Summary of Explainable Ai For Classifying Uti Risk Groups Using a Real-world Linked Ehr and Pathology Lab Dataset, by Yujie Dai et al.
Explainable AI for Classifying UTI Risk Groups Using a Real-World Linked EHR and Pathology Lab Dataset
by Yujie Dai, Brian Sullivan, Axel Montout, Amy Dillon, Chris Waller, Peter Acs, Rachel Denholm, Philip Williams, Alastair D Hay, Raul Santos-Rodriguez, Andrew Dowsey
First submitted to arxiv on: 26 Nov 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary A machine learning model is developed to analyze electronic health records (EHRs) and predict urinary tract infections (UTIs). The model leverages a linked EHR dataset from the UK, comprising around one million de-identified individuals. A data pre-processing pipeline transforms raw EHR data into a structured format for developing predictive models that prioritize fairness, accountability, and transparency. Given limited ground truth UTI outcomes, the study introduces a UTI risk estimation framework informed by clinical expertise to estimate UTI risk across individual patient timelines. Pairwise XGBoost models are trained using this framework to differentiate UTI risk categories, with explainable AI techniques applied to identify key predictors and support interpretability. The findings reveal differences in clinical and demographic predictors across risk groups. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper uses machine learning to help doctors make better decisions about urinary tract infections (UTIs). It looks at a huge dataset of electronic health records from the UK, where over one million people’s medical information is stored. The team developed a special way to clean up this data so that computers can understand it and use it to predict who might get a UTI. Because there aren’t many examples of actual UTIs in the data, they came up with a new method to figure out how likely someone is to get a UTI based on their past medical history. They also used special techniques to help doctors understand why the model made certain predictions. The results show that different groups of people have different signs and symptoms that might indicate a higher risk of getting a UTI. |
Keywords
» Artificial intelligence » Machine learning » Xgboost
