anesthesia. About half (52.2%) of all tweets included at least one hyperlink, most frequently linked to other social media, news organizations, medical organizations, or scientific publications. The majority of tweets (67%) were not retweeted. COVID-19 anesthesia tweet activity started before the pandemic was declared. The trend of daily tweet activity was similar to, and preceded, the US daily death count by about 2 weeks. CONCLUSIONS: The toll of the pandemic has been reflected in the anesthesiology conversation on Twitter, representing 0.01% of all COVID-19 tweets. Daily tweet activity showed how the Twitter community used the platform to learn about important topics impacting anesthesiology practice during a global pandemic. Twitter is a relevant platform through which to communicate about anesthesiology topics, but further research is required to delineate its effectiveness, benefits, and limitations for anesthesiology discussions.

MRI based radiomics enhances prediction of neurodevelopmental outcome in very preterm neonates.

To predict adverse neurodevelopmental outcome of very preterm neonates. A total of 166 preterm neonates born between 24-32 weeks' gestation underwent brain MRI early in life. Radiomics features were extracted from T1- and T2- weighted images. Motor, cognitive, and language outcomes were assessed at a corrected age of 18 and 33 months and 4.5 years. Elastic Net was implemented to select the clinical and radiomic features that best predicted outcome. The area under the receiver operating characteristic (AUROC) curve was used to determine the predictive ability of each feature set. Clinical variables predicted cognitive outcome at 18 months with AUROC 0.76 and motor outcome at 4.5 years with AUROC 0.78. T1-radiomics features showed better prediction than T2-radiomics on the total motor outcome at 18 months and gross motor outcome at 33 months (AUROC: 0.81 vs 0.66 and 0.77 vs 0.7). T2-radiomics features were superior in two 4.5-year motor outcomes (AUROC: 0.78 vs 0.64 and 0.8 vs 0.57). Combining clinical parameters and radiomics features improved model performance in motor outcome at 4.5 years (AUROC: 0.84 vs 0.8). Radiomic features outperformed clinical variables for the prediction of adverse motor outcomes. Adding clinical variables to the radiomics model enhanced predictive performance.