Automated Machine Learning Predicts Necessary Upcoming Therapy Changes in Patients With Psoriasis Vulgaris et Arthritis And Uncovers New Influences On Disease Progression: Retrospective Study.

BACKGROUND: Psoriasis vulgaris (PsV) and Psoriatic arthritis (PsA) are intertwined multifactorial diseases with significant impact on health and quality of life, which can be debilitating due to chronicity and treatment complexity. Predicting treatment response and disease progression in these conditions is challenging, but crucial for optimising therapeutic interventions. The advancing technology of automated machine learning (AutoML) holds great promise for rapidly building highly accurate predictive models based on patient features and treatment data. OBJECTIVE: The study aimed to develop highly accurate ML models using AutoML to address key clinical questions in PsV and PsA patients, including predicting therapy changes and identifying reasons for therapy changes, factors influencing skin lesion progression or factors associated with an abnormal BASDAI score. METHODS: After extensive dataset preparation of clinical study data from 309 PsV and PsA patients, a secondary dataset was created and ultimately analysed using AutoML to build a variety of predictive models and select the most accurate one for each variable of interest. RESULTS: "Therapy change at 24 weeks follow-up" was modelled using the eXtreme Gradient Boosted Trees Classifier with Early Stopping model (AUC of 0.9078 and LogLoss of 0.3955 for the holdout partition) to gain insight into the factors influencing therapy change, such as the initial systemic therapeutic agent, the score achieved in the CASPAR classification criteria at baseline, and changes in quality of life. An AVG blender of 3 models (Gradient Boosted Trees Classifier, ExtraTrees Classifier, Eureqa Generalised Additive Model Classifier) with an AUC of 0.8750 and a LogLoss of 0.4603 was used to predict therapy changes on two hypothetical patients to highlight the importance of such influencing factors. Notably, treatments such as MTX or specific biologicals showed a lower propensity for change. A further AVG Blender of RandomForest Classifier, eXtreme Gradient Boosted Trees Classifier and Eureqa Classifier (AUC of 0.9241 and LogLoss of 0.4498) was then used to estimate "PASI change after 24 weeks" with the primary predictors being the initial PASI score, change in pruritus and change in therapy. A lower initial PASI score, and consistently low pruritus were associated with better outcomes. Finally, "BASDAI classification at baseline" was analysed using an AVG Blender of Eureqa Generalised Additive Model Classifier, eXtreme Gradient Boosted Trees Classifier with Early Stopping and Dropout Additive Regression Trees Classifier with an AUC of 0.8274 and LogLoss of 0.5037. Factors influencing BASDAI scores included initial pain, disease activity and HADS scores for depression and anxiety. Increased pain, disease activity and psychological distress were generally likely to lead to higher BASDAI scores. CONCLUSIONS: The practical implications of these models for clinical decision making in PsV and PsA have the potential to guide early investigation and treatment, contributing to improved patient outcomes.

Evolution of publicly available large language models for complex decision-making in breast cancer care.

PURPOSE: This study investigated the concordance of five different publicly available Large Language Models (LLM) with the recommendations of a multidisciplinary tumor board regarding treatment recommendations for complex breast cancer patient profiles. METHODS: Five LLM, including three versions of ChatGPT (version 4 and 3.5, with data access until September 3021 and January 2022), Llama2, and Bard were prompted to produce treatment recommendations for 20 complex breast cancer patient profiles. LLM recommendations were compared to the recommendations of a multidisciplinary tumor board (gold standard), including surgical, endocrine and systemic treatment, radiotherapy, and genetic testing therapy options. RESULTS: GPT4 demonstrated the highest concordance (70.6%) for invasive breast cancer patient profiles, followed by GPT3.5 September 2021 (58.8%), GPT3.5 January 2022 (41.2%), Llama2 (35.3%) and Bard (23.5%). Including precancerous lesions of ductal carcinoma in situ, the identical ranking was reached with lower overall concordance for each LLM (GPT4 60.0%, GPT3.5 September 2021 50.0%, GPT3.5 January 2022 35.0%, Llama2 30.0%, Bard 20.0%). GPT4 achieved full concordance (100%) for radiotherapy. Lowest alignment was reached in recommending genetic testing, demonstrating a varying concordance (55.0% for GPT3.5 January 2022, Llama2 and Bard up to 85.0% for GPT4). CONCLUSION: This early feasibility study is the first to compare different LLM in breast cancer care with regard to changes in accuracy over time, i.e., with access to more data or through technological upgrades. Methodological advancement, i.e., the optimization of prompting techniques, and technological development, i.e., enabling data input control and secure data processing, are necessary in the preparation of large-scale and multicenter studies to provide evidence on their safe and reliable clinical application. At present, safe and evidenced use of LLM in clinical breast cancer care is not yet feasible.

[Orthopedics and trauma surgery in the digital age]. / Orthopädie und Unfallchirurgie im digitalen Zeitalter.

BACKGROUND: Digital transformation is shaping the future of orthopedics and trauma surgery. Telemedicine, digital health applications, electronic patient records and artificial intelligence play a central role in this. These technologies have the potential to improve medical care, enable individualized patient treatment plans and reduce the burden on the treatment process. However, there are currently challenges in the areas of infrastructure, regulation, reimbursement and data protection. REALISING THE TRANSFORMATION: Effective transformation requires a deep understanding of both technology and clinical practice. Orthopedic and trauma surgeons need to take a leadership role by actively engaging with new technologies, designing new treatment processes and enhancing their medical skills with digital and AI competencies. The integration of digital skills into medical education and specialist training will be crucial for actively shaping the digital transformation and exploiting its full potential.

CD200+ fibroblasts form a pro-resolving mesenchymal network in arthritis.

Fibroblasts are important regulators of inflammation, but whether fibroblasts change phenotype during resolution of inflammation is not clear. Here we use positron emission tomography to detect fibroblast activation protein (FAP) as a means to visualize fibroblast activation in vivo during inflammation in humans. While tracer accumulation is high in active arthritis, it decreases after tumor necrosis factor and interleukin-17A inhibition. Biopsy-based single-cell RNA-sequencing analyses in experimental arthritis show that FAP signal reduction reflects a phenotypic switch from pro-inflammatory MMP3+/IL6+ fibroblasts (high FAP internalization) to pro-resolving CD200+DKK3+ fibroblasts (low FAP internalization). Spatial transcriptomics of human joints indicates that pro-resolving niches of CD200+DKK3+ fibroblasts cluster with type 2 innate lymphoid cells, whereas MMP3+/IL6+ fibroblasts colocalize with inflammatory immune cells. CD200+DKK3+ fibroblasts stabilized the type 2 innate lymphoid cell phenotype and induced resolution of arthritis via CD200-CD200R1 signaling. Taken together, these data suggest a dynamic molecular regulation of the mesenchymal compartment during resolution of inflammation.

CD19 CAR T-Cell Therapy in Autoimmune Disease - A Case Series with Follow-up.

BACKGROUND: Treatment for autoimmune diseases such as systemic lupus erythematosus (SLE), idiopathic inflammatory myositis, and systemic sclerosis often involves long-term immune suppression. Resetting aberrant autoimmunity in these diseases through deep depletion of B cells is a potential strategy for achieving sustained drug-free remission. METHODS: We evaluated 15 patients with severe SLE (8 patients), idiopathic inflammatory myositis (3 patients), or systemic sclerosis (4 patients) who received a single infusion of CD19 chimeric antigen receptor (CAR) T cells after preconditioning with fludarabine and cyclophosphamide. Efficacy up to 2 years after CAR T-cell infusion was assessed by means of Definition of Remission in SLE (DORIS) remission criteria, American College of Rheumatology-European League against Rheumatism (ACR-EULAR) major clinical response, and the score on the European Scleroderma Trials and Research Group (EUSTAR) activity index (with higher scores indicating greater disease activity), among others. Safety variables, including cytokine release syndrome and infections, were recorded. RESULTS: The median follow-up was 15 months (range, 4 to 29). The mean (±SD) duration of B-cell aplasia was 112±47 days. All the patients with SLE had DORIS remission, all the patients with idiopathic inflammatory myositis had an ACR-EULAR major clinical response, and all the patients with systemic sclerosis had a decrease in the score on the EUSTAR activity index. Immunosuppressive therapy was completely stopped in all the patients. Grade 1 cytokine release syndrome occurred in 10 patients. One patient each had grade 2 cytokine release syndrome, grade 1 immune effector cell-associated neurotoxicity syndrome, and pneumonia that resulted in hospitalization. CONCLUSIONS: In this case series, CD19 CAR T-cell transfer appeared to be feasible, safe, and efficacious in three different autoimmune diseases, providing rationale for further controlled clinical trials. (Funded by Deutsche Forschungsgemeinschaft and others.).

[Digital rheumatology]. / Digitale Rheumatologie.

Chronic inflammatory rheumatic diseases mostly run an undulating course and with unspecific symptoms. The initial clarification and timely initiation of treatment are challenging, which is additionally exacerbated by the lack of specialized physicians. Digital approaches, including artificial intelligence (AI), should be of assistance and enable an improved, personalized and needs-based treatment; however, the evidence is currently still very limited. This article provides a compact overview of the current state of digital rheumatology.

Real-world usage of digital health applications (DiGA) in rheumatology: results from a German patient survey.

Mobile health applications and digital therapeutics (DTx) aim to improve current patient care. Real-world data on DTx are, however, scarce. The aim of this study was to evaluate the adherence, acceptance, and efficacy of DTx in a clinical routine rheumatology setting. We conducted a prospective observational cohort study assessing the use, adherence, acceptance, and efficacy of the DTx DiGA (Digitale Gesundheitsanwendungen) by survey over 12 weeks. Patients included had to have a rheumatic disease and had been prescribed a DiGA. Acceptance was assessed using the Net promoter score (NPS). 48 patients were prescribed DiGA. Of these, 39/48 (81%) completed the follow-up survey. 21/39 (54%) patients downloaded the DTx and 20/39 (51%) used the DTx at least once. 9/39 (23%) of patients stopped quickly afterward and 5/39 (13%) reported having completed the whole DTx program. Lack of time and commitment were reported as the main reasons for non-use. Overall acceptance of DiGA was high (Net promoter score (NPS) mean (SD) 7.8/10 (2.3)). While the majority of patients (60%) reported no improvement, one subgroup of patients (7/20, 35%) who regularly used an exercise-based DTx for back pain reported symptom improvement. Acceptance of DTx in patients with rheumatic diseases is high, however onboarding to DTx use and adherence to DTx is still challenging in patients with rheumatic diseases. In a subgroup of patients with back pain, however, the use of an exercise-based DTx led to symptom improvement.

Cinematic rendering in rheumatic diseases-Photorealistic depiction of pathologies improves disease understanding for patients.

Background: Patient education is crucial for successful chronic disease management. Current education material for rheumatic patients however rarely includes images of disease pathologies, limiting patients' disease understanding. Cinematic rendering (CR) is a new tool that allows segmentation of standard medical images (DICOMs) into pictures that illustrate disease pathologies in a photorealistic way. Thus CR has the potential to simplify and improve the explanation of disease pathologies, disease activity and disease consequences and could therefore be a valuable tool to effectively educate and inform patients about their rheumatic and musculoskeletal disease (RMD). Objectives: To examine the feasibility of creating photorealistic images using CR from RMD patients depicting typical rheumatic disease pathologies and, in a second step to investigate the patient-perceived educational potential of these photorealistic images in clinical routine. Methods: We selected conventional, high-resolution (HR) and positron emission tomography (PET) computed tomography (CT) images of patients with rheumatoid arthritis (RA), psoriatic arthritis (PsA), axial spondyloarthritis (axSpA), and giant cell arteritis (GCA) that showed typical respective disease pathologies. These images were segmented using CR technique. In a prospective study, physicians used CR-enhanced and conventional original images to explain the depicted pathognomonic pathologies to patients with the respective rheumatic disease. Patients were then asked to complete a questionnaire evaluating the perceived usefulness of being presented with CR-enhanced images to better understand their underlying disease. Results: CR images were successfully generated from above mentioned CT methods. Pathologies such as bone erosions, bony spurs, bone loss, ankylosis, and PET-based inflammation could be visualized in photorealistic detail. A total of 79 patients (61% females) with rheumatic diseases (RA 29%, PsA 29%, axSpA 24%, GCA 18%) were interviewed and answered the quantitative questionnaire. Mean age was 55.4 ± 12.6 years. Irrespective of disease, all patients agreed or highly agreed that CR-based images help to improve disease understanding, should be shown at disease onset, provide a rationale to regularly take medication and would like to have access to their own CR-enhanced images. Conclusion: Conventional disease images can successfully be turned into photorealistic disease depictions using CR. Patients perceived CR images as a valuable addition to current patient education, enabling personalized disease education and potentially increased medication adherence.

Digital Approaches for a Reliable Early Diagnosis of Psoriatic Arthritis.

Psoriatic arthritis (PsA) is a chronic inflammatory disease that develops in up to 30% of patients with psoriasis. In the vast majority of cases, cutaneous symptoms precede musculoskeletal complaints. Progression from psoriasis to PsA is characterized by subclinical synovio-entheseal inflammation and often non-specific musculoskeletal symptoms that are frequently unreported or overlooked. With the development of increasingly effective therapies and a broad drug armamentarium, prevention of arthritis development through careful clinical monitoring has become priority. Identifying high-risk psoriasis patients before PsA onset would ensure early diagnosis, increased treatment efficacy, and ultimately better outcomes; ideally, PsA development could even be averted. However, the current model of care for PsA offers only limited possibilities of early intervention. This is attributable to the large pool of patients to be monitored and the limited resources of the health care system in comparison. The use of digital technologies for health (eHealth) could help close this gap in care by enabling faster, more targeted and more streamlined access to rheumatological care for patients with psoriasis. eHealth solutions particularly include telemedicine, mobile technologies, and symptom checkers. Telemedicine enables rheumatological visits and consultations at a distance while mobile technologies can improve monitoring by allowing patients to self-report symptoms and disease-related parameters continuously. Symptom checkers have the potential to direct patients to medical attention at an earlier point of their disease and therefore minimizing diagnostic delay. Overall, these interventions could lead to earlier diagnoses of arthritis, improved monitoring, and better disease control while simultaneously increasing the capacity of referral centers.

Performance of a Handheld Ultrasound Device to Assess Articular and Periarticular Pathologies in Patients with Inflammatory Arthritis.

The purpose of this study was to assess the accuracy and performance of a new handheld ultrasound (HHUS) machine in comparison to a conventional cart-based sonographic machine in patients with inflammatory arthritis (IA). IA patients with at least one tender and swollen joint count were enrolled. US was performed on the clinically affected joints using a cart-based sonographic device (Samsung HS40) and a HHUS device (Butterfly iQ). One blinded reader scored all images for the presence of erosions, bony enlargement, synovial hypertrophy, joint effusion, bursitis, tenosynovitis, and enthesitis. Synovitis was graded (B mode and power Doppler (PD)) by the 4-level EULAR-OMERACT scale. To avoid bias by the blinded reader, we included 67 joints of two healthy volunteers in the evaluation. We calculated the overall concordance and the concordance by type of joint and pathological finding. We also measured the time required for the US examination per joint with both devices. Thirty-two patients (20 with RA, 10 with PsA, and one each with gout and SLE-associated arthritis) were included, and 186 joints were examined. The overall raw concordance in B mode was 97% (κappa 0.90, 95% CI (0.89, 0.94)). In B mode, no significant differences were found in relation to type of joint or pathological finding examined. The PD mode of the HHUS device did not detect any PD signal, whereas the cart-based device detected a PD signal in 61 joints (33%). The portable device did not offer any time savings compared to the cart-based device (47.0 versus 46.3 s). The HHUS device was accurate in the assessment of structural damage and inflammation in patients with IA, but only in the B mode. Significant improvements are still needed for HHUS to reliably demonstrate blood flow detection in PD mode.