Prognostic models for amyotrophic lateral sclerosis: a systematic review

Update on recent advances in amyotrophic lateral sclerosis

In the last few years, our understanding of disease molecular mechanisms underpinning ALS has advanced greatly, allowing the first steps in translating into clinical practice novel research findings, including gene therapy approaches. Similarly, the recent advent of assistive technologies has greatly improved the possibility of a more personalized approach to supportive and symptomatic care, in the context of an increasingly complex multidisciplinary line of actions, which remains the cornerstone of ALS management. Against this rapidly growing background, here we provide an comprehensive update on the most recent studies that have contributed towards our understanding of ALS pathogenesis, the latest results from clinical trials as well as the future directions for improving the clinical management of ALS patients.

Current neuroprotective therapies and future prospects for motor neuron disease

Four medications with neuroprotective disease-modifying effects are now in use for motor neuron disease (MND). With FDA approvals for tofersen, relyvrio and edaravone in just the past year, 2022 ended a quarter of a century when riluzole was the sole such drug to offer to patients. The acceleration of approvals may mean we are witnessing the beginning of a step-change in how MND can be treated. Improvements in understanding underlying disease biology has led to more therapies being developed to target specific and multiple disease mechanisms. Consideration for how the pipeline of new therapeutic agents coming through in clinical and preclinical development can be more effectively evaluated with biomarkers, advances in patient stratification and clinical trial design pave the way for more successful translation for this archetypal complex neurodegenerative disease. While it must be cautioned that only slowed rates of progression have so far been demonstrated, pre-empting rapid neurodegeneration by using neurofilament biomarkers to signal when to treat, as is currently being trialled with tofersen, may be more effective for patients with known genetic predisposition to MND. Early intervention with personalized medicines could mean that for some patients at least, in future we may be able to substantially treat what is considered by many to be one of the most distressing diseases in medicine.

Systematic reviews of machine learning in healthcare: a literature review

INTRODUCTION

The increasing availability of data and computing power has made machine learning (ML) a viable approach to faster, more efficient healthcare delivery.

METHODS

A systematic literature review (SLR) of published SLRs evaluating ML applications in healthcare settings published between1 January 2010 and 27 March 2023 was conducted.

RESULTS

In total 220 SLRs covering 10,462 ML algorithms were reviewed. The main application of AI in medicine related to the clinical prediction and disease prognosis in oncology and neurology with the use of imaging data. Accuracy, specificity, and sensitivity were provided in 56%, 28%, and 25% SLRs respectively. Internal and external validation was reported in 53% and less than 1% of the cases respectively. The most common modeling approach was neural networks (2,454 ML algorithms), followed by support vector machine and random forest/decision trees (1,578 and 1,522 ML algorithms, respectively).

EXPERT OPINION

The review indicated considerable reporting gaps in terms of the ML's performance, both internal and external validation. Greater accessibility to healthcare data for developers can ensure the faster adoption of ML algorithms into clinical practice.

Management of amyotrophic lateral sclerosis in clinical practice: Results of the expert consensus using the Delphi methodology

Amyotrophic lateral sclerosis (ALS) is a rare disease characterized by a progressive and irreversible degeneration of upper and lower motor neurons leading to death. In France, limited data exist describing the criteria used in clinical practice for diagnosis and follow-up, and how novel therapies may fit in. The objective of this Delphi panel was to obtain an overview of current French practices in ALS diagnosis, management, and follow-up by determining the scales and criteria used in clinical practice outside of clinical trials, as well as the place of a future treatment like AMX0035, acting on endoplasmic reticulum (ER) stress and mitochondrial dysfunction, in the current therapeutic strategies. A questionnaire was administered to 24 ALS healthcare providers practicing in ALS centers in France. Two rounds of remote voting were organized, before proposition of final consensus statements. Consensus was considered reached when at least 66% of the voters agreed. Consensus were obtained to define the new Gold Coast criteria as the ones used in clinical practice to establish the diagnosis of ALS, thus replacing the revised El Escorial criteria, considered too complex and now mainly used to characterize the patient populations to be included in clinical trials. The clinical factors considered to establish ALS diagnosis are mainly the demonstration of progression of the motor deficit and elimination of differential diagnoses. The ALSFRS-R scale is used in daily clinical practice to assess patient's functional impairment in terms of number of points lost, with the bulbar, respiratory, and fine motor subscores being the most important to evaluate independently. A critical medical need was identified regarding the provision of new therapeutic alternatives in ALS. The panel members would support the earliest management of patients. In this landscape, based on data from a very encouraging phase II (Centaur trial), AMX0035 represents a new tool of choice in current treatment strategies for all patients for whom experts are confident in the diagnosis of ALS, in combination with riluzole. These results will need to be confirmed by the ongoing phase III trial (Phoenix trial).

Palliative Care in Amyotrophic Lateral Sclerosis

Amyotrophic lateral sclerosis (ALS) is an incurable neurodegenerative disease of the motor neurons. Given the evolutive characteristics of this disease, palliative care principles should be a foundation of ALS care. A multidisciplinary medical intervention is of paramount importance in the different phases of disease. The involvement of the palliative care team improves quality of life and symptoms, and prognosis. Early initiation is of paramount importance to ensuring patient-centered care, when the patient has still the capability to communicate effectively and participate in his medical care. Advance care planning supports patients and family members in understanding and sharing their preferences according to their personal values and life goals regarding future medical treatment. The principal problems which require intensive supportive care include cognitive disturbances, psychological distress, pain, sialorrhrea, nutrition, and ventilatory support. Communication skills of health-care professionals are mandatory to manage the inevitability of death. Palliative sedation has peculiar aspects in this population, particularly with the decision of withdrawing ventilatory support.

Artificial intelligence and statistical methods for stratification and prediction of progression in amyotrophic lateral sclerosis: A systematic review

BACKGROUND

Amyotrophic Lateral Sclerosis (ALS) is a fatal neurodegenerative disorder characterised by the progressive loss of motor neurons in the brain and spinal cord. The fact that ALS's disease course is highly heterogeneous, and its determinants not fully known, combined with ALS's relatively low prevalence, renders the successful application of artificial intelligence (AI) techniques particularly arduous.

OBJECTIVE

This systematic review aims at identifying areas of agreement and unanswered questions regarding two notable applications of AI in ALS, namely the automatic, data-driven stratification of patients according to their phenotype, and the prediction of ALS progression. Differently from previous works, this review is focused on the methodological landscape of AI in ALS.

METHODS

We conducted a systematic search of the Scopus and PubMed databases, looking for studies on data-driven stratification methods based on unsupervised techniques resulting in (A) automatic group discovery or (B) a transformation of the feature space allowing patient subgroups to be identified; and for studies on internally or externally validated methods for the prediction of ALS progression. We described the selected studies according to the following characteristics, when applicable: variables used, methodology, splitting criteria and number of groups, prediction outcomes, validation schemes, and metrics.

RESULTS

Of the starting 1604 unique reports (2837 combined hits between Scopus and PubMed), 239 were selected for thorough screening, leading to the inclusion of 15 studies on patient stratification, 28 on prediction of ALS progression, and 6 on both stratification and prediction. In terms of variables used, most stratification and prediction studies included demographics and features derived from the ALSFRS or ALSFRS-R scores, which were also the main prediction targets. The most represented stratification methods were K-means, and hierarchical and expectation-maximisation clustering; while random forests, logistic regression, the Cox proportional hazard model, and various flavours of deep learning were the most widely used prediction methods. Predictive model validation was, albeit unexpectedly, quite rarely performed in absolute terms (leading to the exclusion of 78 eligible studies), with the overwhelming majority of included studies resorting to internal validation only.

CONCLUSION

This systematic review highlighted a general agreement in terms of input variable selection for both stratification and prediction of ALS progression, and in terms of prediction targets. A striking lack of validated models emerged, as well as a general difficulty in reproducing many published studies, mainly due to the absence of the corresponding parameter lists. While deep learning seems promising for prediction applications, its superiority with respect to traditional methods has not been established; there is, instead, ample room for its application in the subfield of patient stratification. Finally, an open question remains on the role of new environmental and behavioural variables collected via novel, real-time sensors.

Construction and Verification of a Risk Prediction Model for the Occurrence of Delayed Cerebral Ischemia after Aneurysmal Subarachnoid Hemorrhage Requiring Mechanical Ventilation

Objectives

Delayed cerebral ischemia (DCI) contributes to poor aneurysm prognosis. Subarachnoid hemorrhage and DCI have irreversible and severe consequences once they occur; therefore, early prediction and prevention are important. We investigated the risk factors for postoperative complications of DCI in patients with aneurysmal subarachnoid hemorrhage (aSAH) requiring mechanical ventilation in intensive care and validated a prediction model.

Methods

We retrospectively analyzed patients with aSAH who were treated in a French university hospital neuro-ICU between January 2010 and December 2015. The patients were randomized into a training group (144) and verification groups (60). Nomograms were validated in the training and verification groups, where receiver operating characteristic curve analysis was used to verify model discrimination; calibration curve and Hosmer-Lemeshow test were used to determine model calibration; and decision curve analysis (DCA) was used to verify clinical validity of the model.

Results

External ventricular drain (EVD), duration of mechanical ventilation, and treatment were significantly associated in the univariate analysis; EVD and rebleeding were significantly associated with the occurrence of DCI after aSAH. Binary logistic regression was used to select five clinicopathological characteristics to predict the occurrence of DCI in patients with aSAH requiring mechanical ventilation nomograms of the risk of DCI. Area under the curve values for the training and verification groups were 0.768 and 0.246, with Brier scores of 0.166 and 0.163, respectively. Hosmer-Lemeshow calibration test values for the training and verification groups were x ² = 3.824 (P = 0.923) and x ² = 10.868 (P = 0.285), respectively. Calibration curves showed good agreement. DCA indicated that the training and verification groups showed large positive returns in the broad risk range of 0-77% and 0-63%, respectively.

Conclusions

The predictive model of concurrent DCI in aSAH has theoretical and practical values and can provide individualized treatment options for patients with aSAH who require mechanical ventilation.

Role of brain 2-[18F]fluoro-2-deoxy-D-glucose-positron-emission tomography as survival predictor in amyotrophic lateral sclerosis

PURPOSE

The identification of prognostic tools in amyotrophic lateral sclerosis (ALS) would improve the design of clinical trials, the management of patients, and life planning. We aimed to evaluate the accuracy of brain 2-[¹⁸F]fluoro-2-deoxy-D-glucose-positron-emission tomography (2-[¹⁸F]FDG-PET) as an independent predictor of survival in ALS.

METHODS

A prospective cohort study enrolled 418 ALS patients, who underwent brain 2-[¹⁸F]FDG-PET at diagnosis and whose survival time was available. We discretized the survival time in a finite number of classes in a data-driven fashion by employing a k-means-like strategy. We identified "hot brain regions" with maximal power in discriminating survival classes, by evaluating the Laplacian scores in a class-aware fashion. We retained the top-m features for each class to train the classification systems (i.e., a support vector machine, SVM), using 10% of the ALS cohort as test set.

RESULTS

Data were discretized in three survival profiles: 0-2 years, 2-5 years, and > 5 years. SVM resulted in an error rate < 20% for two out of three classes separately. As for class one, the discriminant clusters included left caudate body and anterior cingulate cortex. The most discriminant regions were bilateral cerebellar pyramid in class two, and right cerebellar dentate nucleus, and left cerebellar nodule in class three.

CONCLUSION

Brain 2-[¹⁸F]FDG-PET along with artificial intelligence was able to predict with high accuracy the survival time range in our ALS cohort. Healthcare professionals can benefit from this prognostic tool for planning patients' management and follow-up. 2-[¹⁸F]FDG-PET represents a promising biomarker for individual patients' stratification in clinical trials. The lack of a multicentre external validation of the model warrants further studies to evaluate its generalization capability.

A novel quantitative indicator for disease progression rate in amyotrophic lateral sclerosis

OBJECTIVE

The current study sought to develop a new indicator for disease progression rate in amyotrophic lateral sclerosis (ALS).

METHODS

We used a nonparametric method to score diverse patterns of decline in the percentage of predicted forced vital capacity (%FVC) in patients with ALS. This involved 6317 longitudinal %FVC data sets from 920 patients in the Pooled Resource Open-Access ALS Clinical Trials (PRO-ACT) database volunteered by PRO-ACT Consortium members. To assess the utility of the derived scores as a disease indicator, we examined changes over time, the association with prognosis, and correlation with the Risk Profile of the Treatment Research Initiative to Cure ALS (TRICALS). Our local cohort (n = 92) was used for external validation.

RESULTS

We derived scores ranging from 35 to 106 points to construct the FVC Decline Pattern scale (FVC-DiP). Individuals' FVC-DiP scores were determined from a single measurement of %FVC and disease duration at assessment. Although the %FVC declined over the disease course (p < 0.0001), the FVC-DiP remained relatively stable. Low FVC-DiP scores were associated with rapid disease progression. Using our cohort, we demonstrated an association between FVC-DiP and the survival prognosis, the stability of the FVC-DiP per individual, and a correlation between FVC-DiP scores and the TRICALS Risk Profile (r² = 0.904, p < 0.0001).

CONCLUSIONS

FVC-DiP scores reflected patterns of declining %FVC over the natural course of ALS and indicated the disease progression rate. The FVC-DiP may enable easy assessment of disease progression patterns and could be used for assessing treatment efficacy.

Artificial intelligence and its impact on the domains of universal health coverage, health emergencies and health promotion: An overview of systematic reviews

•

An overview of systematic reviews on the application of AI including 129 studies.

•

AI use is prominent in Universal Health Coverage, featuring image analysis in neoplasms.

•

Half of the reviews did not evaluate validation procedures nor reporting guidelines.

•

Risk of bias was only included un a third of the reviews.

•

There is not sufficient evidence to transfer AI to actual healthcare delivery.

Background

Artificial intelligence is fueling a new revolution in medicine and in the healthcare sector. Despite the growing evidence on the benefits of artificial intelligence there are several aspects that limit the measure of its impact in people’s health. It is necessary to assess the current status on the application of AI towards the improvement of people’s health in the domains defined by WHO’s Thirteenth General Programme of Work (GPW13) and the European Programme of Work (EPW), to inform about trends, gaps, opportunities, and challenges.

Objective

To perform a systematic overview of systematic reviews on the application of artificial intelligence in the people’s health domains as defined in the GPW13 and provide a comprehensive and updated map on the application specialties of artificial intelligence in terms of methodologies, algorithms, data sources, outcomes, predictors, performance, and methodological quality.

Methods

A systematic search in MEDLINE, EMBASE, Cochrane and IEEEXplore was conducted between January 2015 and June 2021 to collect systematic reviews using a combination of keywords related to the domains of universal health coverage, health emergencies protection, and better health and wellbeing as defined by the WHO’s PGW13 and EPW. Eligibility criteria was based on methodological quality and the inclusion of practical implementation of artificial intelligence. Records were classified and labeled using ICD-11 categories into the domains of the GPW13. Descriptors related to the area of implementation, type of modeling, data entities, outcomes and implementation on care delivery were extracted using a structured form and methodological aspects of the included reviews studies was assessed using the AMSTAR checklist.

Results

The search strategy resulted in the screening of 815 systematic reviews from which 203 were assessed for eligibility and 129 were included in the review. The most predominant domain for artificial intelligence applications was Universal Health Coverage (N = 98) followed by Health Emergencies (N = 16) and Better Health and Wellbeing (N = 15). Neoplasms area on Universal Health Coverage was the disease area featuring most of the applications (21.7 %, N = 28). The reviews featured analytics primarily over both public and private data sources (67.44 %, N = 87). The most used type of data was medical imaging (31.8 %, N = 41) and predictors based on regions of interest and clinical data. The most prominent subdomain of Artificial Intelligence was Machine Learning (43.4 %, N = 56), in which Support Vector Machine method was predominant (20.9 %, N = 27). Regarding the purpose, the application of Artificial Intelligence I is focused on the prediction of the diseases (36.4 %, N = 47). With respect to the validation, more than a half of the reviews (54.3 %, N = 70) did not report a validation procedure and, whenever available, the main performance indicator was the accuracy (28.7 %, N = 37). According to the methodological quality assessment, a third of the reviews (34.9 %, N = 45) implemented methods for analysis the risk of bias and the overall AMSTAR score below was 5 (4.01 ± 1.93) on all the included systematic reviews.

Conclusion

Artificial intelligence is being used for disease modelling, diagnose, classification and prediction in the three domains of GPW13. However, the evidence is often limited to laboratory and the level of adoption is largely unbalanced between ICD-11 categoriesand diseases. Data availability is a determinant factor on the developmental stage of artificial intelligence applications. Most of the reviewed studies show a poor methodological quality and are at high risk of bias, which limits the reproducibility of the results and the reliability of translating these applications to real clinical scenarios. The analyzed papers show results only in laboratory and testing scenarios and not in clinical trials nor case studies, limiting the supporting evidence to transfer artificial intelligence to actual care delivery.

Predicting functional impairment trajectories in amyotrophic lateral sclerosis: a probabilistic, multifactorial model of disease progression

Objective

To employ Artificial Intelligence to model, predict and simulate the amyotrophic lateral sclerosis (ALS) progression over time in terms of variable interactions, functional impairments, and survival.

Methods

We employed demographic and clinical variables, including functional scores and the utilisation of support interventions, of 3940 ALS patients from four Italian and two Israeli registers to develop a new approach based on Dynamic Bayesian Networks (DBNs) that models the ALS evolution over time, in two distinct scenarios of variable availability. The method allows to simulate patients’ disease trajectories and predict the probability of functional impairment and survival at different time points.

Results

DBNs explicitly represent the relationships between the variables and the pathways along which they influence the disease progression. Several notable inter-dependencies were identified and validated by comparison with literature. Moreover, the implemented tool allows the assessment of the effect of different markers on the disease course, reproducing the probabilistically expected clinical progressions. The tool shows high concordance in terms of predicted and real prognosis, assessed as time to functional impairments and survival (integral of the AU-ROC in the first 36 months between 0.80–0.93 and 0.84–0.89 for the two scenarios, respectively).

Conclusions

Provided only with measurements commonly collected during the first visit, our models can predict time to the loss of independence in walking, breathing, swallowing, communicating, and survival and it can be used to generate in silico patient cohorts with specific characteristics. Our tool provides a comprehensive framework to support physicians in treatment planning and clinical decision-making.

Supplementary Information

The online version contains supplementary material available at 10.1007/s00415-022-11022-0.

Prognostic prediction by hypermetabolism varies depending on the nutritional status in early amyotrophic lateral sclerosis

To examine whether hypermetabolism could predict the prognosis of early amyotrophic lateral sclerosis (ALS) patients with differing nutritional profiles. This single-center, retrospective study examined the prognosis of ALS patients with hypermetabolism in relation to their nutritional status at hospitalization. The metabolic state was estimated by the ratio of measured resting energy expenditure (mREE) to lean soft tissue mass (LSTM) (mREE/LSTM), wherein patients with ratios ≥ 38 were defined as hypermetabolic. Malnutrition was defined as %ideal body weight < 0.9. Forty-eight patients were enrolled in this study. The hypermetabolic group had shorter survival in the normal-weight group but more prolonged survival in the malnutrition group. Multiplication of nutritional and metabolic factors, such as [(body mass index (BMI) − 19.8) × (mREE/LSTM − 38)], designated as BMI-muscle metabolism index (BMM index), successfully predicted the prognosis in the group with a high BMM index (≥ 1), which showed shorter survival and a faster rate of weight loss and functional decline. Multivariate analysis using the Cox model showed high BMM index was an independent poor prognostic factor (hazard ratio: 4.05; p = 0.025). Prognostic prediction by hypermetabolism varies depending on the nutritional status in ALS, and the BMM index is a consistent prognostic factor.

Challenging the Established Order: Innovating Clinical Trials for Amyotrophic Lateral Sclerosis

Development of effective treatments for amyotrophic lateral sclerosis (ALS) has been hampered by disease heterogeneity, a limited understanding of underlying pathophysiology, and methodologic design challenges. We have evaluated 2 major themes in the design of pivotal, phase 3 clinical trials for ALS—(1) patient selection and (2) analytical strategy—and discussed potential solutions with the European Medicines Agency. Several design considerations were assessed using data from 5 placebo-controlled clinical trials (n = 988), 4 population-based cohorts (n = 5,100), and 2,436 placebo-allocated patients from the Pooled Resource Open-Access ALS Clinical Trials (PRO-ACT) database. The validity of each proposed design modification was confirmed by means of simulation and illustrated for a hypothetical setting. Compared to classical trial design, the proposed design modifications reduce the sample size by 30.5% and placebo exposure time by 35.4%. By making use of prognostic survival models, one creates a potential to include a larger proportion of the population and maximize generalizability. We propose a flexible design framework that naturally adapts the trial duration when inaccurate assumptions are made at the design stage, such as enrollment or survival rate. In case of futility, the follow-up time is shortened and patient exposure to ineffective treatments or placebo is minimized. For diseases such as ALS, optimizing the use of resources, widening eligibility criteria, and minimizing exposure to futile treatments and placebo is critical to the development of effective treatments. Our proposed design modifications could circumvent important pitfalls and may serve as a blueprint for future clinical trials in this population.