ORCA study: real-world versus reading centre assessment of disease activity of neovascular age-related macular degeneration (nAMD)

Liakopoulos, Sandra; Spital, Georg; Brinkmann, Christian; Schick, Tina; Ziemssen, Focke; Voegeler, Jessica; Koch, Mirja; Kirchhof, Bernd; Holz, Frank G.; Pauleikhoff, Daniel; Schmitz-Valckenberg, Steffen

doi:10.1136/bjophthalmol-2019-315717

Cited by 14 publications

(11 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In a recent study comparing real-world clinician versus reading-centre assessment of CNV disease activity, 20% of scans were judged active by the reading centre, but no injections were given. 49 Of these cases, some were assessed by the clinician as chronic degenerative cysts only whilst others were monitored in a ‘watch and wait’ fashion, reportedly due to patient preference.…”

Section: Discussionmentioning

confidence: 99%

Nonadherence or Nonpersistence to Intravitreal Injection Therapy for Neovascular Age-Related Macular Degeneration

et al. 2021

View full text Add to dashboard Cite

Topic Systematic review of risk factors for non-adherence and non-persistence to intravitreal anti-vascular endothelial growth factor (anti-VEGF) injection therapy for neovascular age-related macular degeneration (nAMD). Clinical Relevance Lack of adherence (non-adherence) or under-treatment (non-persistence) with respect to evidence from clinical trials remains a significant barrier to optimizing real-world outcomes for patients with nAMD. Contributing factors and strategies to address this are poorly understood. Methods Studies that reported factors for non-adherence and/or non-persistence to anti-VEGF therapy as well as studies examining strategies to improve this were included. Trial eligibility and data extraction were conducted according to Cochrane review methods. Risk of bias was assessed using the Mixed Method Assessment Tool and certainty of evidence evaluated according to the GRADE-CERQual (Confidence in the Evidence from Reviews of Qualitative Research) tool. Data were collated descriptively. Results Of the 1284 abstract results screened, 124 articles were assessed in full and 37 studies met the inclusion criteria. Definitions of non-adherence and non-persistence varied or were not reported. Non-persistence occurred early with up to 50% of patients stopping treatment by 24 months. High rates of non-adherence were similarly reported, occurring in 32 – 95% of patients. Certainty of this finding was downgraded to moderate level due to heterogeneity in definitions used across studies. Multiple factors determine non-adherence and non-persistence, including at condition, therapy, patient, social/economic and health systems/health-care team level. Moderate quality evidence points to lower baseline vision and poorer response to treatment as condition-related variables. The effects of other factors were of lower certainty, predominantly due to small numbers and potential biases in retrospective assessment. Although many factors are non-modifiable (e.g., patient co-morbidity), other factors are potentially correctable (e.g., lack of transport or mismatched patient expectations). Evidence on strategies to improve adherence and persistence is limited, but where available, these have proven effective. Conclusions Awareness of factors related to poor patient adherence and persistence in nAMD could help identify at-risk populations and improve real world outcomes. Further work is required to develop uniform definitions as well as establishing high quality evidence on interventions that can be easily implemented.

show abstract

Section: Discussionmentioning

confidence: 99%

Nonadherence or Nonpersistence to Intravitreal Injection Therapy for Neovascular Age-Related Macular Degeneration

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Undertreatment may be related to (1) misdiagnosis and conservative re-treatment criteria 9 and (2) to the overall burden of treatment, which includes the burden on patients, as well as the complexity of scheduling visits for elderly patients in need of a companion. 10 Recent innovative therapeutic approaches such as long-acting anti-VEGF inhibitors, 11 or administration of therapeutics via a port delivery system, 12 have the potential to reduce treatment burden in neovascular AMD.…”

Section: Introductionmentioning

confidence: 99%

Probabilistic Forecasting of Anti-VEGF Treatment Frequency in Neovascular Age-Related Macular Degeneration

Pfau

Sahu

Rupnow

et al. 2021

Trans. Vis. Sci. Tech.

Self Cite

View full text Add to dashboard Cite

Purpose To probabilistically forecast needed anti-vascular endothelial growth factor (anti-VEGF) treatment frequency using volumetric spectral domain–optical coherence tomography (SD-OCT) biomarkers in neovascular age-related macular degeneration from real-world settings. Methods SD-OCT volume scans were segmented with a custom deep-learning-based analysis pipeline. Retinal thickness and reflectivity values were extracted for the central and the four inner Early Treatment Diabetic Retinopathy Study (ETDRS) subfields for six retinal layers (inner retina, outer nuclear layer, inner segments [IS], outer segments [OS], retinal pigment epithelium-drusen complex [RPEDC] and the choroid). Machine-learning models were probed to predict the anti-VEGF treatment frequency within the next 12 months. Probabilistic forecasting was performed using natural gradient boosting (NGBoost), which outputs a full probability distribution. The mean absolute error (MAE) between the predicted versus actual anti-VEGF treatment frequency was the primary outcome measure. Results In a total of 138 visits of 99 eyes with neovascular AMD (96 patients) from two clinical centers, the prediction of future anti-VEGF treatment frequency was observed with an accuracy (MAE [95% confidence interval]) of 2.60 injections/year [2.25–2.96] ( R 2 = 0.390) using random forest regression and 2.66 injections/year [2.31–3.01] ( R 2 = 0.094) using NGBoost, respectively. Prediction intervals were well calibrated and reflected the true uncertainty of NGBoost-based predictions. Standard deviation of RPEDC-thickness in the central ETDRS-subfield constituted an important predictor across models. Conclusions The proposed, fully automated pipeline enables probabilistic forecasting of future anti-VEGF treatment frequency in real-world settings. Translational Relevance Prediction of a probability distribution allows the physician to inspect the underlying uncertainty. Predictive uncertainty estimates are essential to highlight cases where human-inspection and/or reversion to a fallback alternative is warranted.

show abstract

“…Many diseases of the retina have been redefined by its advent. Indeed, OCT-based parameters (such as the thickness of the central retina) are now well-established biomarkers of disease activity and clinical trial endpoints [9][10][11][12] .…”

mentioning

confidence: 99%

Code-free deep learning for multi-modality medical image classification

et al. 2021

View full text Add to dashboard Cite

A number of large technology companies have created code-free cloud-based platforms that allow researchers and clinicians without coding experience to create deep learning algorithms. In this study, we comprehensively analyse the performance and featureset of six platforms, using four representative cross-sectional and en-face medical imaging datasets to create image classification models. The mean (s.d.) F1 scores across platforms for all model–dataset pairs were as follows: Amazon, 93.9 (5.4); Apple, 72.0 (13.6); Clarifai, 74.2 (7.1); Google, 92.0 (5.4); MedicMind, 90.7 (9.6); Microsoft, 88.6 (5.3). The platforms demonstrated uniformly higher classification performance with the optical coherence tomography modality. Potential use cases given proper validation include research dataset curation, mobile ‘edge models’ for regions without internet access, and baseline models against which to compare and iterate bespoke deep learning approaches.

show abstract

ORCA study: real-world versus reading centre assessment of disease activity of neovascular age-related macular degeneration (nAMD)

Cited by 14 publications

References 22 publications

Nonadherence or Nonpersistence to Intravitreal Injection Therapy for Neovascular Age-Related Macular Degeneration

Nonadherence or Nonpersistence to Intravitreal Injection Therapy for Neovascular Age-Related Macular Degeneration

Probabilistic Forecasting of Anti-VEGF Treatment Frequency in Neovascular Age-Related Macular Degeneration

Code-free deep learning for multi-modality medical image classification

Contact Info

Product

Resources

About