Machine learning algorithm as a diagnostic tool for hypoadrenocorticism in dogs

Diagnosis and classification of portosystemic shunts: a machine learning retrospective case-control study

Diagnosis of portosystemic shunts (PSS) in dogs often requires multiple diagnostic tests, and available clinicopathologic tests have limitations in sensitivity and specificity. The objective of this study was to train and validate a machine learning model (MLM) that can accurately predict the presence of a PSS utilizing routinely collected demographic data and clinicopathologic features. Dogs diagnosed with PSS or control dogs tested for PSS but had the condition ruled out (non-PSS) were identified. Dogs were included if a complete blood count and serum chemistry panel were available from PSS diagnostic testing. Dogs with a PSS were subcategorized as having a single intrahepatic PSS, a single extrahepatic PSS, or multiple extrahepatic PSS. An extreme gradient boosting (XGboost) MLM was trained with data from 70% of the cases, and MLM performance was determined on the test set, comprising the remaining 30% of the case data. Two MLMs were created. The first was designed to predict the presence of any PSS (PSS MLM), and the second to predict the PSS subcategory (PSS SubCat MLM). The trained PSS MLM had a sensitivity of 94.3% (95% CI 90.1-96.8%) and specificity of 90.5% (95% CI 85.32-94.0%) for dogs in the test set. The area under the receiver operator characteristic curve (AUC) was 0.976 (95% CI; 0.964-0.989). The mean corpuscular hemoglobin, lymphocyte count, and serum globulin concentration were most important in prediction classification. The PSS SubCat MLM had an accuracy of 85.7% in determining the subtype of PSS of dogs in the test set, with variable sensitivity and specificity depending on PSS subtype. These MLMs have a high accuracy for diagnosing PSS; however, the prediction of PSS subclassification is less accurate. The MLMs can be used as a screening tool to increase or decrease the index of suspicion for PSS before confirmatory diagnostics such as advanced imaging are pursued.

Evaluation of a Novel Veterinary Dental Radiography Artificial Intelligence Software Program

There is a growing trend of artificial intelligence (AI) applications in veterinary medicine, with the potential to assist veterinarians in clinical decisions. A commercially available, AI-based software program (AISP) for detecting common radiographic dental pathologies in dogs and cats was assessed for agreement with two human evaluators. Furcation bone loss, periapical lucency, resorptive lesion, retained tooth root, attachment (alveolar bone) loss and tooth fracture were assessed. The AISP does not attempt to diagnose or provide treatment recommendations, nor has it been trained to identify other types of radiographic pathology. Inter-rater reliability for detecting pathologies was measured by absolute percent agreement and Gwet's agreement coefficient. There was good to excellent inter-rater reliability among all raters, suggesting the AISP performs similarly at detecting the specified pathologies compared to human evaluators. Sensitivity and specificity for the AISP were assessed using human evaluators as the reference standard. The results revealed a trend of low sensitivity and high specificity, suggesting the AISP may produce a high rate of false negatives and may not be a good tool for initial screening. However, the low rate of false positives produced by the AISP suggests it may be beneficial as a "second set of eyes" because if it detects the specific pathology, there is a high likelihood that the pathology is present. With an understanding of the AISP, as an aid and not a substitute for veterinarians, the technology may increase dental radiography utilization and diagnostic potential.

The potential application of artificial intelligence in veterinary clinical practice and biomedical research

Artificial intelligence (AI) is a fast-paced technological advancement in terms of its application to various fields of science and technology. In particular, AI has the potential to play various roles in veterinary clinical practice, enhancing the way veterinary care is delivered, improving outcomes for animals and ultimately humans. Also, in recent years, the emergence of AI has led to a new direction in biomedical research, especially in translational research with great potential, promising to revolutionize science. AI is applicable in antimicrobial resistance (AMR) research, cancer research, drug design and vaccine development, epidemiology, disease surveillance, and genomics. Here, we highlighted and discussed the potential impact of various aspects of AI in veterinary clinical practice and biomedical research, proposing this technology as a key tool for addressing pressing global health challenges across various domains.

Development and internal validation of diagnostic prediction models using machine-learning algorithms in dogs with hypothyroidism

Introduction

Hypothyroidism can be easily misdiagnosed in dogs, and prediction models can support clinical decision-making, avoiding unnecessary testing and treatment. The aim of this study is to develop and internally validate diagnostic prediction models for hypothyroidism in dogs by applying machine-learning algorithms.

Methods

A single-institutional cross-sectional study was designed searching the electronic database of a Veterinary Teaching Hospital for dogs tested for hypothyroidism. Hypothyroidism was diagnosed based on suggestive clinical signs and thyroid function tests. Dogs were excluded if medical records were incomplete or a definitive diagnosis was lacking. Predictors identified after data processing were dermatological signs, alopecia, lethargy, hematocrit, serum concentrations of cholesterol, creatinine, total thyroxine (tT4), and thyrotropin (cTSH). Four models were created by combining clinical signs and clinicopathological variables expressed as quantitative (models 1 and 2) and qualitative variables (models 3 and 4). Models 2 and 4 included tT4 and cTSH, models 1 and 3 did not. Six different algorithms were applied to each model. Internal validation was performed using a 10-fold cross-validation. Apparent performance was evaluated by calculating the area under the receiver operating characteristic curve (AUROC).

Results

Eighty-two hypothyroid and 233 euthyroid client-owned dogs were included. The best performing algorithms were naive Bayes in model 1 (AUROC = 0.85; 95% confidence interval [CI] = 0.83-0.86) and in model 2 (AUROC = 0.98; 95% CI = 0.97-0.99), logistic regression in model 3 (AUROC = 0.88; 95% CI = 0.86-0.89), and random forest in model 4 (AUROC = 0.99; 95% CI = 0.98-0.99). Positive predictive value was 0.76, 0.84, 0.93, and 0.97 in model 1, 2, 3, and 4, respectively. Negative predictive value was 0.89, 0.89, 0.99, and 0.99 in model 1, 2, 3, and 4, respectively.

Discussion

Machine learning-based prediction models were accurate in predicting and quantifying the likelihood of hypothyroidism in dogs based on internal validation performed in a single-institution, but external validation is required to support the clinical applicability of these models.

Evaluation of a machine learning tool to screen for hypoadrenocorticism in dogs presenting to a teaching hospital

BACKGROUND

Dogs with hypoadrenocorticism (HA) have clinical signs and clinicopathologic abnormalities that can be mistaken as other diseases. In dogs with a differential diagnosis of HA, a machine learning model (MLM) has been validated to discriminate between HA and other diseases. This MLM has not been evaluated as a screening tool for a broader group of dogs.

HYPOTHESIS

An MLM can accurately screen dogs for HA.

ANIMALS

Dogs (n = 1025) examined at a veterinary hospital.

METHODS

Dogs that presented to a tertiary referral hospital that had a CBC and serum chemistry panel were enrolled. A trained MLM was applied to clinicopathologic data and in dogs that were MLM positive for HA, diagnosis was confirmed by measurement of serum cortisol.

RESULTS

Twelve dogs were MLM positive for HA and had further cortisol testing. Five had HA confirmed (true positive), 4 of which were treated for mineralocorticoid and glucocorticoid deficiency, and 1 was treated for glucocorticoid deficiency alone. Three MLM positive dogs had baseline cortisol ≤2 μg/dL but were euthanized or administered glucocorticoid treatment without confirming the diagnosis with an ACTH-stimulation test (classified as "undetermined"), and in 4, HA was ruled out (false positives). The positive likelihood ratio of the MLM was 145 to 254. All dogs diagnosed with HA by attending clinicians tested positive by the MLM.

CONCLUSIONS AND CLINICAL IMPORTANCE

This MLM can robustly predict HA status when indiscriminately screening all dogs with blood work. In this group of dogs with a low prevalence of HA, the false positive rates were clinically acceptable.

Diagnosis of canine spontaneous hypoadrenocorticism

Hypoadrenocorticism is characterized by a reduction in mineralocorticoid and/or glucocorticoid production by the adrenal glands. Several subtypes have been described with different clinical and clinicopathological consequences. Most affected dogs have vague and non-specific signs that precede an eventual life-threatening crisis. This review aims to appraise classification, the available data on epidemiology and the clinical and laboratory features of naturally occurring canine hypoadrenocorticism.

Canine hypoadrenocorticism is a relatively uncommon endocrine disease that can present with a wide variety of clinical signs resulting from cortisol or aldosterone deficiency or both. Hypoadrenocorticism should be considered in all dogs with severe illness and typical electrolyte abnormalities but also in those with waxing and waning clinical signs. Multiple clinical and laboratory features are suggestive of the disease and should prompt evaluation of adrenal function. The ACTH stimulation test is the best test for diagnosing hypoadrenocorticism but, in those cases without the typical presentation, evaluation of aldosterone secretory capacity and endogenous ACTH concentrations should be performed to distinguish primary from secondary disease. In this review we discuss the pathophysiology of the disease, the clinical signs and laboratory features that should raise suspicion of hypoadrenocorticism and the performance of the different diagnostic tests.

Diagnostic Classification of Cases of Canine Leishmaniasis Using Machine Learning

Proposal techniques that reduce financial costs in the diagnosis and treatment of animal diseases are welcome. This work uses some machine learning techniques to classify whether or not cases of canine visceral leishmaniasis are present by physical examinations. For validation of the method, four machine learning models were chosen: K-nearest neighbor, Naïve Bayes, support vector machine and logistic regression models. The tests were performed on three hundred and forty dogs, using eighteen characteristics of the animal and the ELISA (enzyme-linked immunosorbent assay) serological test as validation. Logistic regression achieved the best metrics: Accuracy of 75%, sensitivity of 84%, specificity of 67%, a positive likelihood ratio of 2.53 and a negative likelihood ratio of 0.23, showing a positive relationship in the evaluation between the true positives and rejecting the cases of false negatives.

Investigation of the urine cortisol to creatinine ratio for the diagnosis of hypoadrenocorticism in dogs

OBJECTIVE

To evaluate the urine cortisol-to-creatinine ratio (UCCR) for the diagnosis of hypoadrenocorticism (HA) in dogs and to determine whether the method of urine cortisol measurement affects results.

ANIMALS

41 dogs with naturally occurring HA and 107 dogs with nonadrenal illness.

PROCEDURES

Urine samples were prospectively collected from dogs undergoing testing for HA. Urine cortisol concentrations were measured at a veterinary diagnostic laboratory using either a radioimmunoassay (RIA) or a chemiluminescent immunoassay (CLIA). Receiver operating characteristic (ROC) curves were constructed to assess UCCR performance by both methods for HA diagnosis. Sensitivities, specificities, accuracies, and predictive values were calculated for various cutpoints.

RESULTS

The areas under the ROC curves for UCCR diagnosis of HA were 0.99 (95% CI, 0.98 to 1.00) and 1.00 (95% CI, 1.00 to 1.00) when urine cortisol was determined by RIA and CLIA, respectively. An RIA UCCR of ≤ 2 was 97.2% sensitive, 93.6% specific, and 94.7% accurate for HA diagnosis, whereas a CLIA UCCR of ≤ 10 was 100% sensitive, specific, and accurate. An RIA UCCR > 4 and a CLIA UCCR of > 10 had negative predictive values of 100%.

CLINICAL RELEVANCE

The UCCR was an accurate diagnostic test for HA in this study population, although equivocal results are possible. Case characteristics, method of cortisol measurement, and laboratory-specific cutpoints must be considered when interpreting results.

Metabolomic Abnormalities in Serum from Untreated and Treated Dogs with Hyper- and Hypoadrenocorticism

The adrenal glands play a major role in metabolic processes, and both excess and insufficient serum cortisol concentrations can lead to serious metabolic consequences. Hyper- and hypoadrenocorticism represent a diagnostic and therapeutic challenge. Serum samples from dogs with untreated hyperadrenocorticism (n = 27), hyperadrenocorticism undergoing treatment (n = 28), as well as with untreated (n = 35) and treated hypoadrenocorticism (n = 23) were analyzed and compared to apparently healthy dogs (n = 40). A validated targeted proton nuclear magnetic resonance (¹H NMR) platform was used to quantify 123 parameters. Principal component analysis separated the untreated endocrinopathies. The serum samples of dogs with untreated endocrinopathies showed various metabolic abnormalities with often contrasting results particularly in serum concentrations of fatty acids, and high- and low-density lipoproteins and their constituents, which were predominantly increased in hyperadrenocorticism and decreased in hypoadrenocorticism, while amino acid concentrations changed in various directions. Many observed serum metabolic abnormalities tended to normalize with medical treatment, but normalization was incomplete when compared to levels in apparently healthy dogs. Application of machine learning models based on the metabolomics data showed good classification, with misclassifications primarily observed in treated groups. Characterization of metabolic changes enhances our understanding of these endocrinopathies. Further assessment of the recognized incomplete reversal of metabolic alterations during medical treatment may improve disease management.

Identification of parameters and formulation of a statistical and machine learning model to identify Babesia canis infections in dogs using available ADVIA hematology analyzer data

BACKGROUND

Canine babesiosis is an important tick-borne disease in endemic regions. One of the relevant subspecies in Europe is Babesia canis, and it can cause severe clinical signs such as hemolytic anemia. Apart from acute clinical symptoms dogs can also have a more chronic disease development or be asymptomatic carriers. Our objective was to identify readily available ADVIA hematology analyzer parameters suggestive of B. canis parasitemia in dogs and to formulate a predictive model.

METHODS

A historical dataset of complete blood count data from an ADVIA hematology system with blood smear or PCR confirmed parasitemia cases was used to obtain a model by conventional statistics (CS) methods and machine learning (ML) using logistical regression and tree methods.

RESULTS

Both methods identified that important parameters were platelet count, mean platelet volume and percentage large unstained cells. We were able to formulate a CS model and ML model to screen for Babesia parasitemia in dogs with a sensitivity of 84.6% (CS) and 100% (ML), a specificity of 97.7% (CS) and 95.7% (ML) and a positive likelihood ratio (LR+) of 36.78 (CS) and 23.2 (ML).

CONCLUSIONS

This study introduces two methods of screening for B. canis parasitemia on readily available data from ADVIA hematology systems. The algorithms can easily be introduced in laboratories that use these analyzers. When the algorithm marks a sample as 'suggestive' for Babesia parasitemia, the sample is approximately 37 times more likely to show Babesia merozoites on blood smear analysis.

Day-1 Competencies for Veterinarians Specific to Health Informatics

In 2015, the American Association of Veterinary Medical Colleges (AAVMC) developed the Competency-Based Veterinary Education (CBVE) framework to prepare practice-ready veterinarians through competency-based education, which is an outcomes-based approach to equipping students with the skills, knowledge, attitudes, values, and abilities to do their jobs. With increasing use of health informatics (HI: the use of information technology to deliver healthcare) by veterinarians, competencies in HI need to be developed. To reach consensus on a HI competency framework in this study, the Competency Framework Development (CFD) process was conducted using an online adaptation of Developing-A-Curriculum, an established methodology in veterinary medicine for reaching consensus among experts. The objectives of this study were to (1) create an HI competency framework for new veterinarians; (2) group the competency statements into common themes; (3) map the HI competency statements to the AAVMC competencies as illustrative sub-competencies; (4) provide insight into specific technologies that are currently relevant to new veterinary graduates; and (5) measure panelist satisfaction with the CFD process. The primary emphasis of the final HI competency framework was that veterinarians must be able to assess, select, and implement technology to optimize the client-patient experience, delivery of healthcare, and work-life balance for the veterinary team. Veterinarians must also continue their own education regarding technology by engaging relevant experts and opinion leaders.

Machine-learning based prediction of Cushing's syndrome in dogs attending UK primary-care veterinary practice

Cushing’s syndrome is an endocrine disease in dogs that negatively impacts upon the quality-of-life of affected animals. Cushing’s syndrome can be a challenging diagnosis to confirm, therefore new methods to aid diagnosis are warranted. Four machine-learning algorithms were applied to predict a future diagnosis of Cushing's syndrome, using structured clinical data from the VetCompass programme in the UK. Dogs suspected of having Cushing's syndrome were included in the analysis and classified based on their final reported diagnosis within their clinical records. Demographic and clinical features available at the point of first suspicion by the attending veterinarian were included within the models. The machine-learning methods were able to classify the recorded Cushing’s syndrome diagnoses, with good predictive performance. The LASSO penalised regression model indicated the best overall performance when applied to the test set with an AUROC = 0.85 (95% CI 0.80–0.89), sensitivity = 0.71, specificity = 0.82, PPV = 0.75 and NPV = 0.78. The findings of our study indicate that machine-learning methods could predict the future diagnosis of a practicing veterinarian. New approaches using these methods could support clinical decision-making and contribute to improved diagnosis of Cushing’s syndrome in dogs.

Hypoadrenocorticism in dogs under UK primary veterinary care: frequency, clinical approaches and risk factors

Objectives

To estimate the frequency, clinical approaches and risk factors of hypoadrenocorticism in dogs under UK primary veterinary care.

Materials and Methods

Dogs diagnosed with hypoadrenocorticism were identified from the UK VetCompass™ programme by searching anonymised electronic patient records. Pre‐existing and newly diagnosed cases of disease during 2016 were included. Cases were further sub‐categorised as having a laboratory‐confirmed or presumed diagnosis of hypoadrenocorticism based on the information recorded in the electronic patient records. Descriptive data were manually extracted. Multivariable logistic regression methods were used to identify demographic risk factors.

Results

There were 177 hypoadrenocorticism cases identified from 905,543 dogs in 2016; 72 laboratory‐confirmed and 105 presumed. The 1‐year period prevalence for hypoadrenocorticism in all dogs was 0.06% (95% confidence interval: 0.05‐0.07%). The most common presenting clinical signs in laboratory‐confirmed dogs were lethargy (51/66, 77.3%), anorexia (48/66, 66.7%) and vomiting (48/66, 66.7%). Hyperkalaemia was reported in 47 of 53 (88.7%), hyponatraemia in 46 of 53 (86.8%). Median sodium: potassium ratio was 19.00 (interquartile range: 16.20‐20.60). Breed, age, neuter status and insurance status were associated with a laboratory‐confirmed diagnosis of hypoadrenocorticism. No sex association with hypoadrenocorticism was observed in the multivariable model. The standard poodle had 51.38 times the odds (95% CI: 14.49‐182.18) of hypoadrenocorticism compared with crossbreeds. The labradoodle and West Highland white terrier also had increased odds.

Clinical Significance

This is the first epidemiological study to report on hypoadrenocorticism in dogs within the UK primary‐care population. These results provide benchmark data of current veterinary activity relating to hypoadrenocorticism in primary‐care practices.

Severity Detection for the Coronavirus Disease 2019 (COVID-19) Patients Using a Machine Learning Model Based on the Blood and Urine Tests

The recent outbreak of the coronavirus disease-2019 (COVID-19) caused serious challenges to the human society in China and across the world. COVID-19 induced pneumonia in human hosts and carried a highly inter-person contagiousness. The COVID-19 patients may carry severe symptoms, and some of them may even die of major organ failures. This study utilized the machine learning algorithms to build the COVID-19 severeness detection model. Support vector machine (SVM) demonstrated a promising detection accuracy after 32 features were detected to be significantly associated with the COVID-19 severeness. These 32 features were further screened for inter-feature redundancies. The final SVM model was trained using 28 features and achieved the overall accuracy 0.8148. This work may facilitate the risk estimation of whether the COVID-19 patients would develop the severe symptoms. The 28 COVID-19 severeness associated biomarkers may also be investigated for their underlining mechanisms how they were involved in the COVID-19 infections.

Severity Detection for the Coronavirus Disease 2019 (COVID-19) Patients Using a Machine Learning Model Based on the Blood and Urine Tests

The recent outbreak of the coronavirus disease-2019 (COVID-19) caused serious challenges to the human society in China and across the world. COVID-19 induced pneumonia in human hosts and carried a highly inter-person contagiousness. The COVID-19 patients may carry severe symptoms, and some of them may even die of major organ failures. This study utilized the machine learning algorithms to build the COVID-19 severeness detection model. Support vector machine (SVM) demonstrated a promising detection accuracy after 32 features were detected to be significantly associated with the COVID-19 severeness. These 32 features were further screened for inter-feature redundancies. The final SVM model was trained using 28 features and achieved the overall accuracy 0.8148. This work may facilitate the risk estimation of whether the COVID-19 patients would develop the severe symptoms. The 28 COVID-19 severeness associated biomarkers may also be investigated for their underlining mechanisms how they were involved in the COVID-19 infections.