Prediction of Bladder Cancer Treatment Side Effects Using an Ontology-Based Reasoning for Enhanced Patient Health Safety

Abstract

Predicting potential cancer treatment side effects at time of prescription could decrease potential health risks and achieve better patient satisfaction. This paper presents a new approach, founded on evidence-based medical knowledge, using as much information and proof as possible to help a computer program to predict bladder cancer treatment side effects and support the oncologist’s decision. This will help in deciding treatment options for patients with bladder malignancies. Bladder cancer knowledge is complex and requires simplification before any attempt to represent it in a formal or computerized manner. In this work we rely on the capabilities of OWL ontologies to seamlessly capture and conceptualize the required knowledge about this type of cancer and the underlying patient treatment process. Our ontology allows case-based reasoning to effectively predict treatment side effects for a given set of contextual information related to a specific medical case. The ontology is enriched with proofs and evidence collected from online biomedical research databases using “web crawlers”. We have exclusively designed the crawler algorithm to search for the required knowledge based on a set of specified keywords. Results from the study presented 80.3% of real reported bladder cancer treatment side-effects prediction and were close to really occurring adverse events recorded within the collected test samples when applying the approach. Evidence-based medicine combined with semantic knowledge-based models is prominent in generating predictions related to possible health concerns. The integration of a diversity of knowledge and evidence into one single integrated knowledge-base could dramatically enhance the process of predicting treatment risks and side effects applied to bladder cancer oncotherapy.

Ontologies and Knowledge Graphs in Oncology Research

“…For lung cancer, Sesen et al [51] constructed the LUCADA ontology to use with the clinical decision support application Lung Cancer Assistant. In the domain of bladder cancer, Barki et al [52] developed an ontology to predict side effects caused by treatments.…”

“…Mahmoodi et al [49] derived association rules from the GCO and patient data using a modified version of an Apriori algorithm, to establish system-wide associations between events in text through large-scale text mining. Barki et al [52] predicted side effects of treatments for bladder cancer with Pellet. Nicholson et al [83] used reasoners to signal rule violations in the validation of international rules for multiple primary tumors.…”

“…Reasoners can also be used to detect errors in the ontologies or models that have been built. Works by Barki et al [52], and Nicholson et al [30,83] were described above. Herrmann et al [38] aimed at providing a generalizing pattern to classify tumors.…”

Patient experience of bladder cancer: A data linkage study

“…2 Side effects are related to treatment selection ranging from adverse reactions to chemotherapy and radiotherapy, to intraand post-operative complications associated with surgery. 3,4 Despite the high incidence, relatively little is known about patient experience of bladder cancer, as highlighted in a recent systematic review. 5 However, this information is important when helping patients to select management options and should also guide improvements to patient care pathways.…”

“…Management strategies typically include endoscopic resection, radiotherapy, chemotherapy, immunotherapy and radical surgical approaches such as cystectomy 2 . Side effects are related to treatment selection ranging from adverse reactions to chemotherapy and radiotherapy, to intra‐ and post‐operative complications associated with surgery 3,4 …”