Cox Proportional Hazards (CPH) analysis is the standard for survival analysis in oncology. Recently, several machine learning (ML) techniques have been adapted for this task. Although they have shown to yield results at least as good as classical methods, they are often disregarded because of their lack of transparency and little to no explainability, which are key for their adoption in clinical settings. In this paper, we used data from the Netherlands Cancer Registry of 36,658 non-metastatic breast cancer patients to compare the performance of CPH with ML techniques (Random Survival Forests, Survival Support Vector Machines, and Extreme Gradient Boosting [XGB]) in predicting survival using the $$c$$c -index. We demonstrated that in our dataset, ML-based models can perform at least as good as the classical CPH regression ( $$c$$c -index $$\sim \,0.63$$∼0.63 ), and in the case of XGB even better ( $$c$$c -index $$\sim 0.73$$∼0.73 ). Furthermore, we used Shapley Additive Explanation (SHAP) values to explain the models’ predictions. We concluded that the difference in performance can be attributed to XGB’s ability to model nonlinearities and complex interactions. We also investigated the impact of specific features on the models’ predictions as well as their corresponding insights. Lastly, we showed that explainable ML can generate explicit knowledge of how models make their predictions, which is crucial in increasing the trust and adoption of innovative ML techniques in oncology and healthcare overall.

Miniature, wearable sensor modules are a promising technology to monitor activities of daily living (ADL) over extended periods of time. To assure both user compliance and meaningful results, the selection and placement site of sensors requires careful consideration. We investigated these aspects for the classification of 16 ADL in 6 healthy subjects under laboratory conditions using ReSense, our custom-made inertial measurement unit enhanced with a barometric pressure sensor used to capture activity-related altitude changes. Subjects wore a module on each wrist and ankle, and one on the trunk. Activities comprised whole body movements as well as gross and dextrous upper-limb activities. Wrist-module data outperformed the other locations for the three activity groups. Specifically, overall classification accuracy rates of almost 93% and more than 95% were achieved for the repeated holdout and user-specific validation methods, respectively, for all 16 activities. Including the altitude profile resulted in a considerable improvement of up to 20% in the classification accuracy for stair ascent and descent. The gyroscopes provided no useful information for activity classification under this scheme. The proposed sensor setting could allow for robust long-term activity monitoring with high compliance in different patient populations.

Objectives: Increasing evidence exists that poor speech perception abilities precede the phonological deficits typically observed in dyslexia, a developmental disorder in learning to read. Impaired processing of dynamic features of speech, such as slow amplitude fluctuations and transient acoustic cues, disrupts effortless tracking of the speech envelope and constrains the development of adequate phonological skills. In this study, a speech envelope enhancement (EE) strategy was implemented to reduce speech perception deficits by students with dyslexia. The EE emphasizes onset cues and reinforces the temporal structure of the speech envelope specifically. Design: Speech perception was assessed in 42 students with and without dyslexia using a sentence repetition task in a speech-weighted background noise. Both natural and vocoded speech were used to assess the contribution of the temporal envelope on the speech perception deficit. Their envelope-enhanced counterparts were added to each baseline condition to administer the effect of the EE algorithm. In addition to speech-in-noise perception, general cognitive abilities were assessed. Results: Results demonstrated that students with dyslexia not only benefit from EE but benefit more from it than typical readers. Hence, EE completely normalized speech reception thresholds for students with dyslexia under adverse listening conditions. In addition, a correlation between speech perception deficits and phonological processing was found for students with dyslexia, further supporting the relation between speech perception abilities and reading skills. Similar results and relations were found for conditions with natural and vocoded speech, providing evidence that speech perception deficits in dyslexia stem from difficulties in processing the temporal envelope. Conclusions: Using speech EE, speech perception skills in students with dyslexia were improved passively and instantaneously, without requiring any explicit learning. In addition, the observed positive relationship between speech processing and advanced phonological skills opens new avenues for specific intervention strategies that directly target the potential core deficit in dyslexia.

In the last few years, federated learning (FL) has emerged as a novel alternative for analyzing data spread across different parties without needing to centralize them. In order to increase the adoption of FL, there is a need to develop more algorithms that can be deployed under this novel privacy-preserving paradigm. In this paper, we present our federated generalized linear model (GLM) for horizontally partitioned data. It allows generating models of different families (linear, Poisson, logistic) without disclosing privacy-sensitive individual records. We describe its algorithm (which can be implemented in the user’s platform of choice) and compare the obtained federated models against their centralized counterpart, which were mathematically equivalent. We also validated their execution time with increasing numbers of records and involved parties. We show that our federated GLM is accurate enough to be used for the privacy-preserving analysis of horizontally partitioned data in real-life scenarios. Further development of this type of algorithm has the potential to make FL a much more common practice among researchers.

Machine Learning (ML) can improve the diagnosis, treatment decisions, and understanding of cancer. However, the low explainability of how "black box" ML methods produce their output hinders their clinical adoption. In this paper, we used data from the Netherlands Cancer Registry to generate a ML-based model to predict 10-year overall survival of breast cancer patients. Then, we used Local Interpretable Model-Agnostic Explanations (LIME) and SHapley Additive exPlanations (SHAP) to interpret the model's predictions. We found that, overall, LIME and SHAP tend to be consistent when explaining the contribution of different features. Nevertheless, the feature ranges where they have a mismatch can also be of interest, since they can help us identifying "turning points" where features go from favoring survived to favoring deceased (or vice versa). Explainability techniques can pave the way for better acceptance of ML techniques. However, their evaluation and translation to real-life scenarios need to be researched further.

Background Long‐term colon cancer survivors present heterogeneous health‐related quality of life (HRQOL) outcomes. We determined unobserved subgroups (classes) of survivors with similar HRQOL patterns and investigated their stability over time and the association of clinical covariates with these classes. Materials and Methods Data from the population‐based PROFILES registry were used. Included were survivors with nonmetastatic (TNM stage I–III) colon cancer (n = 1,489). HRQOL was assessed with the Dutch translation of the European Organisation for Research and Treatment of Cancer Quality of Life Questionnaire C30 version 3.0. Based on survivors’ HRQOL, latent class analysis (LCA) was used to identify unobserved classes of survivors. Moreover, latent transition analysis (LTA) was used to investigate changes in class membership over time. Furthermore, the effect of covariates on class membership was assessed using multinomial logistic regression. Results LCA identified five classes at baseline: class 1, excellent HRQOL (n = 555, 37.3%); class 2, good HRQOL with prevalence of insomnia (n = 464, 31.2%); class 3, moderate HRQOL with prevalence of fatigue (n = 213, 14.3%); class 4, good HRQOL with physical limitations (n = 134, 9.0%); and class 5, poor HRQOL (n = 123, 8.3%). All classes were stable with high self‐transition probabilities. Longer time since the diagnosis, no comorbid conditions, and male sex were associated with class 1, whereas older age was associated with class 4. Clinical covariates were not associated with class membership. Conclusion The identified classes are characterized by distinct patterns of HRQOL and can support patient‐centered care. LCA and LTA are powerful tools for investigating HRQOL in cancer survivors. Implications for Practice Long‐term colon cancer survivors show great heterogeneity in their health‐related quality of life. This study identified five distinct clusters of survivors with similar patterns of health‐related quality of life and showed that these clusters remain stable over time. It was also shown that these clusters do not significantly differ in tumor characteristics or received treatment. Cluster membership of long‐term survivors can be identified by sociodemographic characteristics but is not predetermined by diagnosis and treatment.