1
|
Motta F, Morandini P, Maffia F, Vecellio M, Tonutti A, De Santis M, Costanzo A, Puggioni F, Savevski V, Selmi C. Connecting the use of innovative treatments and glucocorticoids with the multidisciplinary evaluation through rule-based natural-language processing: a real-world study on patients with rheumatoid arthritis, psoriatic arthritis, and psoriasis. Front Med (Lausanne) 2023; 10:1179240. [PMID: 37387783 PMCID: PMC10301822 DOI: 10.3389/fmed.2023.1179240] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/03/2023] [Accepted: 05/15/2023] [Indexed: 07/01/2023] Open
Abstract
Background The impact of a multidisciplinary management of rheumatoid arthritis (RA), psoriatic arthritis (PsA), and psoriasis on systemic glucocorticoids or innovative treatments remains unknown. Rule-based natural language processing and text extraction help to manage large datasets of unstructured information and provide insights into the profile of treatment choices. Methods We obtained structured information from text data of outpatient visits between 2017 and 2022 using regular expressions (RegEx) to define elastic search patterns and to consider only affirmative citation of diseases or prescribed therapy by detecting negations. Care processes were described by binary flags which express the presence of RA, PsA and psoriasis and the prescription of glucocorticoids and biologics or small molecules in each cases. Logistic regression analyses were used to train the classifier to predict outcomes using the number of visits and the other specialist visits as the main variables. Results We identified 1743 patients with RA, 1359 with PsA and 2,287 with psoriasis, accounting for 5,677, 4,468 and 7,770 outpatient visits, respectively. Among these, 25% of RA, 32% of PsA and 25% of psoriasis cases received biologics or small molecules, while 49% of RA, 28% of PsA, and 40% of psoriasis cases received glucocorticoids. Patients evaluated also by other specialists were treated more frequently with glucocorticoids (70% vs. 49% for RA, 60% vs. 28% for PsA, 51% vs. 40% for psoriasis; p < 0.001) as well as with biologics/small molecules (49% vs. 25% for RA, 64% vs. 32% in PsA; 51% vs. 25% for psoriasis; p < 0.001) compared to cases seen only by the main specialist. Conclusion Patients with RA, PsA, or psoriasis undergoing multiple evaluations are more likely to receive innovative treatments or glucocorticoids, possibly reflecting more complex cases.
Collapse
Affiliation(s)
- Francesca Motta
- Department of Biomedical Sciences, Humanitas University, Pieve Emanuele, Milan, Italy
- Division of Rheumatology and Clinical Immunology, IRCCS Humanitas Research Hospital, Rozzano, Milan, Italy
| | - Pierandrea Morandini
- Artificial Intelligence Center, IRCCS Humanitas Research Hospital, Rozzano, Milan, Italy
| | - Fiore Maffia
- Artificial Intelligence Center, IRCCS Humanitas Research Hospital, Rozzano, Milan, Italy
| | - Matteo Vecellio
- Division of Rheumatology and Clinical Immunology, IRCCS Humanitas Research Hospital, Rozzano, Milan, Italy
- Wellcome Centre for Human Genetics, University of Oxford, Oxford, United Kingdom
- Centro Ricerche Fondazione Italiana Ricerca Sull'Artrite (FIRA), Fondazione Pisana per la Scienza ONLUS, San Giuliano Terme (Pisa), Milan, Italy
| | - Antonio Tonutti
- Department of Biomedical Sciences, Humanitas University, Pieve Emanuele, Milan, Italy
- Division of Rheumatology and Clinical Immunology, IRCCS Humanitas Research Hospital, Rozzano, Milan, Italy
| | - Maria De Santis
- Department of Biomedical Sciences, Humanitas University, Pieve Emanuele, Milan, Italy
- Division of Rheumatology and Clinical Immunology, IRCCS Humanitas Research Hospital, Rozzano, Milan, Italy
| | - Antonio Costanzo
- Department of Biomedical Sciences, Humanitas University, Pieve Emanuele, Milan, Italy
- Division of Dermatology, IRCCS Humanitas Research Hospital, Rozzano, Milan, Italy
| | - Francesca Puggioni
- Division of Asthma, Allergy and Personalized Medicine, IRCCS Humanitas Research Hospital, Rozzano, Milan, Italy
| | - Victor Savevski
- Artificial Intelligence Center, IRCCS Humanitas Research Hospital, Rozzano, Milan, Italy
| | - Carlo Selmi
- Department of Biomedical Sciences, Humanitas University, Pieve Emanuele, Milan, Italy
- Division of Rheumatology and Clinical Immunology, IRCCS Humanitas Research Hospital, Rozzano, Milan, Italy
| |
Collapse
|
2
|
Seppen BF, Verkleij SJ, Wiegel J, ter Wee MM, Nurmohamed MT, Bos WH. Probability of Medication Intensifications in Rheumatoid Arthritis Patients With Low Disease Activity Scores on Their Patient-Reported Outcomes: A Medical-Records Review Study. J Clin Rheumatol 2022; 28:397-401. [PMID: 35905459 PMCID: PMC9704811 DOI: 10.1097/rhu.0000000000001883] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/15/2022]
Abstract
BACKGROUND Patients with rheumatoid arthritis require frequent consultations to monitor disease activity and intensify medication when treatment targets are not met. However, because most patients are in remission during follow-up, it should be possible to reduce the number of consultations for them. Electronic patient-reported outcomes (ePROs) could be used to identify patients who meet their treatment goal and who could therefore be eligible to skip their visit. OBJECTIVE The aim of this study was to assess the probability that patients with low disease activity scores on their ePROs do not need a disease-modifying antirheumatic drug (DMARD) or steroid intensification in the first 2 weeks after completion of the ePROs. METHODS This medical-records review study compared results of ePROs answered during routine care with DMARD or steroid intensifications collected from anonymized electronic medical record at Reade. The primary outcome was the positive predictive value (PPV) of having a low disease activity score on an ePRO for not receiving a DMARD or steroid intensifications within 2 weeks. The 3 studied ePROs (and respective low disease activity outcome) were the Routine Assessment of Patient Index Data 3 (RAPID3) (score <2), Patient Acceptable Symptom State (PASS) (yes), and the flare question (no). The secondary aim of the study was to assess which combination of ePROs resulted in the best PPV for DMARD or steroid intensifications. RESULTS Of the 400 randomly selected records, ultimately 321 were included (302 unique patients). The PPV of a RAPID3 <2, being in PASS, and a negative answer on the flare question were, respectively, 99%, 95%, and 83% to not receive a DMARD or steroid intensification within 2 weeks. The combination of a RAPID3 <2 and a negative flare question resulted in a PPV of 100%; this combination was present in 29% (93/321) of the total study population. CONCLUSION The RAPID3, PASS, and flare question have a high diagnostic accuracy to identify individuals who will not receive a DMARD or steroid intensification in the following 2 weeks. The combination of the RAPID3 and flare question yielded the best combination of diagnostic accuracy and highest percentage of patients who could be eligible to skip a visit. These results suggest that accurate identification of patients who meet their treatment goal with ePROs is possible.
Collapse
Affiliation(s)
| | | | - Jimmy Wiegel
- From the Reade Rheumatology
- Department of Rheumatology, Amsterdam UMC
| | - Marieke M. ter Wee
- Department of Epidemiology and Data Science, Amsterdam UMC, Vrije Universiteit Amsterdam, Amsterdam, the Netherlands
| | | | - Wouter H. Bos
- From the Reade Rheumatology
- Department of Rheumatology, Amsterdam UMC
| |
Collapse
|
4
|
Real-world evidence in rheumatic diseases: relevance and lessons learnt. Rheumatol Int 2019; 39:403-416. [PMID: 30725156 DOI: 10.1007/s00296-019-04248-1] [Citation(s) in RCA: 13] [Impact Index Per Article: 2.6] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/25/2018] [Accepted: 01/28/2019] [Indexed: 12/17/2022]
Abstract
An emerging trend in the medical literature, including the Rheumatology literature, is that of accumulating large, multicentric, multi-national data based on registries of patients seen in real life situations. Such real-world evidence (RWE) may help provide valuable insights into the long-term outcomes of disease in unselected patients seen in daily practice, including patients belonging to vulnerable populations such as extremes of age, during pregnancy and lactation. Evidences gathered from real life practice settings can help understand drug prescription patterns, including adherence to treatment guidelines, cost-effectiveness of therapy, and real-life long-term outcomes, and adverse effects of treatment with particular medications. Registry-based data also helps analyze comorbidities in patients with rheumatic diseases, and their impact on quality of life, morbidity and mortality. Traditionally, a randomized controlled trial (RCT), or systematic reviews of multiple, homogenous RCTs, have been considered the cornerstone of evidence-based medicine, and RWE does, at times, provide differing viewpoints from the results of particular drugs in clinical trial settings. Therefore, in the present day, it is prudent to consider the complementary nature of information derived from RWE to that obtained from rigorous, clinical trial settings. Future guidelines for disease management may consider it relevant to include information from RWE in addition to that available from clinical trials, to help devise management guidelines that are harmonious with routine practice settings.
Collapse
|