RESUMEN
BACKGROUND: The diagnosis of inflammatory rheumatic diseases (IRDs) is often delayed due to unspecific symptoms and a shortage of rheumatologists. Digital diagnostic decision support systems (DDSSs) have the potential to expedite diagnosis and help patients navigate the health care system more efficiently. OBJECTIVE: The aim of this study was to assess the diagnostic accuracy of a mobile artificial intelligence (AI)-based symptom checker (Ada) and a web-based self-referral tool (Rheport) regarding IRDs. METHODS: A prospective, multicenter, open-label, crossover randomized controlled trial was conducted with patients newly presenting to 3 rheumatology centers. Participants were randomly assigned to complete a symptom assessment using either Ada or Rheport. The primary outcome was the correct identification of IRDs by the DDSSs, defined as the presence of any IRD in the list of suggested diagnoses by Ada or achieving a prespecified threshold score with Rheport. The gold standard was the diagnosis made by rheumatologists. RESULTS: A total of 600 patients were included, among whom 214 (35.7%) were diagnosed with an IRD. Most frequent IRD was rheumatoid arthritis with 69 (11.5%) patients. Rheport's disease suggestion and Ada's top 1 (D1) and top 5 (D5) disease suggestions demonstrated overall diagnostic accuracies of 52%, 63%, and 58%, respectively, for IRDs. Rheport showed a sensitivity of 62% and a specificity of 47% for IRDs. Ada's D1 and D5 disease suggestions showed a sensitivity of 52% and 66%, respectively, and a specificity of 68% and 54%, respectively, concerning IRDs. Ada's diagnostic accuracy regarding individual diagnoses was heterogenous, and Ada performed considerably better in identifying rheumatoid arthritis in comparison to other diagnoses (D1: 42%; D5: 64%). The Cohen κ statistic of Rheport for agreement on any rheumatic disease diagnosis with Ada D1 was 0.15 (95% CI 0.08-0.18) and with Ada D5 was 0.08 (95% CI 0.00-0.16), indicating poor agreement for the presence of any rheumatic disease between the 2 DDSSs. CONCLUSIONS: To our knowledge, this is the largest comparative DDSS trial with actual use of DDSSs by patients. The diagnostic accuracies of both DDSSs for IRDs were not promising in this high-prevalence patient population. DDSSs may lead to a misuse of scarce health care resources. Our results underscore the need for stringent regulation and drastic improvements to ensure the safety and efficacy of DDSSs. TRIAL REGISTRATION: German Register of Clinical Trials DRKS00017642; https://drks.de/search/en/trial/DRKS00017642.
Asunto(s)
Inteligencia Artificial , Reumatología , Humanos , Femenino , Masculino , Persona de Mediana Edad , Estudios Prospectivos , Reumatología/métodos , Adulto , Estudios Cruzados , Enfermedades Reumáticas/diagnóstico , Internet , Anciano , Derivación y Consulta/estadística & datos numéricosRESUMEN
BACKGROUND: Individuals with anti-citrullinated protein antibodies (ACPAs) and subclinical inflammatory changes in joints are at high risk of developing rheumatoid arthritis. Treatment strategies to intercept this pre-stage clinical disease remain to be developed. We aimed to assess whether 6-month treatment with abatacept improves inflammation in preclinical rheumatoid arthritis. METHODS: The abatacept reversing subclinical inflammation as measured by MRI in ACPA positive arthralgia (ARIAA) study is a randomised, international, multicentre, double-blind, placebo-controlled trial done in 14 hospitals and community centres across Europe (11 in Germany, two in Spain, and one in the Czech Republic). Adults (aged ≥18 years) with ACPA positivity, joint pain (but no swelling), and signs of osteitis, synovitis, or tenosynovitis in hand MRI were randomly assigned (1:1) to weekly subcutaneous abatacept 125 mg or placebo for 6 months followed by a double-blind, drug-free, observation phase for 12 months. The primary outcome was the proportion of participants with any reduction in inflammatory MRI lesions at 6 months. The primary efficacy analysis was done in the modified intention-to-treat population, which included participants who were randomly assigned and received study medication. Safety analyses were conducted in participants who received the study medication and had at least one post-baseline observation. The study was registered with the EUDRA-CT (2014-000555-93). FINDINGS: Between Nov 6, 2014, and June 15, 2021, 139 participants were screened. Of 100 participants, 50 were randomly assigned to abatacept 125 mg and 50 to placebo. Two participants (one from each group) were excluded due to administration failure or refusing treatment; thus, 98 were included in the modified intention-to-treat population. 70 (71%) of 98 participants were female and 28 (29%) of 98 were male. At 6 months, 28 (57%) of 49 participants in the abatacept group and 15 (31%) of 49 participants in the placebo group showed improvement in MRI subclinical inflammation (absolute difference 26·5%, 95% CI 5·9-45·6; p=0·014). Four (8%) of 49 participants in the abatacept group and 17 (35%) of 49 participants in the placebo group developed rheumatoid arthritis (hazard ratio [HR] 0·14 [0·04-0·47]; p=0·0016). Improvement of MRI inflammation (25 [51%] of 49 participants in the abatacept group, 12 [24%] of 49 in the placebo group; p=0·012) and progression to rheumatoid arthritis (17 [35%] of 49, 28 [57%] of 49; HR 0·14 [0·04-0·47]; p=0·018) remained significantly different between the two groups after 18 months, 12 months after the end of the intervention. There were 12 serious adverse events in 11 participants (four [8%] of 48 in the abatacept group and 7 [14%] of 49 in the placebo group). No deaths occurred during the study. INTERPRETATION: 6-month treatment with abatacept decreases MRI inflammation, clinical symptoms, and risk of rheumatoid arthritis development in participants at high risk. The effects of the intervention persist through a 1-year drug-free observation phase. FUNDING: Innovative Medicine Initiative.
Asunto(s)
Antirreumáticos , Artritis Reumatoide , Adulto , Masculino , Humanos , Femenino , Adolescente , Abatacept/efectos adversos , Antirreumáticos/efectos adversos , Resultado del Tratamiento , Artritis Reumatoide/diagnóstico por imagen , Artritis Reumatoide/tratamiento farmacológico , Inflamación/tratamiento farmacológico , Artralgia/inducido químicamenteRESUMEN
OBJECTIVES: The ASSIST study investigated prescribing in routine psoriatic arthritis (PsA) care and whether the patient reported outcome: PsA Impact of Disease questionnaire (PsAID-12), impacted treatment. This study also assessed a range of patient and clinician factors and their relationship to PsAID-12 scoring and treatment modification. METHODS: Patients with PsA were selected across the UK and Europe between July 2021-March 2022. Patients completed the PsAID questionnaire, with the results shared with their physician. Patient characteristics, disease activity, current treatment methods, treatment strategies, medication changes and patient satisfaction scores were recorded. RESULTS: 503 patients recruited. 36.2% had changes made to treatment, 88.8% of this had treatment escalation. Overall, the mean PsAID-12 score was higher for patients with treatment escalation; the PsAID-12 score was associated with odds of treatment escalation (OR: 1.58; p< 0.0001). However, most clinicians reported PsAID-12 did not impact their decision to escalate treatment, instead supporting treatment reduction decisions. Physician's assessment of disease activity had the most statistically significant effect on likelihood of treatment escalation, (OR = 2.68, per 1-point score increase). Escalation was more likely in patients not treated with biologic therapies. Additional factors associated with treatment escalation included: patient characteristics, physician characteristics, disease activity and disease impact. CONCLUSION: This study highlights multiple factors impacting treatment decision making for individuals with PsA. PsAID-12 scoring correlates with multiple measures of disease severity and odds of treatment escalation. However, most clinicians reported the PsAID-12 did not influence treatment escalation decisions. PsAID scoring could be used to increase confidence in treatment de-escalation.
RESUMEN
OBJECTIVES: To assess the impact of low to moderate biomechanical stress on entheses in patients with psoriasis and psoriatic arthritis (PsA). METHODS: We conducted a prospective interventional study on a cohort of psoriasis and PsA patients who underwent a 60 min badminton training session. Pain assessment by Visual Analogue Scale (VAS), physical examination of 29 entheses (SPARCC, LEI, MASES) and bilateral ultrasound at the lateral humeral epicondyle, inferior patellar pole and Achilles tendon were performed before and after training. Ultrasound changes were assessed using the OMERACT scoring system. A follow-up assessment of pain and adverse events was performed at 1 week. RESULTS: Sixteen patients were included (n=7 PsA; n=9 psoriasis) and 196 entheseal ultrasound scans were acquired. At baseline, median VAS pain (IQR) was 0.5 cm (0-2.3) and the total number of tender entheses was 12/464. Mean (min; max) Disease Activity Index for Psoriatic Arthritis was 6.1 (0.8; 19) and 5/7 PsA patients had an Minimal Disease Activity status. After training, no significant change in VAS pain (0.0 cm (0.0-2.0)) nor in tender entheses (13/464) emerged. Four patients (n=2 PsA, n=2 psoriasis) developed a grade-1 power Doppler-signal at six entheses, which, however, remained non-tender. At 1 week, median VAS pain remained stable (0.0 cm (0.0-3.0); p>0.05) and only one participant with active PsA at baseline reported increased arthralgias in three joints. CONCLUSIONS: Low to moderate physical strain, as in the context of leisure sport activity, seems well tolerated in psoriatic patients without increases in tenderness, pain and ultrasound-proven inflammation. Evidence-based recommendations for physical activity in PsA are direly needed and larger controlled studies should be conducted to define safe exercise thresholds.
Asunto(s)
Artritis Psoriásica , Psoriasis , Humanos , Artritis Psoriásica/complicaciones , Artritis Psoriásica/diagnóstico , Artritis Psoriásica/tratamiento farmacológico , Estudios Prospectivos , Psoriasis/complicaciones , Psoriasis/diagnóstico , Actividades Recreativas , DolorRESUMEN
VEXAS syndrome is a recently identified autoinflammatory systemic disease caused by an acquired somatic mutation of the X-linked UBA1 gene, the key enzyme of the first step of ubiquitylation. The acronym VEXAS stands for the characteristics Vacuoles, E1 enzyme, X-linked, autoinflammatory and somatic. The disease occurs in advanced adulthood preferentially in men and is characterized by hematological, rheumatological and dermatological symptoms. The latter include neutrophil-rich lesions reminiscent of Sweet's syndrome, erythema nodosum- and panniculitis-like skin manifestations and recurrent polychondritis of the nose and auricles. The presence of cytoplasmic vacuoles in myeloid and erythroid precursors in the bone marrow is characteristic. In up to half of the cases, VEXAS syndrome is associated with myelodysplastic syndrome. Dermatologists should be familiar with the clinical picture, as skin symptoms are often the first indicator of the disease. Molecular diagnostics are essential for confirming the diagnosis and risk stratification of affected patients. In this minireview we provide an overview of the pathophysiology, diagnosis and therapy of VEXAS syndrome and illustrate its clinical picture with two own cases.
Asunto(s)
Enfermedades Autoinmunes , Enfermedades de los Cartílagos , Pabellón Auricular , Síndrome de Sweet , Masculino , Humanos , Adulto , Síndrome de Sweet/diagnóstico , MutaciónRESUMEN
OBJECTIVES: Shared decision-making (SDM) is advocated to improve patient outcomes in Psoriatic arthritis (PsA). We analysed current prescribing practices and the extent of SDM in PsA across Europe. METHODS: The ASSIST study was a cross-sectional observational study of PsA patients aged ≥18 years attending face-to-face appointments between July 2021-March 2022. Patient demographics, current treatment and treatment decisions were recorded. SDM was measured by the clinician's effort to collaborate (CollaboRATE questionnaire) and patient communication confidence (PEPPI-5 tool). RESULTS: 503 patients were included from 24 centres across the UK, France, Germany, Italy and Spain. Physician- and patient-reported measures of disease activity were highest in the UK. Conventional synthetic DMARDs constituted a higher percentage of current PsA treatment in UK than continental Europe (66.4% vs 44.9%), which differed from biologic DMARDs (36.4% vs 64.4%). Implementing treatment escalation was most common in the UK. CollaboRATE and PEPPI-5 scores were high across centres. Of 31 patients with low CollaboRATE scores (<4.5), no patients with low PsAID-12 scores (<5) had treatment escalation. However, of 465 patients with CollaboRATE scores ≥4.5, 59 patients with low PsAID-12 scores received treatment escalation. CONCLUSIONS: Higher rates of treatment escalation seen in the UK may be explained by higher disease activity and a younger cohort. High levels of collaboration in face-to-face PsA consultations suggests effective implementation of the SDM approach. Our data indicate that, in patients with mild disease activity, only those with higher perceived collaboration underwent treatment escalation. Prospective studies should examine the impact of SDM on PsA patient outcomes. TRIAL REGISTRATION: clinicaltrials.gov, NCT05171270.
RESUMEN
OBJECTIVE: The possibility of combining real and virtual environments is driving the increased use of augmented reality (AR) in education, including medical training. The aim of this multicentre study was to evaluate the students' perspective on the AR-based Rheumality GO!® app as a new teaching concept, presenting six real anonymised patient cases with rheumatoid arthritis (RA), psoriatic arthritis (PsA), and axial spondyloarthritis (axSpA). METHODS: The study encompassed 347 undergraduate medical students (232 women and 115 men) from four medical universities in Germany (Jena, Bad Nauheim/Gießen, Nuremberg, Erlangen). The course was divided into a theoretical refresher lecture followed by six AR-based cases in each of the three indications presented in the Rheumality GO!® app. All participants evaluated the course after completion, assessing the benefit of the app from a student´s perspective using a questionnaire with 16 questions covering six subject areas. RESULTS: The use of the AR-based app Rheumality GO!® improved the understanding of pathologies in RA, PsA, and axSpA for 99% of the participants. For 98% of respondents, the concept of AR with real patient data has made a positive impact on the teaching environment. On the other hand, 82% were in favour of the use of virtual tools (e.g. AR) in addition to this conventional approach. CONCLUSION: The results of our survey showed that from medical students' perspective, an AR-based concept like the Rheumality GO!® app can complement rheumatology teaching in medical school as an effective and attractive tool though not replace bedside teaching.
RESUMEN
INTRODUCTION: Our aim was to investigate the efficacy and safety of upadacitinib (UPA) in patients with either oligo- or polyarticular active psoriatic arthritis (PsA) using routine clinical practice data from an observational, prospective, multicentre study. METHODS: This interim analysis contains upadacitinib efficacy and safety data from the UPJOINT study, collected from baseline to the week 24 visit with a focus on composite measures, clinical assessments and patient-reported outcomes, amongst others, including minimal disease activity (MDA), very low disease activity (VLDA), Disease Activity Index for Psoriatic Arthritis (DAPSA), Leeds Enthesitis Index (LEI), resolution of dactylitis and nail psoriasis and body surface area affected by skin psoriasis (BSA). RESULTS: A total of 296 patients with baseline data and 192 with completed week 24 visits were included in the analysis. The proportion of patients achieving MDA increased from 2.7% at baseline to 39.1% at week 24 (95% CI 32.1, 46.3). Similarly, the number of patients in DAPSA remission (DAPSA ≤ 4) increased from 0 at baseline to 32 (16.7%) by week 24. At that time, 59.4% of the patients were either in DAPSA remission or had low disease activity (DAPSA ≤ 14). During the 24 weeks time frame, the proportion of patients with BSA ≤ 3 increased from 80.7% to 91.1%. Furthermore, at weeks 12 and 24, 45.14% and 47.19% of affected patients showed a resolution of enthesitis. Active dactylitis and nail psoriasis at baseline were reported to affect 10.5% and 22.0%, decreasing to 2.6% and 5.7% at week 24, respectively. The safety findings are consistent with the known safety profile of upadacitinib in rheumatoid arthritis and PsA; no new safety risks were identified. CONCLUSION: The data from this study confirm the findings of previous randomized controlled trials suggesting UPA is an effective treatment for active PsA without any new safety signals in patients from daily clinical practice. CLINICAL TRIAL REGISTRATION: ClinicalTrials.gov identifier, NCT04758117.
Upadacitinib is an antirheumatic medical therapy approved for treating psoriatic arthritis with insufficient response to previous conventional or biological therapies (DMARD-IR). Psoriatic arthritis is a chronic inflammatory disease affecting the joints, spine, tendons/entheses, skin, nails and other parts of the musculoskeletal system. Early diagnosis and treatment initiation are essential for patients with psoriatic arthritis given the potentially irreversible damage to joints, spine, and entheses and the considerable impact on quality of life. The results presented in this manuscript help clinicians evaluate whether the efficacy and the safety profile of upadacitinib found in previous clinical trials can be reproduced in patients seen in daily clinical practice. This analysis presents descriptive data on the real-world efficacy and safety of upadacitinib, measured by clinical and patient-reported outcomes assessed in four visits over 24 weeks. In summary, our findings confirm the results of previous clinical trials showing that upadacitinib effectively reduces symptom severity of PsA and substantially increases the proportion of patients achieving treatment goals relevant to clinical practice, such as remission or very low disease activity. In addition, safety data were consistent with previous studies of upadacitinib in rheumatoid arthritis or psoriatic arthritis; no new risks to the patients' safety were identified.
RESUMEN
Several studies have shown that tapering or stopping disease-modifying anti-rheumatic drugs (DMARDs) in rheumatoid arthritis (RA) patients in sustained remission is feasible. However, tapering/stopping bears the risk of decline in physical function as some patients may relapse and face increased disease activity. Here, we analyzed the impact of tapering or stopping DMARD treatment on the physical function of RA patients. The study was a post hoc analysis of physical functional worsening for 282 patients with RA in sustained remission tapering and stopping DMARD treatment in the prospective randomized RETRO study. HAQ and DAS-28 scores were determined in baseline samples of patients continuing DMARD (arm 1), tapering their dose by 50% (arm 2), or stopping after tapering (arm 3). Patients were followed over 1 year, and HAQ and DAS-28 scores were evaluated every 3 months. The effect of treatment reduction strategy on functional worsening was assessed in a recurrent-event Cox regression model with a study-group (control, taper, and taper/stop) as the predictor. Two-hundred and eighty-two patients were analyzed. In 58 patients, functional worsening was observed. The incidences suggest a higher probability of functional worsening in patients tapering and/or stopping DMARDs, which is likely due to higher relapse rates in these individuals. At the end of the study, however, functional worsening was similar among the groups. Point estimates and survival curves show that the decline in functionality according to HAQ after tapering or discontinuation of DMARDs in RA patients with stable remission is associated with recurrence, but not with an overall functional decline.
RESUMEN
OBJECTIVE: Rheumatoid arthritis (RA) is characterized by erosive joint damage, deterioration of bone mass, and biomechanics. Preclinical evidence suggests a beneficial effect of Janus kinase inhibition (JAKi) on bone properties, but clinical data are scarce to date. In this study, we evaluated the effect of JAKi through baricitinib (BARI) on 1) volumetric bone mineral density (vBMD), bone microstructure, biomechanics, and erosion repair and 2) synovial inflammation in RA patients. METHODS: Prospective, single-arm, interventional, open-label, single-center phase 4 study in RA patients with pathological bone status and clinical indication of JAKi (BARE BONE trial). Participants received BARI (4 mg/day) over 52 weeks. To assess bone properties and synovial inflammation, high-resolution computed tomography scans and magnetic resonance imaging were performed at baseline (BL), week 24, and week 52. Clinical response and safety were monitored. RESULTS: Thirty RA patients were included. BARI significantly improved disease activity (Disease Activity Score in 28 joints using the erythrocyte sedimentation rate: 4.82 ± 0.90 to 2.71 ± 0.83) and synovial inflammation (RAMRIS synovitis score: 5.3 [4.2] to 2.7 [3.5]). We observed a significant improvement in trabecular vBMD with a mean change of 6.11 mgHA/mm3 (95% confidence interval [95% CI] 0.01-12.26). Biomechanical properties also improved with mean change from baseline in estimated stiffness of 2.28 kN/mm (95% CI 0.30-4.25) and estimated failure load of 98.8 N (95% CI 15.9-181.7). The number and size of erosions in the metacarpal joints remained stable. No new safety signals with BARI treatment were observed. CONCLUSION: Bones of RA patients improve with BARI therapy, as shown by an increase in trabecular bone mass and an improvement of biomechanical properties.
Asunto(s)
Antirreumáticos , Artritis Reumatoide , Humanos , Antirreumáticos/uso terapéutico , Artritis Reumatoide/diagnóstico por imagen , Artritis Reumatoide/tratamiento farmacológico , Artritis Reumatoide/patología , Fenómenos Biomecánicos , Inflamación/tratamiento farmacológico , Imagen por Resonancia Magnética/métodos , Estudios ProspectivosRESUMEN
Early and effective discrimination (triage) of patients with inflammatory rheumatic diseases (IRD) and other diseases (non-IRD) is essential for successful treatment and preventing damage. The aim of this study was to investigate diagnostic delays and pre-diagnosis treatment in patients newly presenting to rheumatology outpatient clinics. A total of 600 patients newly presenting to one university hospital and two non-academic centers were included. Time from onset of symptoms to rheumatology consultation "total delay" as well as medical treatment before consultation were recorded. Median time from symptom onset to rheumatologist appointment (total delay) was 30 weeks. Median time to online search, first physician appointment request and first physician appointment was 2, 4 and 5 weeks, respectively. Total delay was significantly shorter for IRD patients compared to non-IRD patients, 26 vs 35 weeks (p = 0.007). Only 17.7% of all patients and 22.9% of IRD patients had a delay of less than 12 weeks. Total delay was significantly lower in patients seen in non-academic centers compared to the university center, 20 vs 50 weeks (p < 0.0001). 32.2% of IRD patients received medical treatment that eased their symptoms prior to the rheumatology appointment. These findings highlight the persistent diagnostic delays in rheumatology; however, they also suggest that current triage strategies effectively lead to earlier appointments for IRD patients. Improvement of triage methods and pre-diagnosis treatment could decrease overall burden of disease in IRD patients.
Asunto(s)
Enfermedades Reumáticas , Reumatología , Humanos , Diagnóstico Tardío , Enfermedades Reumáticas/diagnóstico , Reumatólogos , Derivación y ConsultaRESUMEN
Introduction: Being able to independently determine vaccine induced antibody responses by minimal-invasive methods is of great interest to enable a flexible and effective vaccination strategy. This study aimed to evaluate (1) the accuracy, feasibility, usability and acceptability of capillary blood and saliva self-sampling to determine SARS-CoV-2 antibody responses in patients with immune-mediated inflammatory diseases (IMIDs) and health professionals (HP). Methods: IMID patients and HP having received two doses of SARS-CoV-2 vaccines, self-collected capillary blood (Tasso+) and saliva samples. Capillary samples were considered interchangeable with venous blood if three criteria were met: Spearman's correlation coefficient (r) > 0.8, non-significant Wilcoxon signed-rank test (i.e., p > 0.05), and a small bias or 95% of tests within 10% difference through Bland-Altman. Participants completed a survey to investigate self-sampling usability (system usability scale; SUS) and acceptability (net promoter score; NPS). Study personnel monitored correct self-sampling completion and recorded protocol deviations. Results: 60 participants (30 IMID patients and 30 HP) were analyzed. We observed interchangeability for capillary samples with an accuracy of 98.3/100% for Anti-SARS-CoV-2 IgG/IgA antibodies, respectively. Fifty-eight capillary blood samples and all 60 saliva samples were successfully collected within the first attempt. Usability of both self-sampling procedures was rated as excellent, with significantly higher saliva ratings (p < 0.001). Capillary self-sampling was perceived as significantly (p < 0.001) less painful compared to traditional venous blood collection. Participants reported a NPS for capillary and saliva self-sampling of +68% and +63%, respectively. The majority of both groups (73%) preferred capillary self-sampling over professional venous blood collection. Conclusion: Our results indicate that capillary self-sampling is accurate, feasible and preferred over conventional venous blood collection. Implementation could enable easy access, flexible vaccination monitoring, potentially leading to a better protection of vulnerable patient groups. Self-collection of saliva is feasible and safe however more work is needed to determine its application in clinical practice.
Asunto(s)
Vacunas contra la COVID-19 , COVID-19 , Humanos , COVID-19/diagnóstico , COVID-19/prevención & control , Saliva , Inmunogenicidad Vacunal , SARS-CoV-2 , Anticuerpos AntiviralesRESUMEN
Symptom checkers are increasingly used to assess new symptoms and navigate the health care system. The aim of this study was to compare the accuracy of an artificial intelligence (AI)-based symptom checker (Ada) and physicians regarding the presence/absence of an inflammatory rheumatic disease (IRD). In this survey study, German-speaking physicians with prior rheumatology working experience were asked to determine IRD presence/absence and suggest diagnoses for 20 different real-world patient vignettes, which included only basic health and symptom-related medical history. IRD detection rate and suggested diagnoses of participants and Ada were compared to the gold standard, the final rheumatologists' diagnosis, reported on the discharge summary report. A total of 132 vignettes were completed by 33 physicians (mean rheumatology working experience 8.8 (SD 7.1) years). Ada's diagnostic accuracy (IRD) was significantly higher compared to physicians (70 vs 54%, p = 0.002) according to top diagnosis. Ada listed the correct diagnosis more often compared to physicians (54 vs 32%, p < 0.001) as top diagnosis as well as among the top 3 diagnoses (59 vs 42%, p < 0.001). Work experience was not related to suggesting the correct diagnosis or IRD status. Confined to basic health and symptom-related medical history, the diagnostic accuracy of physicians was lower compared to an AI-based symptom checker. These results highlight the potential of using symptom checkers early during the patient journey and importance of access to complete and sufficient patient information to establish a correct diagnosis.
Asunto(s)
Inteligencia Artificial , Reumatología , Humanos , Reumatólogos , Encuestas y CuestionariosRESUMEN
Background: Concerns have been raised about the reduced immunogenicity of vaccines against SARS-CoV-2 in patients with immune-mediated inflammatory diseases and the higher risk of breakthrough infections. The objective of our study was to investigate the intensity and longevity of SARS-CoV-2 vaccination responses in patients with immune-mediated inflammatory diseases, and to assess the effects of diagnosis, treatment, and adapted vaccination schedules. Methods: SARS-CoV-2 IgG antibody response after SARS-CoV-2 vaccination was measured over time in a large prospective cohort of healthy controls and participants with immune-mediated inflammatory diseases (attending or admitted to affiliated centres) between Dec 15, 2020, and Dec 1, 2021. Cohort participants with immune-mediated inflammatory diseases and control participants with no diagnosis of immune-mediated inflammatory diseases, were eligible for this analysis. Demographic data and disease-specific data were collected using a questionnaire. Humoral response was compared across treatment and disease groups, and with respect to the receipt of additional vaccinations. SARS-CoV-2 antibody response was measured by ELISA using optical density ratio units and modelled over time with age and sex adjustment using mixed-effects models. Using these models, marginal mean antibody titres and marginal risks of a poor response (optical density ratio <1·1) were calculated for each week starting from week 8 after the first vaccination to week 40. Findings: Among 5076 individuals registered, 2535 participants with immune-mediated inflammatory diseases (mean age 55·0 [15·2] years; 1494 [58·9%] women and 1041 [41·1%] men) and 1198 healthy controls (mean age 40·7 [13·5] years; 554 [46·2%] women and 644 [53·8%] men) were included in this analysis. Mean antibody titres were higher in healthy controls compared with people with immune-mediated inflammatory diseases at all timepoints, with a peak antibody response in healthy controls (mean optical density ratio 12·48; 95% CI 11·50-13·53) of more than twice that in participants with immune-mediated inflammatory diseases (5·50; 5·23-5·77; mean difference 6·98; 5·92-8·04). A poor response to vaccination was observed in participants with immune-mediated inflammatory diseases who were taking B-cell inhibitors (peak mean difference from healthy controls 11·68; 10·07-13·29) and T-cell inhibitors (peakmean difference from healthy controls 10·43; 8·33-12·53). Mean differences in antibody responses between different immune-mediated inflammatory diseases were small. Participants with immune-mediated inflammatory diseases who were given a third vaccine dose had higher mean antibody titres than did healthy controls vaccinated with two vaccine doses at 40 weeks after the initial vaccination (mean difference 1·34; 0·01-2·69). Interpretation: People with immune-mediated inflammatory diseases show a lower and less durable SARS-CoV-2 vaccination response and are at risk of losing humoral immune protection. Adjusted vaccination schedules with earlier booster doses or more frequent re-doses, or both, could better protect people with immune-mediated inflammatory diseases. Funding: Deutsche Forschungsgemeinschaft, Bundesministerium für Bildung und Forschung, European Research Council, Innovative Medicine Initiative, Friedrich-Alexander-Universität Erlangen-Nürnberg, Else Kröner-Memorial Foundation.
RESUMEN
Introduction: Rheport is an online rheumatology referral system allowing automatic appointment triaging of new rheumatology patient referrals according to the respective probability of an inflammatory rheumatic disease (IRD). Previous research reported that Rheport was well accepted among IRD patients. Its accuracy was, however, limited, currently being based on an expert-based weighted sum score. This study aimed to evaluate whether machine learning (ML) models could improve this limited accuracy. Materials and methods: Data from a national rheumatology registry (RHADAR) was used to train and test nine different ML models to correctly classify IRD patients. Diagnostic performance was compared of ML models and the current algorithm was compared using the area under the receiver operating curve (AUROC). Feature importance was investigated using shapley additive explanation (SHAP). Results: A complete data set of 2265 patients was used to train and test ML models. 30.5% of patients were diagnosed with an IRD, 69.3% were female. The diagnostic accuracy of the current Rheport algorithm (AUROC of 0.534) could be improved with all ML models, (AUROC ranging between 0.630 and 0.737). Targeting a sensitivity of 90%, the logistic regression model could double current specificity (17% vs. 33%). Finger joint pain, inflammatory marker levels, psoriasis, symptom duration and female sex were the five most important features of the best performing logistic regression model for IRD classification. Conclusion: In summary, ML could improve the accuracy of a currently used rheumatology online referral system. Including further laboratory parameters and enabling individual feature importance adaption could increase accuracy and lead to broader usage.
RESUMEN
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.