Hind Zantout

Understanding the trajectory of Huntington's disease (HD) is critical for patient stratification and the development of targeted interventions. Traditionally, studies relied on age–CAG models to estimate disease onset and progression, based on the well-established relationship between CAG repeat length and age at onset. However, additional genetic, environmental, and clinical factors can cause substantial variability. Recent machine learning approaches integrate clinical, imaging, and molecular data for more precise prediction of disease progression. Following PRISMA guidelines, we systematically reviewed studies on HD onset and progression. Using Web of Science, PubMed, and IEEE Xplore, 20 studies published between 2003 and 2024 met the inclusion criteria. We analyzed the machine learning approaches and input features used, assessed methodological quality, and evaluated risk of bias using the PROBAST tool. Overall, machine learning models, particularly support vector machines and ensemble approaches, consistently outperformed traditional age–CAG models. Several studies predicted conversion from premanifest to manifest HD within 5–10 years with high accuracy (88–98%). Beyond predicting onset, machine learning models have also been used to model dis-ease progression using clinical scores assessing motor, cognitive, and functional impairment. Performance was higher in studies incorporating structural and functional MRI biomarkers, and improved further with longitudinal clinical integration, enabling pre-diction of decline years before symptoms onset. Overall, machine learning shows strong potential to improve prognostic modeling in HD, especially through multimodal and longitudinal data. However, common methodological weaknesses and bias highlight the need for larger, externally validated studies using objective biomarkers.

Huntington's disease (HD) presents a heterogeneous neurodegenerative course, with motor, cognitive, and functional symptoms progressing differently across individuals. This atypical progression complicates the definition of discrete disease stages, hindering understanding of disease trajectories, timely pa- tient care, and therapy development. Consequently, current clinical staging systems rely heavily on clinician-defined, domain-specific criteria and fixed clinical measurement boundaries for stage assignment, reducing objectivity and often leading to overlapping clinical measurements across stages. While machine learning methods can help, existing approaches cannot fully capture complex temporal relationships within and across patients. We propose URL- STFN, a dynamic graph-based representation learning model that encodes both inter- and intra-patient temporal patterns from longitudinal clinical measures. We then evaluate disease stages formed through clustering and stability analysis of URL-STFN latent representations, and compare them with representations obtained from conventional embedding approaches. We further benchmark these clustering-based stages against states derived from conventional temporal models, including DHMM. We hypothesize that clustering URL-STFN latent representations enables identification of HD stages with reduced overlap in clinical measurements. The proposed framework is evaluated using 1,477 clinical visits from the Enroll-HD dataset, a large lon- gitudinal cohort with repeated clinical assessments. For staging, we used 44 clinical measurements spanning motor, cognitive, and functional domains. URL-STFN identifies clinically meaningful HD stages consistent with estab- lished disease progression while reducing overlap in clinical feature values compared with DHMM-derived and clinical staging approaches. These find- ings highlight the potential of a dynamic graph-based representation learning and clustering framework to support more objective, data-driven, and precise HD staging.

Programming demands a variety of cognitive skills, and mastering these competencies is essential for success in computer science education. The importance of formative feedback is well acknowledged in programming education, and thus, a diverse range of techniques has been proposed to generate and enhance formative feedback for programming exercises. This article reviews state-of-the-art automated feedback generation techniques and categorizes the various approaches based on the underlying computational techniques, programming languages, the kind of programming errors they deal with, and the type of feedback they provide. It covers data-driven techniques, those which use program repair methods, machine learning-based techniques, and techniques based around the use of large language models, particularly noting the rapid uptake of the latter. The article provides a summary of key findings and challenges, alongside recommendations for future work. The findings reveal that although there exist numerous tools for automated programming feedback, many studies depend on non-public benchmarks, which limits reproducibility and independent evaluation of the tools and their datasets. Additionally, tools are not always language agnostic and in some cases involve complex configuration steps. Large language models have demonstrated transformative potential in generating feedback. However, most research has focused on introductory courses (CS1 and CS2) indicating the need to apply them in advanced fields like machine learning and image processing. Although large language models have outperformed traditional approaches, challenges related to hallucinations and incorrect responses still need to be addressed as precision is critical in a pedagogical setting. Most of the studies use proprietary models that lack transparency and customization options, emphasizing the need for further research into open LLM alternatives.

Generative AI has considerably altered traditional workplace practice across numerous industries. Ever since the emergence of large language models (LLMs), their potential to generate formative feedback for introductory programming courses has been extensively researched. However, most of these studies have focused on Python. In this work, we examine the bug-fixing and feedback-generation abilities of Code Llama and ChatGPT for Java programming assignments using our new Java benchmark called CodeWBugs. The results indicate that ChatGPT performs reasonably well, and was able to fix 94.33% programs. By comparison, we observed high variability in the results from Code Llama. We further analyzed the impact of different types of prompts and observed that prompts that included task descriptions and test inputs yielded better results. In most cases, the LLMs precisely localized the bugs and also offered guidance on how to proceed. Nevertheless, we also noticed incorrect responses generated by the LLMs, emphasizing the need to validate responses before disseminating feedback to learners.