An interpretable machine learning prognostic system for risk stratification in oropharyngeal cancer

Alabi, Rasheed Omobolaji; Almangush, Alhadi; Elmusrati, Mohammed; Leivo, Ilmo; Mäkitie, Antti

doi:10.1016/j.ijmedinf.2022.104896

Cited by 23 publications

(17 citation statements)

References 62 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This interpretability can be particularly valuable in guiding treatment decisions, such as when considering alternative treatment modalities like radiotherapy (external/brachy), where surgery carries a higher risk of side effects On the other hand, RF and SVM models do not provide a straightforward way to visualize how the features impact the predicted outcome, which makes them less interpretable. Improving model interpretability was not the primary objective of our study; therefore we did not explore methods such as partial dependence plots or surrogate models to enhance interpretability ( 35 ).…”

Section: Discussionmentioning

confidence: 99%

A comparison of machine learning models for predicting urinary incontinence in men with localized prostate cancer

et al. 2023

View full text Add to dashboard Cite

IntroductionUrinary incontinence (UI) is a common side effect of prostate cancer treatment, but in clinical practice, it is difficult to predict. Machine learning (ML) models have shown promising results in predicting outcomes, yet the lack of transparency in complex models known as “black-box” has made clinicians wary of relying on them in sensitive decisions. Therefore, finding a balance between accuracy and explainability is crucial for the implementation of ML models. The aim of this study was to employ three different ML classifiers to predict the probability of experiencing UI in men with localized prostate cancer 1-year and 2-year after treatment and compare their accuracy and explainability. MethodsWe used the ProZIB dataset from the Netherlands Comprehensive Cancer Organization (Integraal Kankercentrum Nederland; IKNL) which contained clinical, demographic, and PROM data of 964 patients from 65 Dutch hospitals. Logistic Regression (LR), Random Forest (RF), and Support Vector Machine (SVM) algorithms were applied to predict (in)continence after prostate cancer treatment. ResultsAll models have been externally validated according to the TRIPOD Type 3 guidelines and their performance was assessed by accuracy, sensitivity, specificity, and AUC. While all three models demonstrated similar performance, LR showed slightly better accuracy than RF and SVM in predicting the risk of UI one year after prostate cancer treatment, achieving an accuracy of 0.75, a sensitivity of 0.82, and an AUC of 0.79. All models for the 2-year outcome performed poorly in the validation set, with an accuracy of 0.6 for LR, 0.65 for RF, and 0.54 for SVM. ConclusionThe outcomes of our study demonstrate the promise of using non-black box models, such as LR, to assist clinicians in recognizing high-risk patients and making informed treatment choices. The coefficients of the LR model show the importance of each feature in predicting results, and the generated nomogram provides an accessible illustration of how each feature impacts the predicted outcome. Additionally, the model’s simplicity and interpretability make it a more appropriate option in scenarios where comprehending the model’s predictions is essential.

show abstract

Section: Discussionmentioning

confidence: 99%

A comparison of machine learning models for predicting urinary incontinence in men with localized prostate cancer

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Considering the escalating global incidence of CRC, there is an urgent need for tools capable of quantifying the risk of disease progression, ultimately enhancing overall patient outcomes. A significant clinical challenge lies in accurately determining the risk of CRC‐related LMs and conducting timely imaging screening 21 . Numerous studies employing ML and AI technology 22 have contributed to the improved prognosis of CRC patients with remarkable results.…”

Section: Discussionmentioning

confidence: 99%

“…It is based on Shapley values, a game‐theoretic concept developed by economist Lloyd Shapley to determine the importance of individuals by calculating their contributions to cooperation. This method has received much attention in AI interpretability research and has contributed significantly to advancing the clinical applications of models 21,22 . The Shapley value interpretation is an additive feature attribution method that interprets a model's predicted value as a linear function of a binary variable.

g ()(, z^{'}) goodbreak= ϕ_{0} goodbreak+ \sum_{j = 1}^{M} ϕ_{j} z_{j}^{'}

z^{'} \in {\{0 ， 1\}}^{M}

ϕ_{j} \in R

where g is the explanatory model (3a), z is the coalition vector, M is the maximum coalition size (3b), and ϕ j ∈ R is the feature attribution of feature j .…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

An interpretable deep learning framework for predicting liver metastases in postoperative colorectal cancer patients using natural language processing and clinical data integration

Li,

Wang,

Cai

et al. 2023

Cancer Medicine

View full text Add to dashboard Cite

BackgroundThe significance of liver metastasis (LM) in increasing the risk of death for postoperative colorectal cancer (CRC) patients necessitates innovative approaches to predict LM.AimOur study presents a novel and significant contribution by developing an interpretable fusion model that effectively integrates both free‐text medical record data and structured laboratory data to predict LM in postoperative CRC patients.MethodsWe used a robust dataset of 1463 patients and leveraged state‐of‐the‐art natural language processing (NLP) and machine learning techniques to construct a two‐layer fusion framework that demonstrates superior predictive performance compared to single modal models. Our innovative two‐tier algorithm fuses the results from different data modalities, achieving balanced prediction results on test data and significantly enhancing the predictive ability of the model. To increase interpretability, we employed Shapley additive explanations to elucidate the contributions of free‐text clinical data and structured clinical data to the final model. Furthermore, we translated our findings into practical clinical applications by creating a novel NLP score‐based nomogram using the top 13 valid predictors identified in our study.ResultsThe proposed fusion models demonstrated superior predictive performance with an accuracy of 80.8%, precision of 80.3%, recall of 80.5%, and an F1 score of 80.8% in predicting LMs.ConclusionThis fusion model represents a notable advancement in predicting LMs for postoperative CRC patients, offering the potential to enhance patient outcomes and support clinical decision‐making.

show abstract

“…LIME, the acronym for local interpretable model-agnostic explanations 26 , is a model agnostic technique that is applied to an already trained model to investigate and analyze the relationship between the input parameters and output represented by the model 27 . It is a local model interpretability technique that works by tweaking the input parameters while observing the effect of this tweak on the output 28 . The significance of the tweaking helps to understand the degree of accuracy of the prediction made by the model and to investigate which of the input variables caused the prediction of a data sample.…”

Section: Methodsmentioning

confidence: 99%

Machine learning explainability in nasopharyngeal cancer survival using LIME and SHAP

Alabi

Elmusrati

Leivo

et al. 2023

Sci Rep

Self Cite

View full text Add to dashboard Cite

Nasopharyngeal cancer (NPC) has a unique histopathology compared with other head and neck cancers. Individual NPC patients may attain different outcomes. This study aims to build a prognostic system by combining a highly accurate machine learning model (ML) model with explainable artificial intelligence to stratify NPC patients into low and high chance of survival groups. Explainability is provided using Local Interpretable Model Agnostic Explanations (LIME) and SHapley Additive exPlanations (SHAP) techniques. A total of 1094 NPC patients were retrieved from the Surveillance, Epidemiology, and End Results (SEER) database for model training and internal validation. We combined five different ML algorithms to form a uniquely stacked algorithm. The predictive performance of the stacked algorithm was compared with a state-of-the-art algorithm—extreme gradient boosting (XGBoost) to stratify the NPC patients into chance of survival groups. We validated our model with temporal validation (n = 547) and geographic external validation (Helsinki University Hospital NPC cohort, n = 60). The developed stacked predictive ML model showed an accuracy of 85.9% while the XGBoost had 84.5% after the training and testing phases. This demonstrated that both XGBoost and the stacked model showed comparable performance. External geographic validation of XGBoost model showed a c-index of 0.74, accuracy of 76.7%, and area under curve of 0.76. The SHAP technique revealed that age of the patient at diagnosis, T-stage, ethnicity, M-stage, marital status, and grade were among the prominent input variables in decreasing order of significance for the overall survival of NPC patients. LIME showed the degree of reliability of the prediction made by the model. In addition, both techniques showed how each feature contributed to the prediction made by the model. LIME and SHAP techniques provided personalized protective and risk factors for each NPC patient and unraveled some novel non-linear relationships between input features and survival chance. The examined ML approach showed the ability to predict the chance of overall survival of NPC patients. This is important for effective treatment planning care and informed clinical decisions. To enhance outcome results, including survival in NPC, ML may aid in planning individualized therapy for this patient population.

show abstract

An interpretable machine learning prognostic system for risk stratification in oropharyngeal cancer

Cited by 23 publications

References 62 publications

A comparison of machine learning models for predicting urinary incontinence in men with localized prostate cancer

A comparison of machine learning models for predicting urinary incontinence in men with localized prostate cancer

An interpretable deep learning framework for predicting liver metastases in postoperative colorectal cancer patients using natural language processing and clinical data integration

Machine learning explainability in nasopharyngeal cancer survival using LIME and SHAP

Contact Info

Product

Resources

About