Sanda: A Small and Incomplete Dataset Analyser

Ibias, Alfredo; Varma, Varun; Karol, Capala,; Gherardini, Luca; Sousa, J. Eduardo

doi:10.2139/ssrn.4364273

Cited by 1 publication

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To model the healthy and sick classes, we used the CACTUS ( 29 , 30 ) algorithm. In the first step, fully anonymized data abstractions of the quantitative and qualitative biomarker data were generated by ( 34 ) transforming raw biomarker data into two-stage data abstractions (flips) based on receiver-operator curve (ROC) theory.…”

Section: Methodsmentioning

confidence: 99%

“…At the same time, HaBio presents all the challenges for ML described above. Considering the need for novel biomarker discovery for haematuria patients’ stratification and ensuring the models explainability, we analysed the HaBio cohort using various ML algorithms, including the recently developed CACTUS explainable classification algorithm ( 29 , 30 ). To facilitate the diagnosis procedure and provide actionable insights for clinical patient management, we have provided a selection of biomarkers that could be useful in clinical practice, along with their possible decision boundaries.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Stratifying risk of disease in haematuria patients using machine learning techniques to improve diagnostics

Drożdż,

Duggan,

Ruddock

et al. 2024

Front. Oncol.

View full text Add to dashboard Cite

BackgroundDetailed and invasive clinical investigations are required to identify the causes of haematuria. Highly unbalanced patient population (predominantly male) and a wide range of potential causes make the ability to correctly classify patients and identify patient-specific biomarkers a major challenge. Studies have shown that it is possible to improve the diagnosis using multi-marker analysis, even in unbalanced datasets, by applying advanced analytical methods. Here, we applied several machine learning algorithms to classify patients from the haematuria patient cohort (HaBio) by analysing multiple biomarkers and to identify the most relevant ones.Materials and methodsWe applied several classification and feature selection methods (k-means clustering, decision trees, random forest with LIME explainer and CACTUS algorithm) to stratify patients into two groups: healthy (with no clear cause of haematuria) or sick (with an identified cause of haematuria e.g., bladder cancer, or infection). The classification performance of the models was compared. Biomarkers identified as important by the algorithms were also analysed in relation to their involvement in the pathological processes.ResultsResults showed that a high unbalance in the datasets significantly affected the classification by random forest and decision trees, leading to the overestimation of the sick class and low model performance. CACTUS algorithm was more robust to the unbalance in the dataset. CACTUS obtained a balanced accuracy of 0.747 for both genders, 0.718 for females and 0.803 for males. The analysis showed that in the classification process for the whole dataset: microalbumin, male gender, and tPSA emerged as the most informative biomarkers. For males: age, microalbumin, tPSA, cystatin C, BTA, HAD and S100A4 were the most significant biomarkers while for females microalbumin, IL-8, pERK, and CXCL16.ConclusionsCACTUS algorithm demonstrated improved performance compared with other methods such as decision trees and random forest. Additionally, we identified the most relevant biomarkers for the specific patient group, which could be considered in the future as novel biomarkers for diagnosis. Our results have the potential to inform future research and provide new personalised diagnostic approaches tailored directly to the needs of the individuals.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%