Prognosis for patients with amyotrophic lateral sclerosis: development and validation of a personalised prediction model

ALS blood expression profiling identifies new biomarkers, patient subgroups, and evidence for neutrophilia and hypoxia

BACKGROUND

Amyotrophic lateral sclerosis (ALS) is a debilitating disease with few treatment options. Progress towards new therapies requires validated disease biomarkers, but there is no consensus on which fluid-based measures are most informative.

METHODS

This study analyzed microarray data derived from blood samples of patients with ALS (n = 396), ALS mimic diseases (n = 75), and healthy controls (n = 645). Goals were to provide in-depth analysis of differentially expressed genes (DEGs), characterize patient-to-patient heterogeneity, and identify candidate biomarkers.

RESULTS

We identified 752 ALS-increased and 764 ALS-decreased DEGs (FDR < 0.10 with > 10% expression change). Gene expression shifts in ALS blood broadly resembled acute high altitude stress responses. ALS-increased DEGs had high exosome expression, were neutrophil-specific, associated with translation, and overlapped significantly with genes near ALS susceptibility loci (e.g., IFRD1, TBK1, CREB5). ALS-decreased DEGs, in contrast, had low exosome expression, were erythroid lineage-specific, and associated with anemia and blood disorders. Genes encoding neurofilament proteins (NEFH, NEFL) had poor diagnostic accuracy (50-53%). However, support vector machines distinguished ALS patients from ALS mimics and controls with 87% accuracy (sensitivity: 86%, specificity: 87%). Expression profiles were heterogeneous among patients and we identified two subgroups: (i) patients with higher expression of IL6R and myeloid lineage-specific genes and (ii) patients with higher expression of IL23A and lymphoid-specific genes. The gene encoding copper chaperone for superoxide dismutase (CCS) was most strongly associated with survival (HR = 0.77; P = 1.84e-05) and other survival-associated genes were linked to mitochondrial respiration. We identify a 61 gene signature that significantly improves survival prediction when added to Cox proportional hazard models with baseline clinical data (i.e., age at onset, site of onset and sex). Predicted median survival differed 2-fold between patients with favorable and risk-associated gene expression signatures.

CONCLUSIONS

Peripheral blood analysis informs our understanding of ALS disease mechanisms and genetic association signals. Our findings are consistent with low-grade neutrophilia and hypoxia as ALS phenotypes, with heterogeneity among patients partly driven by differences in myeloid and lymphoid cell abundance. Biomarkers identified in this study require further validation but may provide new tools for research and clinical practice.

Survival prediction models in motor neuron disease

BACKGROUND AND PURPOSE

This study aimed to assess the predictive value of multimodal brain magnetic resonance imaging (MRI) on survival in a large cohort of patients with motor neuron disease (MND), in combination with clinical and cognitive features.

METHODS

Two hundred MND patients were followed up prospectively for a median of 4.13 years. At baseline, subjects underwent neurological examination, cognitive assessment and brain MRI. Grey matter volumes of cortical and subcortical structures and diffusion tensor MRI metrics of white matter tracts were obtained. A multivariable Royston-Parmar survival model was created using clinical and cognitive variables. The increase of survival prediction accuracy provided by MRI variables was assessed.

RESULTS

The multivariable clinical model included predominant upper or lower motor neuron presentations and diagnostic delay as significant prognostic predictors, reaching an area under the receiver operating characteristic curve (AUC) of a 4-year survival prediction of 0.79. The combined clinical and MRI model including selected grey matter fronto-temporal volumes and diffusion tensor MRI metrics of the corticospinal and extra-motor tracts reached an AUC of 0.89. Considering amyotrophic lateral sclerosis patients only, the clinical model including diagnostic delay and semantic fluency scores provided an AUC of 0.62, whereas the combined clinical and MRI model reached an AUC of 0.77.

CONCLUSION

Our study demonstrated that brain MRI measures of motor and extra-motor structural damage, when combined with clinical and cognitive features, are useful predictors of survival in patients with MND, particularly when a diagnosis of amyotrophic lateral sclerosis is made.

Development of a prognostic model of respiratory insufficiency or death in amyotrophic lateral sclerosis

A clinically useful model to prognose onset of respiratory insufficiency in amyotrophic lateral sclerosis (ALS) would inform disease interventions, communication and clinical trial design. We aimed to derive and validate a clinical prognostic model for respiratory insufficiency within 6 months of presentation to an outpatient ALS clinic.We used multivariable logistic regression and internal cross-validation to derive a clinical prognostic model using a single-centre cohort of 765 ALS patients who presented between 2006 and 2015. External validation was performed using the multicentre Pooled Resource Open-Access ALS Clinical Trials (PRO-ACT) database with 7083 ALS patients. Predictors included baseline characteristics at first outpatient visit. The primary outcome was respiratory insufficiency within 6 months, defined by initiation of noninvasive ventilation, forced vital capacity (FVC) <50% predicted, tracheostomy, or death.Of 765 patients in our centre, 300 (39%) had respiratory insufficiency or death within 6 months. Six baseline characteristics (diagnosis age, delay between symptom onset and diagnosis, FVC, symptom onset site, amyotrophic lateral sclerosis functional rating scale-revised (ALSFRS-R) total score and ALSFRS-R dyspnoea score) were used to prognose the risk of the primary outcome. The derivation cohort c-statistic was 0.86 (95% CI 0.84-0.89) and internal cross-validation produced a c-statistic of 0.86 (95% CI 0.85-0.87). External validation of the model using the PRO-ACT cohort produced a c-statistic of 0.74 (95% CI 0.72-0.75).We derived and externally validated a clinical prognostic rule for respiratory insufficiency in ALS. Future studies should investigate interventions on equivalent high-risk patients.

Spinal Cord Imaging in Amyotrophic Lateral Sclerosis: Historical Concepts-Novel Techniques

Amyotrophic lateral sclerosis (ALS) is the most common adult onset motor neuron disease with no effective disease modifying therapies at present. Spinal cord degeneration is a hallmark feature of ALS, highlighted in the earliest descriptions of the disease by Lockhart Clarke and Jean-Martin Charcot. The anterior horns and corticospinal tracts are invariably affected in ALS, but up to recently it has been notoriously challenging to detect and characterize spinal pathology in vivo. With recent technological advances, spinal imaging now offers unique opportunities to appraise lower motor neuron degeneration, sensory involvement, metabolic alterations, and interneuron pathology in ALS. Quantitative spinal imaging in ALS has now been used in cross-sectional and longitudinal study designs, applied to presymptomatic mutation carriers, and utilized in machine learning applications. Despite its enormous clinical and academic potential, a number of physiological, technological, and methodological challenges limit the routine use of computational spinal imaging in ALS. In this review, we provide a comprehensive overview of emerging spinal cord imaging methods and discuss their advantages, drawbacks, and biomarker potential in clinical applications, clinical trial settings, monitoring, and prognostic roles.

Tracking a Fast-Moving Disease: Longitudinal Markers, Monitoring, and Clinical Trial Endpoints in ALS

Amyotrophic lateral sclerosis (ALS) encompasses a heterogeneous group of phenotypes with different progression rates, varying degree of extra-motor involvement and divergent progression patterns. The natural history of ALS is increasingly evaluated by large, multi-time point longitudinal studies, many of which now incorporate presymptomatic and post-mortem assessments. These studies not only have the potential to characterize patterns of anatomical propagation, molecular mechanisms of disease spread, but also to identify pragmatic monitoring markers. Sensitive markers of progressive neurodegenerative change are indispensable for clinical trials and individualized patient care. Biofluid markers, neuroimaging indices, electrophysiological markers, rating scales, questionnaires, and other disease-specific instruments have divergent sensitivity profiles. The discussion of candidate monitoring markers in ALS has a dual academic and clinical relevance, and is particularly timely given the increasing number of pharmacological trials. The objective of this paper is to provide a comprehensive and critical review of longitudinal studies in ALS, focusing on the sensitivity profile of established and emerging monitoring markers.

Revised Airlie House consensus guidelines for design and implementation of ALS clinical trials

OBJECTIVE

To revise the 1999 Airlie House consensus guidelines for the design and implementation of preclinical therapeutic studies and clinical trials in amyotrophic lateral sclerosis (ALS).

METHODS

A consensus committee comprising 140 key members of the international ALS community (ALS researchers, clinicians, patient representatives, research funding representatives, industry, and regulatory agencies) addressed 9 areas of need within ALS research: (1) preclinical studies; (2) biological and phenotypic heterogeneity; (3) outcome measures; (4) disease-modifying and symptomatic interventions; (5) recruitment and retention; (6) biomarkers; (7) clinical trial phases; (8) beyond traditional trial designs; and (9) statistical considerations. Assigned to 1 of 8 sections, committee members generated a draft set of guidelines based on a "background" of developing a (pre)clinical question and a "rationale" outlining the evidence and expert opinion. Following a 2-day, face-to-face workshop at the Airlie House Conference Center, a modified Delphi process was used to develop draft consensus research guidelines, which were subsequently reviewed and modified based on comments from the public. Statistical experts drafted a separate document of statistical considerations (section 9).

RESULTS

In this report, we summarize 112 guidelines and their associated backgrounds and rationales. The full list of guidelines, the statistical considerations, and a glossary of terms can be found in data available from Dryad (appendices e-3-e-5, doi.org/10.5061/dryad.32q9q5d). The authors prioritized 15 guidelines with the greatest potential to improve ALS clinical research.

CONCLUSION

The revised Airlie House ALS Clinical Trials Consensus Guidelines should serve to improve clinical trial design and accelerate the development of effective treatments for patients with ALS.

Machine Learning in Amyotrophic Lateral Sclerosis: Achievements, Pitfalls, and Future Directions

Background: Amyotrophic Lateral Sclerosis (ALS) is a relentlessly progressive neurodegenerative condition with limited therapeutic options at present. Survival from symptom onset ranges from 3 to 5 years depending on genetic, demographic, and phenotypic factors. Despite tireless research efforts, the core etiology of the disease remains elusive and drug development efforts are confounded by the lack of accurate monitoring markers. Disease heterogeneity, late-stage recruitment into pharmaceutical trials, and inclusion of phenotypically admixed patient cohorts are some of the key barriers to successful clinical trials. Machine Learning (ML) models and large international data sets offer unprecedented opportunities to appraise candidate diagnostic, monitoring, and prognostic markers. Accurate patient stratification into well-defined prognostic categories is another aspiration of emerging classification and staging systems. Methods: The objective of this paper is the comprehensive, systematic, and critical review of ML initiatives in ALS to date and their potential in research, clinical, and pharmacological applications. The focus of this review is to provide a dual, clinical-mathematical perspective on recent advances and future directions of the field. Another objective of the paper is the frank discussion of the pitfalls and drawbacks of specific models, highlighting the shortcomings of existing studies and to provide methodological recommendations for future study designs. Results: Despite considerable sample size limitations, ML techniques have already been successfully applied to ALS data sets and a number of promising diagnosis models have been proposed. Prognostic models have been tested using core clinical variables, biological, and neuroimaging data. These models also offer patient stratification opportunities for future clinical trials. Despite the enormous potential of ML in ALS research, statistical assumptions are often violated, the choice of specific statistical models is seldom justified, and the constraints of ML models are rarely enunciated. Conclusions: From a mathematical perspective, the main barrier to the development of validated diagnostic, prognostic, and monitoring indicators stem from limited sample sizes. The combination of multiple clinical, biofluid, and imaging biomarkers is likely to increase the accuracy of mathematical modeling and contribute to optimized clinical trial designs.

A ferroptosis-based panel of prognostic biomarkers for Amyotrophic Lateral Sclerosis

Accurate patient stratification into prognostic categories and targeting Amyotrophic Lateral Sclerosis (ALS)-associated pathways may pave the way for promising trials. We evaluated blood-based prognostic indicators using an array of pathological markers. Plasma samples were collected as part of a large, phase III clinical trial (Mitotarget/TRO19622) at months 1, 6, 12 and 18. The ALSFRS-r score was used as a proxy of disease progression to assess the predictive value of candidate biological indicators. First, established clinical predictors were evaluated in all 512 patients. Subsequently, pathologic markers, such as proxies of neuronal integrity (Neurofilament light chain and phosphorylated heavy chain), DNA oxidation (8-oxo-2'-desoxyguanosine), lipid peroxidation (4-hydroxy-2-nonenal, isoprostane), inflammation (interleukin-6) and iron status (ferritin, hepcidin, transferrin) were assessed in a subset of 109 patients that represented the whole cohort. Markers of neuronal integrity, DNA and lipid oxidation, as well as iron status at baseline are accurate predictors of disability at 18-month follow-up. The composite scores of these markers in association with established clinical predictors enable the accurate forecasting of functional decline. The identified four biomarkers are all closely associated with 'ferroptosis', a recently discovered form of programmed cell death with promising therapeutic targets. The predictive potential of these pathophysiology-based indicators may offer superior patient stratification for future trials, individualised patient care and resource allocation.

Aerobic Exercise Therapy in Ambulatory Patients With ALS: A Randomized Controlled Trial

Background: Weakness caused by motor neuron degeneration in amyotrophic lateral sclerosis (ALS) may result in avoidance of physical activity, resulting in deconditioning and reduced health-related quality of life (HRQoL). Objective: To study the effectiveness of aerobic exercise therapy (AET) on disease-specific and generic HRQoL in ambulatory patients with ALS. Methods: We conducted a multicenter, assessor-blinded, randomized controlled trial. Using a biphasic randomization model, ambulatory ALS patients were assigned (1:1) to AET+usual care (UC), or UC. AET consisted of a 16-week aerobic cycling exercise program. Primary outcome measures were the 40-item ALS assessment questionnaire (ALSAQ-40), and the mental component summary (MCS) and physical component summary (PCS) scores of the short-form survey (SF-36), using linear mixed effects models. Per-protocol (PP) analysis was performed for those patients who attended ≥75% of the training sessions; controls were matched (1:1) by propensity score matching. Results: Of 325 screened patients, 57 were randomized: 27 to AET+UC and 30 to UC. No significant mean slope differences between groups were observed for ALSAQ-40 (-1.07; 95% confidence interval [CI] -2.6 to 0.5, P=0.172) nor for SF-36 MCS (0.24; -0.7 to 1.1, P=0.576) or PCS (-0.51; -1.4 to 0.38, P=0.263). There were no adverse events related to the AET. PP-analyses showed significantly less deterioration in ALSAQ-40 (-1.88, -3.8 to 0.0, P=0.046) in AET+UC compared to UC. Conclusions: AET+UC was not superior to UC alone in preserving HRQoL in ambulatory ALS patient. However, the study was unfortunately underpowered, because only 10 patients completed the protocol. AET+UC may preserve disease-specific HRQoL in slow progressors. Clinical trial registration number: Netherlands National Trial Register (NTR): 1616.

Refining eligibility criteria for amyotrophic lateral sclerosis clinical trials

OBJECTIVE

To assess the effect of eligibility criteria on exclusion rates, generalizability, and outcome heterogeneity in amyotrophic lateral sclerosis (ALS) clinical trials and to assess the value of a risk-based inclusion criterion.

METHODS

A literature search was performed to summarize the eligibility criteria of clinical trials. The extracted criteria were applied to an incidence cohort of 2,904 consecutive patients with ALS to quantify their effects on generalizability and outcome heterogeneity. We evaluated the effect of a risk-based selection approach on trial design using a personalized survival prediction model.

RESULTS

We identified 38 trials. A large variability exists between trials in all patient characteristics for enrolled patients (p < 0.001), except for the proportion of men (p = 0.21). Exclusion rates varied widely (from 14% to 95%; mean 59.8%; 95% confidence interval 52.6%-66.7%). Stratification of the eligible populations into prognostic subgroups showed that eligibility criteria lead to exclusion of patients in all prognostic groups. Eligibility criteria neither reduce heterogeneity in survival time (from 22.0 to 20.5 months, p = 0.09) nor affect between-patient variability in functional decline (from 0.62 to 0.65, p = 0.25). In none of the 38 trials were the eligibility criteria found to be more efficient than the prediction model in optimizing sample size and eligibility rate.

CONCLUSIONS

The majority of patients with ALS are excluded from trial participation, which questions the generalizability of trial results. Eligibility criteria only minimally improve homogeneity in trial endpoints. An individualized risk-based criterion could be used to balance the gains in trial design and loss in generalizability.

Predictors of diagnostic delay in amyotrophic lateral sclerosis: a cohort study based on administrative and electronic medical records data

Objectives: To characterize the timing and pathway of amyotrophic lateral sclerosis (ALS) diagnosis and to identify predictors of delayed diagnosis in a retrospective cohort. Methods: The cohort included all patients with incident ALS between 2010 and 2014 in Friuli-Venezia Giulia (FVG) region, Italy, admitted to two University Hospitals. Information on demographics, clinical presentation, and healthcare use was obtained from health databases and electronic medical records (EMRs). Total diagnostic time (TDT), the interval between ALS symptoms onset and diagnosis, was compared between patient groups through Wilcoxon-Mann-Whitney test. The adjusted odds ratio (aOR), with 95% confidence interval (95% CI), of having a TDT ≥12 months was estimated using unconditional logistic regression. Results: Among 134 patients, median TDT (interquartile range [IQR]) was 11.5 months (7.1-18.3), shorter in those aged <60 years vs. ≥60 years (8.1; 5.1-11.1 vs. 12.4; 7.4-21.5; p = 0.0064), first referred to a neurologist vs. other specialist (10.2; 6.1-16.3 vs. 13.2; 8.1-24.5; p = 0.0386) and without neurologic comorbidities (11.1; 7.1-16.5 vs. 19.7; 8.8-33.7; p = 0.0243). TDT was ≥12 months in 64 (48.5%) patients and was predicted by male sex (aOR: 2.47; 95% CI: 1.06-5.75), age at onset ≥60 years (11.46; 3.13-41.9), spinal onset (2.04; 1.00-5.93), and prior therapies or first referral to a non-neurologist (3.15; 1.36-7.29). Conclusions: In this cohort, delayed diagnosis was common, particularly in older patients and in those with neurological comorbidities. Timely referral to a neurologist may improve diagnostic timing.

Diagnostic and Prognostic Performance of Neurofilaments in ALS

There is a need for biomarkers for amyotrophic lateral sclerosis (ALS), to support the diagnosis of the disease, to predict disease progression and to track disease activity and treatment responses. Over the last decade multiple studies have investigated the potential of neurofilament levels, both in cerebrospinal fluid and blood, as biomarker for ALS. The most widely studied neurofilament subunits are neurofilament light chain (NfL) and phosphorylated neurofilament heavy chain (pNfH). Neurofilament levels are reflecting neuronal injury and therefore potentially of value in ALS and other neurological disorders. In this mini-review, we summarize and discuss the available evidence about neurofilaments as diagnostic and prognostic biomarker for human ALS.

Personalized Medicine and Molecular Interaction Networks in Amyotrophic Lateral Sclerosis (ALS): Current Knowledge

Multiple genes and mechanisms of pathophysiology have been implicated in amyotrophic lateral sclerosis (ALS), suggesting it is a complex systemic disease. With this in mind, applying personalized medicine (PM) approaches to tailor treatment pipelines for ALS patients may be necessary. The modelling and analysis of molecular interaction networks could represent valuable resources in defining ALS-associated pathways and discovering novel therapeutic targets. Here we review existing omics datasets and analytical approaches, in order to consider how molecular interaction networks could improve our understanding of the molecular pathophysiology of this fatal neuromuscular disorder.

Biomarker Supervised G-CSF (Filgrastim) Response in ALS Patients

Objective: To evaluate safety, tolerability and feasibility of long-term treatment with Granulocyte-colony stimulating factor (G-CSF), a well-known hematopoietic stem cell factor, guided by assessment of mobilized bone marrow derived stem cells and cytokines in the serum of patients with amyotrophic lateral sclerosis (ALS) treated on a named patient basis.

Methods: 36 ALS patients were treated with subcutaneous injections of G-CSF on a named patient basis and in an outpatient setting. Drug was dosed by individual application schemes (mean 464 Mio IU/month, range 90-2160 Mio IU/month) over a median of 13.7 months (range from 2.7 to 73.8 months). Safety, tolerability, survival and change in ALSFRS-R were observed. Hematopoietic stem cells were monitored by flow cytometry analysis of circulating CD34⁺ and CD34⁺CD38⁻ cells, and peripheral cytokines were assessed by electrochemoluminescence throughout the intervention period. Analysis of immunological and hematological markers was conducted.

Results: Long term and individually adapted treatment with G-CSF was well tolerated and safe. G-CSF led to a significant mobilization of hematopoietic stem cells into the peripheral blood. Higher mobilization capacity was associated with prolonged survival. Initial levels of serum cytokines, such as MDC, TNF-beta, IL-7, IL-16, and Tie-2 were significantly associated with survival. Continued application of G-CSF led to persistent alterations in serum cytokines and ongoing measurements revealed the multifaceted effects of G-CSF.

Conclusions: G-CSF treatment is feasible and safe for ALS patients. It may exert its beneficial effects through neuroprotective and -regenerative activities, mobilization of hematopoietic stem cells and regulation of pro- and anti-inflammatory cytokines as well as angiogenic factors. These cytokines may serve as prognostic markers when measured at the time of diagnosis. Hematopoietic stem cell numbers and cytokine levels are altered by ongoing G-CSF application and may potentially serve as treatment biomarkers for early monitoring of G-CSF treatment efficacy in ALS in future clinical trials.

Riluzole and edaravone: A tale of two amyotrophic lateral sclerosis drugs

Over the past decades, a multitude of experimental drugs have been shown to delay disease progression in preclinical animal models of amyotrophic lateral sclerosis (ALS) but failed to show efficacy in human clinical trials or are still waiting for approval under Phase I-III trials. Riluzole, a glutamatergic neurotransmission inhibitor, is the only drug approved by the USA Food and Drug Administration for ALS treatment with modest benefits on survival. Recently, an antioxidant drug, edaravone, developed by Mitsubishi Tanabe Pharma was found to be effective in halting ALS progression during early stages. The newly approved drug edaravone is a force multiplier for ALS treatment. This short report provides an overview of the two drugs that have been approved for ALS treatment and highlights an update on the timeline of drug development, how clinical trials were done, the outcome of these trials, primary endpoint, mechanism of actions, dosing information, administration, side effects, and storage procedures. Moreover, we also discussed the pressing issues and challenges of ALS clinical trials and drug developments as well as future outlook.

Serum neurofilament light chain levels as a marker of upper motor neuron degeneration in patients with Amyotrophic Lateral Sclerosis

AIMS

Amyotrophic lateral sclerosis (ALS) is the most common motor neuron degeneration disease with a diagnostic delay of about 1 year after symptoms onset. In ALS, blood neurofilament light chain (NfL) levels are elevated, but it is not entirely clear what drives this increase and what the diagnostic performance of serum NfL is in terms of predictive values and likelihood ratios. The aims of this study were to further explore the prognostic and diagnostic performances of serum NfL to discriminate between patients with ALS and ALS mimics, and to investigate the relationship between serum NfL with motor neuron degeneration.

METHODS

The diagnostic performances of serum NfL were based on a cohort of 149 serum samples of patients with ALS, 19 serum samples of patients with a disease mimicking ALS and 82 serum samples of disease control patients. The serum NfL levels were correlated with the number of regions (thoracic, bulbar, upper limb and lower limb) displaying upper and/or lower motor neuron degeneration. The prognostic performances of serum NfL were investigated based on a Cox regression analysis.

RESULTS

The associated predictive values and likelihood ratio to discriminate patients with ALS and ALS mimics were established. Serum NfL was associated with motor neuron degeneration driven by upper motor neuron (UMN) degeneration and was independently associated with survival in patients with ALS.

CONCLUSIONS

Altogether, these findings suggest that elevated serum NfL levels in ALS are driven by UMN degeneration and the disease progression rate and are independently associated with survival at time of diagnosis.

Deconstructing progression of amyotrophic lateral sclerosis in stages: a Markov modeling approach

OBJECTIVES

Propose an empirical amyotrophic lateral sclerosis (ALS) staging approach called Fine'til 9 (FT9) based on how many of the patient's ALS functional rating scale (ALSFRS-R) subscores are 9 or less (of normal 12). Gain insights into progression of ALS by applying Markov models to ALS stages by multiple systems (King's, Milan-Torino system (MITOS) and FT9).

METHODS

Patients from the Pooled Resource Open-Access ALS Clinical Trials (PRO-ACT) dataset were staged using ALSFRS-R responses. Risks of progression through stages and death were estimated, as were effects of prognostic variables on these risks.

RESULTS

A total of 29,947 time points in 3199 patients from the PRO-ACT dataset were assigned stages. Although the three systems were moderately correlated, MITOS stages were heavily skewed toward advanced disease, whereas King's and FT9 stages were more balanced. Non-sequential progression was observed with King's system. Markov models adequately described transitions from stage to stage in the first year of observation, but underestimated risks beyond that point. Regardless of staging method, initial rate of ALSFRS-R decline had a powerful effect on rate of progression through sequential stages, whereas age predominantly influenced stage-specific mortality.

CONCLUSION

King's and FT9 are more sensitive to observed progression of disease in clinical trials than MITOS. FT9 can partition the course similar to King's, and may have advantages of sequential progression and easy applicability to retrospective data. Markov transition intensity estimates may be of value for counseling, health economic studies, and research design. In particular, this framework permits estimation of multidimensional effects of variables (including treatment) on outcome.

Unraveling the Complexity of Amyotrophic Lateral Sclerosis Survival Prediction

Objective: The heterogeneity of amyotrophic lateral sclerosis (ALS) survival duration, which varies from <1 year to >10 years, challenges clinical decisions and trials. Utilizing data from 801 deceased ALS patients, we: (1) assess the underlying complex relationships among common clinical ALS metrics; (2) identify which clinical ALS metrics are the "best" survival predictors and how their predictive ability changes as a function of disease progression. Methods: Analyses included examination of relationships within the raw data as well as the construction of interactive survival regression and classification models (generalized linear model and random forests model). Dimensionality reduction and feature clustering enabled decomposition of clinical variable contributions. Thirty-eight metrics were utilized, including Medical Research Council (MRC) muscle scores; respiratory function, including forced vital capacity (FVC) and FVC % predicted, oxygen saturation, negative inspiratory force (NIF); the Revised ALS Functional Rating Scale (ALSFRS-R) and its activities of daily living (ADL) and respiratory sub-scores; body weight; onset type, onset age, gender, and height. Prognostic random forest models confirm the dominance of patient age-related parameters decline in classifying survival at thresholds of 30, 60, 90, and 180 days and 1, 2, 3, 4, and 5 years. Results: Collective prognostic insight derived from the overall investigation includes: multi-dimensionality of ALSFRS-R scores suggests cautious usage for survival forecasting; upper and lower extremities independently degenerate and are autonomous from respiratory decline, with the latter associating with nearer-to-death classifications; height and weight-based metrics are auxiliary predictors for farther-from-death classifications; sex and onset site (limb, bulbar) are not independent survival predictors due to age co-correlation. Conclusion: The dimensionality and fluctuating predictors of ALS survival must be considered when developing predictive models for clinical trial development or in-clinic usage. Additional independent metrics and possible revisions to current metrics, like the ALSFRS-R, are needed to capture the underlying complexity needed for population and personalized forecasting of survival.