A novel method predicting clinical response using only background clinical data in RA patients before treatment with infliximab

Miyoshi, Fumito; Honne, Kyoko; Minota, Seiji; Okada, Masato; Ogawa, Noriyoshi; Mimura, Toshihide

doi:10.3109/14397595.2016.1168536

Cited by 19 publications

(10 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Disease progression and outcome was a focus for 27 studies. Other considered issues were disease severity [72][73][74][75][76][77][78] in psoriasis, RA, IBD and coeliac disease; treatment response [79][80][81][82][83][84][85][86][87] in IBD, RA and primary biliary cirrhosis (PBC); and survival prediction [88][89][90] in PBC, RA and SLE. Other models focused on improved image segmentation to aid prognoses [91][92][93][94][95][96] for IBD and MS. Disease progression and outcome was the second-most prevalent area for model development.…”

Section: Disease Progression and Outcomementioning

confidence: 99%

A systematic review of the applications of artificial intelligence and machine learning in autoimmune diseases

et al. 2020

View full text Add to dashboard Cite

Autoimmune diseases are chronic, multifactorial conditions. Through machine learning (ML), a branch of the wider field of artificial intelligence, it is possible to extract patterns within patient data, and exploit these patterns to predict patient outcomes for improved clinical management. Here, we surveyed the use of ML methods to address clinical problems in autoimmune disease. A systematic review was conducted using MEDLINE, embase and computers and applied sciences complete databases. Relevant papers included "machine learning" or "artificial intelligence" and the autoimmune diseases search term(s) in their title, abstract or key words. Exclusion criteria: studies not written in English, no real human patient data included, publication prior to 2001, studies that were not peer reviewed, non-autoimmune disease comorbidity research and review papers. 169 (of 702) studies met the criteria for inclusion. Support vector machines and random forests were the most popular ML methods used. ML models using data on multiple sclerosis, rheumatoid arthritis and inflammatory bowel disease were most common. A small proportion of studies (7.7% or 13/169) combined different data types in the modelling process. Cross-validation, combined with a separate testing set for more robust model evaluation occurred in 8.3% of papers (14/169). The field may benefit from adopting a best practice of validation, cross-validation and independent testing of ML models. Many models achieved good predictive results in simple scenarios (e.g. classification of cases and controls). Progression to more complex predictive models may be achievable in future through integration of multiple data types.

show abstract

Section: Disease Progression and Outcomementioning

confidence: 99%

A systematic review of the applications of artificial intelligence and machine learning in autoimmune diseases

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Machine learning approaches have also been employed to generate treatment response algorithms. Miyoshi et al, (2016) reported that infliximab response could be predicted by using the 9 variables ESR, TJC, albumin, monocyte count, red blood cell number, prednisolone dose, methotrexate dose, HbA1c, and previous biologic exposure with 92 % accuracy [21]. However, these results were not confirmed in other anti-TNF cohorts and infliximab is rarely used in the UK because it has to be given intravenously compared to the subcutaneous route of other anti-TNFs.…”

Section: Clinical and Demographic Predictors Of Responsementioning

confidence: 99%

Using the Immunophenotype to Predict Response to Biologic Drugs in Rheumatoid Arthritis

Mulhearn

Barton

2019

Preprint

View full text Add to dashboard Cite

Tumour necrosis factor-α is a key mediator of inflammation in rheumatoid arthritis its discovery led to the development of highly successful anti-TNF therapy. Subsequently, other biologic drugs targeting immune pathways, namely interleukin-6 blockade, B cell depletion, and T cell co-stimulation blockade, have been developed. Not all patients respond to a biologic drug leading to a knowledge gap between biologic therapies available and the confident prediction of response. So far, genetic studies have failed to uncover clinically informative biomarkers to predict response. Given that the targets of biologics are immune pathways, immunological study has become all the more pertinent. Furthermore, advances in single cell technology have enabled the characterisation of many leucocyte subsets. Studying the blood immunophenotype may therefore define biomarker profiles relevant to each individual patient’s disease and treatment outcome. This review summarises our current understanding of how immune biomarkers might be able to predict treatment response to biologic drugs.

show abstract

“…Man kann bei diesen Funktionen dabei aber nicht von einer Therapieempfehlung und im strengeren Sinne auch nicht von einer personalisierten Behandlung sprechen, da allgemeingültige Regeln angewendet werden. Bereits 2016 erreichte ein neuronales Netzwerk zur Vorhersage auf das Ansprechen auf Infliximab eine Accuracy von 92 % mit nur 9 klinischen Variablen [24]. Auch die Entscheidung zur Infliximab-Dosiseskalation konnte durch maschinelles Lernen effizient klassifiziert und damit vorhergesagt werden [25].…”

Section: Automatisierte Klinische Entscheidungssysteme In Der Rheumatologieunclassified

Künstliche Intelligenz-unterstützte Behandlung in der Rheumatologie

Hügle

Kalweit

2021

Z Rheumatol

View full text Add to dashboard Cite

ZusammenfassungComputergesteuerte klinische Entscheidungssysteme finden seit Längerem Einzug in die Praxis. Deren primäre Ziele sind die Verbesserung der Behandlungsqualität, Zeitersparnis oder Fehlervermeidung. Meist handelt es sich um regelbasierte Algorithmen, die in elektronische Patientenakten integriert werden, z. B. um Medikamenteninteraktionen zu erkennen. Durch künstliche Intelligenz (KI) können klinische Entscheidungssysteme disruptiv weiterentwickelt werden. Aus Daten wird durch maschinelles Lernen konstant neues Wissen geschaffen, um individuelle Krankheitsverläufe bei Patienten vorherzusagen, Probleme schneller zu erkennen, Phänotypen zu identifizieren oder die Therapieentscheidung zu unterstützen. Solche Algorithmen für rheumatologische Erkrankungen gibt es bereits. Am weitesten fortgeschritten hierbei sind die automatisierte Bilderkennung sowie Vorhersagen zum Krankheitsverlauf bei der rheumatoiden Arthritis. Von nutzerfreundlichen, durch Schnittstellen vernetzten KI-Entscheidungssystemen kann aber noch nicht gesprochen werden. Zudem sind die Algorithmen oft noch nicht genügend validiert und reproduzierbar. Anstatt die KI-unterstützte Wahl der Behandlung dem Arzt oder der Ärztin vorzugeben, wird KI eher als hybride Entscheidungsunterstützung dienen – immer unter Einbezug sowohl des Experten als auch des Patienten. Es gibt zudem ein großes Bedürfnis nach Sicherheit durch nachvollziehbare und auditierbare Algorithmen, um die Qualität und Transparenz von KI-unterstützten Therapieempfehlungen nachhaltig zu gewährleisten.

show abstract

A novel method predicting clinical response using only background clinical data in RA patients before treatment with infliximab

Cited by 19 publications

References 19 publications

A systematic review of the applications of artificial intelligence and machine learning in autoimmune diseases

A systematic review of the applications of artificial intelligence and machine learning in autoimmune diseases

Using the Immunophenotype to Predict Response to Biologic Drugs in Rheumatoid Arthritis

Künstliche Intelligenz-unterstützte Behandlung in der Rheumatologie

Contact Info

Product

Resources

About