Purpose of review Immunocompromised patients are at high risk for infection. During the coronavirus disease (COVID-19) pandemic, immunocompromised patients exhibited increased odds of intensive care unit admission and death. Early pathogen identification is essential to mitigating infection related risk in immunocompromised patients. Artificial intelligence (AI) and machine learning (ML) have tremendous appeal to address unmet diagnostic needs. These AI/ML tools often rely on the wealth of data found in healthcare to enhance our ability to identify clinically significant patterns of disease. To this end, our review provides an overview of the current AI/ML landscape as it applies to infectious disease testing with emphasis on immunocompromised patients. Recent findings Examples include AI/ML for predicting sepsis in high risk burn patients. Likewise, ML is utilized to analyze complex host-response proteomic data to predict respiratory infections including COVID-19. These same approaches have also been applied for pathogen identification of bacteria, viruses, and hard to detect fungal microbes. Future uses of AI/ML may include integration of predictive analytics in point-of-care (POC) testing and data fusion applications. Summary Immunocompromised patients are at high risk for infections. AI/ML is transforming infectious disease testing and has great potential to address challenges encountered in the immune compromised population.

Background Blood transfusions are performed frequently in goats, but crossmatches are rarely performed. Hypothesis/Objectives Determine differences in the frequency of agglutination and hemolytic crossmatch reactions between large and small breed goats. Animals Healthy adult goats, 10 large and 10 small breed. Methods Two hundred eighty major and minor agglutination and hemolytic crossmatches: 90 large breed donor to large breed recipient (L‐L), 90 small breed donor to small breed recipient (S‐S), 100 large breed donor to small breed recipient (L‐S). A linear mixed model with treatment group (L‐L, S‐S, L‐S) as a fixed effect and individual crossmatch as a random effect was used to identify variations in reaction frequency among groups and individuals. Results Frequency of major agglutination reactions for L‐L, S‐S, and L‐S were 3/90 (3.3%), 7/90 (7.8%), and 10/100 (10.0%), respectively. Frequency of major hemolytic reactions for L‐L, S‐S, and L‐S were 27/84 (32.1%), 7/72 (9.7%), and 31/71 (43.7%). Individual pairings and groupings had no effect on agglutination reactions. Individual pairings had no effect on the frequency of hemolytic reactions. For major hemolytic crossmatches, pairwise comparisons identified higher frequencies of reactions when comparing L‐L to S‐S (P = .007) and L‐S to S‐S (P < .001). Conclusion and Clinical Importance Goats experience increased frequencies of hemolytic reactions compared to agglutination. Significant increases in hemolysis were seen between large breed donors and small breed recipients, compared to small breed pairings. Additional studies are required to determine correlations between crossmatches and transfusion reactions.

Background Urolithiasis in small ruminants has a poor long‐term prognosis, and long‐term clinical outcomes are variable and unpredictable. Objectives To assess the accuracy of preoperative and postoperative blood l‐lactate concentrations in predicting a negative outcome in goats undergoing tube cystostomy. Animals Thirty‐four male goats undergoing tube cystostomy. Methods Retrospective study. Medical records of goats undergoing tube cystostomy from 2015 to 2020 were reviewed. Clinical variables recorded included signalment, procedures before surgery, urolith location and type, duration of hospitalization, and heart rate. PCV, plasma total protein, potassium, preoperative and postoperative blood l‐lactate concentrations, preoperative and postoperative creatinine concentrations, and relative changes in blood l‐lactate and creatinine concentrations over time were measured using heparinized blood. A negative outcome was defined as death or euthanasia from urolithiasis complications at 6 months after discharge. Negative outcomes as a function of independent clinical variables were evaluated using χ2 or Fisher's exact tests, and multivariate logistic regression. P < .05 was considered significant. Results Median (95% confidence interval) preoperative, postoperative, and the relative change over time of blood l‐lactate concentrations were 3.3 mmol/L (2.2, 4.8), 1.0 mmol/L (0.7, 1.3), and 0.4 mmol/L (−3.5, 3.2), respectively. Preoperative (P = 1), postoperative (P = .14), and the relative change over time (P = .63) of blood l‐lactate concentrations were not significant predictors of a negative outcome. Furthermore, all other clinical variables measured were not significant predictors of a negative outcome (P > .05). Conclusions and Clinical Importance Veterinarians should advise clients that clinical outcomes after tube cystostomy in goats are likely unpredictable.