RandomForest4Life: A Random Forest for predicting ALS disease progression

Hothorn, Torsten; Jung, Hans H.

doi:10.3109/21678421.2014.893361

Cited by 57 publications

(57 citation statements)

References 24 publications

(31 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Team 3 (ref. 15) won a third place prize of $10,000. As in previous installments of the DREAM challenges 16 , the aggregation of predictions across teams 1 and 2 further reduced the prediction error.…”

Section: Methods Performance and Assessmentmentioning

confidence: 99%

Crowdsourced analysis of clinical trial data to predict amyotrophic lateral sclerosis progression

et al. 2014

Self Cite

View full text Add to dashboard Cite

Amyotrophic lateral sclerosis (ALS) is a fatal neurodegenerative disease with substantial heterogeneity in its clinical presentation. This makes diagnosis and effective treatment difficult, so better tools for estimating disease progression are needed. Here, we report results from the DREAM-Phil Bowen ALS Prediction Prize4Life challenge. In this crowdsourcing competition, competitors developed algorithms for the prediction of disease progression of 1,822 ALS patients from standardized, anonymized phase 2/3 clinical trials. The two best algorithms outperformed a method designed by the challenge organizers as well as predictions by ALS clinicians. We estimate that using both winning algorithms in future trial designs could reduce the required number of patients by at least 20%. The DREAM-Phil Bowen ALS Prediction Prize4Life challenge also identified several potential nonstandard predictors of disease progression including uric acid, creatinine and surprisingly, blood pressure, shedding light on ALS pathobiology. This analysis reveals the potential of a crowdsourcing competition that uses clinical trial data for accelerating ALS research and development

show abstract

Section: Methods Performance and Assessmentmentioning

confidence: 99%

Crowdsourced analysis of clinical trial data to predict amyotrophic lateral sclerosis progression

et al. 2014

Self Cite

View full text Add to dashboard Cite

show abstract

“…The same conclusion can be drawn from the observation that diagnostic delay is a strong prognostic factor, since the implication is that the progression slope until diagnosis is similar to the slope after diagnosis. However, it has been noted in various studies that the ALSFrS-r progression rate can decrease, and sometimes even show a change in the positive direction between follow-up visits (33)(34)(35)(36)(37)(38). A study examining the relationship between spread and prognosis (10) showed that involvement of two regions within three months of onset -defined as the 'rapid-spread type' -was associated with a poor prognosis.…”

Section: Discussionmentioning

confidence: 98%

Regionality of disease progression predicts prognosis in amyotrophic lateral sclerosis

Kleij

Jones

Steen

et al. 2015

Amyotrophic Lateral Sclerosis and Frontotemporal Degeneration

View full text Add to dashboard Cite

Amyotrophic lateral sclerosis (ALS) is a devastating neurological syndrome in which motor neurons degenerate relentlessly. Although the site of onset and the rate of spread have been studied extensively, little is known about whether focal as opposed to diffuse disease affects prognosis. We therefore tested the hypothesis that regionality of disease burden is a prognostic factor in ALS. We analysed clinical data from two large multicentre, longitudinal trials. Regionality was defined as the difference in progression rates in three domains as measured by the revised ALS Functional Rating Scale, omitting the respiratory domain from analysis. We used death by trial end as the outcome variable and tested this by logistic regression against predictor variables including regionality and overall rate of disease progression. There were 561 patients. Regionality of disease was independently associated with significantly higher chance of death by study end (odds ratio most diffuse against most focal category 0.354 (0.191, 0.657), p = 0.001), with a direct relationship between degree of regionality and odds of death. We have shown using clinical trial data that focal disease is associated with a worse prognosis in ALS. Measures of regionality warrant further independent consideration in the development of future prognostic models.

show abstract

“…The effect of the dominant variable on the change of a patient's functional status, namely, the time between disease onset and treatment start, seems to be primarily prognostic according to the original MOB, whereas the predictive effect of calcium has been obscured by the prognostic effects and only becomes apparent with the application of the predMOB. However, the PRO‐ACT data base is a mixture of diverse trials and the membership of a patient to the respective study is not traceable . Hence, the meaningfulness and generalizability of the results are debatable.…”

Section: Discussionmentioning

confidence: 99%

Exploratory identification of predictive biomarkers in randomized trials with normal endpoints

Krzykalla

Benner

Kopp‐Schneider

2019

Statistics in Medicine

View full text Add to dashboard Cite

One of the main endeavours in present‐day medicine, especially in oncological research, is to provide evidence for individual treatment decisions (“stratified medicine”). In the pursuit of optimal treatment decision rules, the identification of predictive biomarkers that modify the treatment effect is essential. Proposed methods have often been based on recursive partitioning since a wide variety of interaction patterns can be captured automatically and the results are easily interpretable. Furthermore, these methods are readily extendable to high‐dimensional settings by means of ensemble learning. In this article, we present predMOB, an adaptation of the model‐based recursive partitioning (MOB) for subgroup analysis approach specifically tailored to the identification of predictive factors. In a simulation study, predMOB outperforms the original MOB with respect to the number of false detections and shows to be more robust in moderately complex settings. Furthermore, we compare the results of predMOB for the application to a public data base of amyotrophic lateral sclerosis patients to those obtained from the original MOB and are able to elucidate the nature of the biomarkers' effects.

show abstract

RandomForest4Life: A Random Forest for predicting ALS disease progression

Cited by 57 publications

References 24 publications

Crowdsourced analysis of clinical trial data to predict amyotrophic lateral sclerosis progression

Crowdsourced analysis of clinical trial data to predict amyotrophic lateral sclerosis progression

Regionality of disease progression predicts prognosis in amyotrophic lateral sclerosis

Exploratory identification of predictive biomarkers in randomized trials with normal endpoints

Contact Info

Product

Resources

About