Applications of Artificial Intelligence in Urinalysis: Is the Future Already Here?

An artificial intelligence-driven support tool for prediction of urine culture test results

BACKGROUND AND AIMS

We aimed to develop an easily deployable artificial intelligence (AI)-driven model for rapid prediction of urine culture test results.

MATERIAL AND METHODS

We utilized a training dataset (n = 34,584 urine samples) and two separate, unseen test sets (n = 10,083 and 9,289 samples). Various machine learning models were compared for diagnostic performance. Predictive parameters included urinalysis results (dipstick and flow cytometry), patient demographics (age and gender), and sample collection method.

RESULTS

Although more complex models achieved the highest AUCs for predicting positive cultures (highest: multilayer perceptron (MLP) with AUC of 0.884, 95% CI 0.878-0.89), multiple logistic regression (MLR) using only flow cytometry parameters achieved a very good AUC (0.858, 95% CI 0.852-0.865). To aid interpretation, prediction results of the MLP and MLR models were categorized based on likelihood ratio (LR) for positivity: highly unlikely (LR 0.1), unlikely (LR 0.3), grey zone (LR 0.9), likely (LR 5.0), and highly likely (LR 40). This resulted in 17%, 28%, 34%, 9%, and 13% of samples falling into each respective category for the MLR model and 20%, 26%, 31%, 7%, and 16% for the MLP model.

CONCLUSIONS

In conclusion, this robust model has the potential to assist clinicians in their decision-making process by providing insights prior to the availability of urine culture results in a significant portion of samples (∼2/3rd).

Artificial intelligence in the clinical laboratory

Laboratory medicine has become a highly automated medical discipline. Nowadays, artificial intelligence (AI) applied to laboratory medicine is also gaining more and more attention, which can optimize the entire laboratory workflow and even revolutionize laboratory medicine in the future. However, only a few commercially available AI models are currently approved for use in clinical laboratories and have drawbacks such as high cost, lack of accuracy, and the need for manual review of model results. Furthermore, there are a limited number of literature reviews that comprehensively address the research status, challenges, and future opportunities of AI applications in laboratory medicine. Our article begins with a brief introduction to AI and some of its subsets, then reviews some AI models that are currently being used in clinical laboratories or that have been described in emerging studies, and explains the existing challenges associated with their application and possible solutions, finally provides insights into the future opportunities of the field. We highlight the current status of implementation and potential applications of AI models in different stages of the clinical testing process.

Unveiling drug induced nephrotoxicity using novel biomarkers and cutting-edge preventive strategies

Drug-induced nephrotoxicity is still a significant obstacle in pharmacotherapy of various diseases and it accounts for around 25 % of serious side-effects reported after drug administration. Furthermore, some groups of drugs such as nonsteroidal anti-inflammatory drugs, antibiotics, antiviral drugs, antifungal drugs, immunosuppressants, and chemotherapeutic drugs have the "preference" for damaging the kidney and are often referred to as the kidney's "silent killer". Clinically, the onset of acute kidney injury associated with drug administration is registered in approximately 20 % of patients and many of them develop chronic kidney disease vulnerability. However, current knowledge about the mechanisms underlying this dangerous phenomenon is still insufficient with many unknowns. Hence, the valuable use of these drugs in clinical practice is significantly limited. The main aim of this study is to draw attention to commonly prescribed nephrotoxic drugs by clinicians or drugs bought over the counter. In addition, the complex relationship between immunological, vascular and inflammatory events that promote kidney damage is discussed. The practical use of this knowledge could be implemented in the engineering of novel biomarkers for early detection of drug-associated kidney damage such as Kidney Injury Molecule (KIM-1), lipocalin associated with neutrophil gelatinase (NGAL) and various microRNAs. In addition, the utilization of artificial intelligence (AI) for the development of computer algorithms that could detect kidney damage at an early stage should be further explored. Therefore, this comprehensive review provides a new outlook on drug nephrotoxicity that opens the door for further clinical research of novel potential drugs or natural products for the prevention of drug-induced nephrotoxicity and accessible education.