Applying the Huntington's Disease Integrated Staging System (HD-ISS) to Observational Studies

Prognostic enrichment for early-stage Huntington's disease: An explainable machine learning approach for clinical trial

BACKGROUND

In Huntington's disease clinical trials, recruitment and stratification approaches primarily rely on genetic load, cognitive and motor assessment scores. They focus less on in vivo brain imaging markers, which reflect neuropathology well before clinical diagnosis. Machine learning methods offer a degree of sophistication which could significantly improve prognosis and stratification by leveraging multimodal biomarkers from large datasets. Such models specifically tailored to HD gene expansion carriers could further enhance the efficacy of the stratification process.

OBJECTIVES

To improve stratification of Huntington's disease individuals for clinical trials.

METHODS

We used data from 451 gene positive individuals with Huntington's disease (both premanifest and diagnosed) from previously published cohorts (PREDICT, TRACK, TrackON, and IMAGE). We applied whole-brain parcellation to longitudinal brain scans and measured the rate of lateral ventricular enlargement, over 3 years, which was used as the target variable for our prognostic random forest regression models. The models were trained on various combinations of features at baseline, including genetic load, cognitive and motor assessment score biomarkers, as well as brain imaging-derived features. Furthermore, a simplified stratification model was developed to classify individuals into two homogenous groups (low risk and high risk) based on their anticipated rate of ventricular enlargement.

RESULTS

The predictive accuracy of the prognostic models substantially improved by integrating brain imaging features alongside genetic load, cognitive and motor biomarkers: a 24 % reduction in the cross-validated mean absolute error, yielding an error of 530 mm3/year. The stratification model had a cross-validated accuracy of 81 % in differentiating between moderate and fast progressors (precision = 83 %, recall = 80 %).

CONCLUSIONS

This study validated the effectiveness of machine learning in differentiating between low- and high-risk individuals based on the rate of ventricular enlargement. The models were exclusively trained using features from HD individuals, which offers a more disease-specific, simplified, and accurate approach for prognostic enrichment compared to relying on features extracted from healthy control groups, as done in previous studies. The proposed method has the potential to enhance clinical utility by: i) enabling more targeted recruitment of individuals for clinical trials, ii) improving post-hoc evaluation of individuals, and iii) ultimately leading to better outcomes for individuals through personalized treatment selection.

Time to Functional Loss as an Endpoint in Huntington's Disease Trials: Enrichment and Sample Size

BACKGROUND

Clinical trial scenarios can be modeled using data from observational studies, providing critical information for design of real-world trials. The Huntington's Disease Integrated Staging System (HD-ISS) characterizes disease progression over an individual's lifespan and allows for flexibility in the design of trials with the goal of delaying progression. Enrichment methods can be applied to the HD-ISS to identify subgroups requiring smaller estimated sample sizes.

OBJECTIVE

Investigate time to the event of functional decline (HD-ISS Stage 3) as an endpoint for trials in HD and present sample size estimates after enrichment.

METHODS

We classified individuals from observational studies according to the HD-ISS. We assessed the ability of the prognostic index normed (PIN) and its components to predict time to HD-ISS Stage 3. For enrichment, we formed groups from deciles of the baseline PIN distribution for HD-ISS Stage 2 participants. We selected enrichment subgroups closer to Stage 3 transition and estimated sample sizes, using delay in the transition time as the effect size.

RESULTS

In predicting time to HD-ISS Stage 3, PIN outperforms its components. Survival curves for each PIN decile show that groups with PIN from 1.48 to 2.74 have median time to Stage 3 of approximately 2 years and these are combined to create enrichment subgroups. Sample size estimates are presented by enrichment subgroup.

CONCLUSIONS

PIN is predictive of functional decline. A delay of 9 months or more in the transition to Stage 3 for an enriched sample yields feasible sample size estimates, demonstrating that this approach can aid in planning future trials. © 2024 The Author(s). Movement Disorders published by Wiley Periodicals LLC on behalf of International Parkinson and Movement Disorder Society.

Huntington's Disease: Latest Frontiers in Therapeutics

PURPOSE OF REVIEW

Huntington's disease (HD) is an autosomal-dominant disorder caused by a pathological expansion of a trinucleotide repeat (CAG) on exon 1 of the huntingtin (HTT) gene. HD is characterized by the presence of chorea, alongside other hyperkinesia, parkinsonism and a combination of cognitive and behavioural features. Currently, there are no disease-modifying therapies (DMTs) for HD, and the only intervention(s) with approved indication target the treatment of chorea. This article reviews recent research on the clinical development of DMTs and newly developed tools that enhance clinical trial design towards a successful DMT in the future.

RECENT FINDINGS

HD is living in an era of target-specific drug development with emphasis on the mechanisms related to mutant Huntingtin (HTT) protein. Examples include antisense oligonucleotides (ASO), splicing modifiers and microRNA molecules that aim to reduce the levels of mutant HTT protein. After initial negative results with ASO molecules Tominersen and WVE-120101/ WVE-120102, the therapeutic landscape continues to expand, with various trials currently under development to document proof-of-concept and safety/tolerability. Immune-targeted therapies have also been evaluated in early-phase clinical trials, with promising preliminary findings. The possibility of quantifying mHTT in CSF, along with the development of an integrated biological staging system in HD are important innovations applicable to clinical trial design that enhance the drug development process. Although a future in HD with DMTs remains a hope for those living with HD, care partners and care providers, the therapeutic landscape is promising, with various drug development programs underway following a targeted approach supported by disease-specific biomarkers and staging frameworks.

Prevalence and burden of pain across the entire spectrum of Huntington's disease

BACKGROUND

Pain is an important symptom in Huntington's disease (HD), however, not systematically studied and understood. The objective of the current study is to assess the prevalence of pain, pain interference in daily activities, painful conditions, analgesic use and the severity of the pain burden across different disease stages and 'Age at symptom Onset' groups. Additionally, the association between pain and disease burden was investigated.

METHODS

A cross-sectional analysis was conducted within two large data sets, which included different types of pain scales. Multivariable logistic regression analyses and analyses of variance were performed to compare the pain levels with those in the general population. The analyses were adjusted for sex and age. Locally Estimated Scatterplot Smoothing was used to test the association between pain and the HD pathology score: a measure of disease burden.

RESULTS

The mean prevalence of pain in the HD population was 40% and for pain interference around 35% in both data sets. Patients in the early, middle and late stage of HD experience more pain burden compared with what is reported in patients with chronic pain (p<0.01). A positive and significant association was demonstrated between pain and disease burden. Patients in late stage HD with pain use significantly less analgesics compared with the general population (5% vs 13%, respectively (p<0.01)).

CONCLUSIONS

Pain is a prevalent and important symptom in HD. Severe pain burden in the HD population is present and positively associated with disease burden. Risk for undertreatment with analgesics is nevertheless present. Awareness of pain in HD needs to be increased, both clinically and scientifically.

Exploring bradyphrenia in Huntington's disease using the computerized test of information processing (CTiP)

Background

Bradyphrenia, best thought of as the mental equivalent of bradykinesia, has been described in several disorders of the brain including Parkinson's disease and schizophrenia; however, little is known about this phenomenon in Huntington's Disease (HD).

Objective

The aim of this study was to investigate the presence of bradyphrenia in HD using the Computerized Test of Information Processing (CTiP), an easy to administer and objective task that assesses cognitive processing speed with increasing task complexity.

Methods

This study included 211 participants: Huntington's Disease Integrated Staging System (HD-ISS) Stage 0 [n = 28], Stage 1 [n = 30], Stage 2 [n = 48] and Stage 3 [n = 48], and healthy controls (HC) [n = 57]. The CTiP incorporates three subtests: Simple Reaction Time (SRT), which assesses baseline motor function; Choice Reaction Time (CRT), with an added decisional component; and Semantic Search Reaction Time (SSRT), with an added conceptual component. SRT scores were subtracted from CRT and SSRT scores to establish a motor-corrected measure of central conduction time, which was used to operationalize bradyphrenia.

Results

HD-ISS and HC within-group reaction times differed significantly when comparing motor-corrected CRT vs SSRT (all ps < 0.0001). Furthermore, the magnitude of these differences increased with HD disease stage (p < 0.0001). An ROC analysis determined that motor-corrected within-subject differences significantly distinguished Stage 2 + 3 from Stage 0 + 1 (AUC = 0.72, p < 0.0001).

Conclusions

We report evidence of bradyphrenia in HD that increases with disease progression. This processing deficit, which can be quantified using the CTiP, has the potential to greatly impact HD daily life and warrants additional research.

Clinical Review of Juvenile Huntington's Disease

 Juvenile Huntington's disease (JHD) is rare. In the first decade of life speech difficulties, rigidity, and dystonia are common clinical motor symptoms, whereas onset in the second decade motor symptoms may sometimes resemble adult-onset Huntington's disease (AOHD). Cognitive decline is mostly detected by declining school performances. Behavioral symptoms in general do not differ from AOHD but may be confused with autism spectrum disorder or attention deficit hyperactivity disorder and lead to misdiagnosis and/or diagnostic delay. JHD specific features are epilepsy, ataxia, spasticity, pain, itching, and possibly liver steatosis. Disease progression of JHD is faster compared to AOHD and the disease duration is shorter, particularly in case of higher CAG repeat lengths. The diagnosis is based on clinical judgement in combination with a positive family history and/or DNA analysis after careful consideration. Repeat length in JHD is usually > 55 and caused by anticipation, usually via paternal transmission. There are no pharmacological and multidisciplinary guidelines for JHD treatment. Future perspectives for earlier diagnosis are better diagnostic markers such as qualitative MRI and neurofilament light in serum.