Visual acuity prediction on real-life patient data using a machine learning based multistage system

In ophthalmology, intravitreal operative medication therapy (IVOM) is a widespread treatment for diseases related to the age-related macular degeneration (AMD), the diabetic macular edema, as well as the retinal vein occlusion. However, in real-world settings, patients often suffer from loss of vision on time scales of years despite therapy, whereas the prediction of the visual acuity (VA) and the earliest possible detection of deterioration under real-life conditions is challenging due to heterogeneous and incomplete data. In this contribution, we present a workflow for the development of a research-compatible data corpus fusing different IT systems of the department of ophthalmology of a German maximum care hospital. The extensive data corpus allows predictive statements of the expected progression of a patient and his or her VA in each of the three diseases. For the disease AMD, we found out a significant deterioration of the visual acuity over time. Within our proposed multistage system, we subsequently classify the VA progression into the three groups of therapy "winners", "stabilizers", and "losers" (WSL classification scheme). Our OCT biomarker classification using an ensemble of deep neural networks results in a classification accuracy (F1-score) of over 98%, enabling us to complete incomplete OCT documentations while allowing us to exploit them for a more precise VA modelling process. Our VA prediction requires at least four VA examinations and optionally OCT biomarkers from the same time period to predict the VA progression within a forecasted time frame, whereas our prediction is currently restricted to IVOM/no therapy. We achieve a final prediction accuracy of 69% in macro average F1-score, while being in the same range as the ophthalmologists with 57.8 and 50 ± 10.7 % F1-score.

Prognostic value of single-subject grey matter networks in early multiple sclerosis

The identification of prognostic markers in early multiple sclerosis (MS) is challenging and requires reliable measures that robustly predict future disease trajectories. Ideally, such measures should make inferences at the individual level to inform clinical decisions. This study investigated the prognostic value of longitudinal structural networks to predict 5-year Expanded Disability Status Scale (EDSS) progression in patients with relapsing-remitting MS (RRMS). We hypothesized that network measures, derived from MRI, outperform conventional MRI measurements at identifying patients at risk of developing disability progression. This longitudinal, multicentre study within the Magnetic Resonance Imaging in MS (MAGNIMS) network included 406 patients with RRMS (mean age = 35.7 ± 9.1 years) followed up for 5 years (mean follow-up = 5.0 ± 0.6 years). EDSS was determined to track disability accumulation. A group of 153 healthy subjects (mean age = 35.0 ± 10.1 years) with longitudinal MRI served as controls. All subjects underwent MRI at baseline and again 1 year after baseline. Grey matter atrophy over 1 year and white matter lesion load were determined. A single-subject brain network was reconstructed from T1-weighted scans based on grey matter atrophy measures derived from a statistical parameter mapping-based segmentation pipeline. Key topological measures, including network degree, global efficiency and transitivity, were calculated at single-subject level to quantify network properties related to EDSS progression. Areas under receiver operator characteristic (ROC) curves were constructed for grey matter atrophy and white matter lesion load, and the network measures and comparisons between ROC curves were conducted. The applied network analyses differentiated patients with RRMS who experience EDSS progression over 5 years through lower values for network degree [H(2) = 30.0, P < 0.001] and global efficiency [H(2) = 31.3, P < 0.001] from healthy controls but also from patients without progression. For transitivity, the comparisons showed no difference between the groups [H(2) = 1.5, P = 0.474]. Most notably, changes in network degree and global efficiency were detected independent of disease activity in the first year. The described network reorganization in patients experiencing EDSS progression was evident in the absence of grey matter atrophy. Network degree and global efficiency measurements demonstrated superiority of network measures in the ROC analyses over grey matter atrophy and white matter lesion load in predicting EDSS worsening (all P-values < 0.05). Our findings provide evidence that grey matter network reorganization over 1 year discloses relevant information about subsequent clinical worsening in RRMS. Early grey matter restructuring towards lower network efficiency predicts disability accumulation and outperforms conventional MRI predictors.

Immune Response to Initial and Booster SARS-CoV-2 mRNA Vaccination in Patients Treated with Siponimod-Final Analysis of a Nonrandomized Controlled Clinical Trial (AMA-VACC)

BACKGROUND

Evidence on SARS-CoV-2 mRNA vaccination under siponimod treatment is rare.

METHODS

AMA-VACC is a prospective, open-label clinical study on SARS-CoV-2 mRNA vaccination during ongoing siponimod treatment (cohort 1), during siponimod interruption (cohort 2), or during treatment with other disease-modifying therapies or without therapy (cohort 3). SARS-CoV-2-specific antibodies and T-cell reactivity were measured six months after the initial vaccination and one month after the booster.

RESULTS

41 patients were recruited into cohort 1 (n = 17), cohort 2 (n = 4), and cohort 3 (n = 20). Seroconversion for SARS-CoV-2 neutralizing antibodies was reached by 50.0%, 100.0%, and 90.0% of patients at month 6 and by 81.3%, 100.0%, and 100.0% one month after booster (cohorts 1, 2, and 3, respectively). Antibody levels in cohort 1 increased after the booster compared to month 6 but remained lower compared to cohorts 2 and 3. T-cell responses were seen in 28.5%, 25.0%, and 73.7% at month 6 and in 28.6%, 50.0%, and 83.3% after the booster (cohorts 1, 2, and 3, respectively). In cohort 1, the extent of T-cell response was lower at month 6 compared to cohorts 2 and 3 but reached almost similar levels after the booster.

CONCLUSIONS

The antibody and T-cell responses support SARS-CoV-2 (booster) vaccines in siponimod-treated patients.

Regulation of the programmed cell death protein 1/programmed cell death ligand 1 axis in relapsing-remitting multiple sclerosis

The programmed cell death protein 1/programmed cell death ligand 1 axis plays an important role in the adaptive immune system and has influence on neoplastic and inflammatory diseases, while its role in multiple sclerosis is unclear. Here, we aimed to analyse expression patterns of programmed cell death protein 1 and programmed cell death ligand 1 on peripheral blood mononuclear cells and their soluble variants in multiple sclerosis patients and controls, to determine their correlation with clinical disability and disease activity. In a cross-sectional study, we performed in-depth flow cytometric immunophenotyping of peripheral blood mononuclear cells and analysed soluble programmed cell death protein 1 and programmed cell death ligand 1 serum levels in patients with relapsing-remitting multiple sclerosis and controls. In comparison to control subjects, relapsing-remitting multiple sclerosis patients displayed distinct cellular programmed cell death protein 1/programmed cell death ligand 1 expression patterns in immune cell subsets and increased soluble programmed cell death ligand 1 levels, which correlated with clinical measures of disability and MRI activity over time. This study extends our knowledge of how programmed cell death protein 1 and programmed cell death ligand 1 are expressed in the membranes of patients with relapsing-remitting multiple sclerosis and describes for the first time the elevation of soluble programmed cell death ligand 1 in the blood of multiple sclerosis patients. The distinct expression pattern of membrane-bound programmed cell death protein 1 and programmed cell death ligand 1 and the correlation between soluble programmed cell death ligand 1, membrane-bound programmed cell death ligand 1, disease and clinical factors may offer therapeutic potential in the setting of multiple sclerosis and might improve future diagnosis and clinical decision-making.

Liquid Biopsies in Lung Cancer

As lung cancer has the highest cancer-specific mortality rates worldwide, there is an urgent need for new therapeutic and diagnostic approaches to detect early-stage tumors and to monitor their response to the therapy. In addition to the well-established tissue biopsy analysis, liquid-biopsy-based assays may evolve as an important diagnostic tool. The analysis of circulating tumor DNA (ctDNA) is the most established method, followed by other methods such as the analysis of circulating tumor cells (CTCs), microRNAs (miRNAs), and extracellular vesicles (EVs). Both PCR- and NGS-based assays are used for the mutational assessment of lung cancer, including the most frequent driver mutations. However, ctDNA analysis might also play a role in monitoring the efficacy of immunotherapy and its recent accomplishments in the landscape of state-of-the-art lung cancer therapy. Despite the promising aspects of liquid-biopsy-based assays, there are some limitations regarding their sensitivity (risk of false-negative results) and specificity (interpretation of false-positive results). Hence, further studies are needed to evaluate the usefulness of liquid biopsies for lung cancer. Liquid-biopsy-based assays might be integrated into the diagnostic guidelines for lung cancer as a tool to complement conventional tissue sampling.

Canakinumab for Treatment of Adult-Onset Still's Disease to Achieve Reduction of Arthritic Manifestation (CONSIDER): phase II, randomised, double-blind, placebo-controlled, multicentre, investigator-initiated trial

BACKGROUND

Inhibition of interleukin (IL)-1 represents a promising treatment option in adult-onset Still's disease (AOSD).

OBJECTIVE

To investigate the efficacy and safety of canakinumab in patients with AOSD and active joint involvement by means of a multicentre, double-blind, randomised, placebo-controlled trial.

METHODS

Patients with AOSD and active joint involvement (tender and swollen joint counts of ≥4 each) were treated with canakinumab (4 mg/kg, maximum 300 mg subcutaneous every 4 weeks) or placebo. The primary endpoint was the proportion of patients with a clinically relevant reduction in disease activity at week 12 as determined by the change in disease activity score (ΔDAS28>1.2).

RESULTS

At enrolment, patients had high active disease with a mean DAS28(ESR) of 5.4 in the canakinumab and 5.3 in the placebo group, respectively. In the intention-to-treat analysis, 12 patients (67%) in the canakinumab group and 7 patients (41%) in the placebo group fulfilled the primary outcome criterion (p=0.18). In the per-protocol analysis, significantly higher American College of Rheumatology (ACR) 30% (61% vs 20%, p=0.033), ACR 50% (50% vs 6.7%, p=0.009) and ACR 70% (28% vs 0%, p=0.049) response rates were observed in the canakinumab group compared with the placebo group. Two patients in the canakinumab group experienced a serious adverse event.

CONCLUSION

Although the study was terminated prematurely and the primary endpoint was not achieved, treatment with canakinumab led to an improvement of several outcome measures in AOSD. The overall safety findings were consistent with the known profile of canakinumab. Thus, our data support indication for IL-1 inhibition with canakinumab in AOSD.

Psoriatic arthritis epidemiology, comorbid disease profiles and risk factors: results from a claims database analysis

OBJECTIVE

Psoriasis is a systemic inflammatory disease often accompanied by comorbidities, including metabolic syndrome, cardiovascular diseases and depression. Up to 41% of psoriasis patients develop psoriatic arthritis (PsA), making it one of the most relevant manifestations. A large health claims data set was analysed to determine the rate of PsA development in psoriasis patients. Furthermore, comorbid disease profiles of psoriasis patients with or without PsA were compared, and potential risk factors for the development of PsA were identified.

METHODS

This was a non-interventional, retrospective analysis of anonymized insurance health claims data using a subset of the Institute of Applied Health Research Berlin (InGef) database. The primary outcome was the prevalence and incidence of diagnosed PsA among psoriasis patients in Germany. Risk factors for the development of PsA in psoriasis patients were determined by conditional logistic regression analysis.

RESULTS

The cumulative percentage of patients with existing psoriasis developing concomitant PsA over 4 years was 3.44%, with a mean time to diagnosis of PsA of 1.5 years. Psoriasis patients diagnosed with acute rheumatism (odds ratio: 2.93, 95% CI = 1.76, 4.86; P < 0.001) or pain in unspecific joints (odds ratio: 1.74, 95% CI = 1.01, 2.99; P = 0.047) showed an increased risk for development of PsA later on. Interestingly, fewer than half of the patients with concomitant PsA consulted a rheumatologist.

CONCLUSIONS

Unspecific arthritic symptoms are likely to precede PsA diagnoses and can develop soon after onset of psoriasis, with accumulating risk over time. There is a high unmet need for early rheumatological assessment of psoriasis patients.