POS0994 DEVELOPMENT OF AN AUTOMATED ALGORITHM BASED ON METHODS OF ARTIFICIAL INTELLIGENCE TO ASSIST IN THE PREDICTION OF CORRECT REFERRALS OF PSORIATIC ARTHRITIS AND AXIAL SPONDYLOARTHRITIS BY USING PATIENT HISTORY TEXTS

Background

Diagnosis and treatment of PsA and axSpA is often delayed due to missing clear diagnostic criteria and limitations in resources for referral to rheumatologist including high numbers of incorrect referrals. Primary care is usually provided by either general practitioner, dermatologists, or orthopedics. Clinical discriminators with a high specificity for rheumatic conditions include morning stiffness (MST; peripheral or axial, >30min). Artificial intelligence (AI) and natural language processing (NLP) methods offer algorithms for learning systems to recognize disease associated terms and classify clinical phenotypes using large data sets that may support early identification of patients with suspected diagnosis of PsA or axSpA.

Objectives

AI and NLP methods are used to identify patients with typical attributes for inflammation by using morning stiffness as one potential discriminating pattern, which can be detected automatically and might help to prioritize referral for rheumatologist appointments.

Methods

Within a multicentre observational study, patients with visits at the rheumatologist with a suspected diagnosis of PsA or axSpA from the referral primary care provider were recruited. All data on clinical examinations and findings were collected and evaluated by rheumatologists in focus on criteria for diagnosis of PsA/axSpA (gold standard for evaluation). Unstructured text from the patient history was used to extract diagnosis-relevant characteristics. The information extraction algorithms used NLP models to detect expert curated “morning stiffness” (MST) keywords and puts them into a contextualized framework that allows to capture possible negations.

Results

A total of 116 patients were recruited (73 female, 63%) with a median age of 42 (IQR: 34-54). 51 patients were referred as axSpA (44%) and 60 as PsA (52%) by primary care providers. After preselection for PsA and axSpA patients, we observed a 23% rate of referrals without rheumatic diagnosis. Only 7.1% of patients were admitted without signs of MST, 29% with axial MST, 35% with peripheral MST and 28% with both MST types. Average morning stiffness duration was recorded as 35 minutes; patients with a finally confirmed rheumatic diagnosis had a higher average MST duration reported (36 minutes) compared to patients without a confirmed diagnosis. Our AI assisted extraction of MST identified MST in 82.7% of patient history texts. In 75% NLP methods correctly identified the negation of MST symptoms (6 of 8), and 94% of MST was detected when both axial and peripheral joints were affected (30 of 32). Manual inspection of 20 patient history reports where MST was not detected by our automated algorithm revealed that 17 reports did not contain information about MST and three mention unspecific early morning discomfort, without mention of MST.

Conclusion

The high rate of correct detection of MST from patient history text using NLP methods allowed us to assess the potential for NLP models to support automated analysis of patient reports to facilitate intelligent patient referral.

Acknowledgements

We thank the Fraunhofer Excellence Cluster for Immune-Mediated Diseases CIMD for the financial support.

Disclosure of Interests

None declared

Invited article: Electric solar wind sail: toward test missions

The electric solar wind sail (E-sail) is a space propulsion concept that uses the natural solar wind dynamic pressure for producing spacecraft thrust. In its baseline form, the E-sail consists of a number of long, thin, conducting, and centrifugally stretched tethers, which are kept in a high positive potential by an onboard electron gun. The concept gains its efficiency from the fact that the effective sail area, i.e., the potential structure of the tethers, can be millions of times larger than the physical area of the thin tethers wires, which offsets the fact that the dynamic pressure of the solar wind is very weak. Indeed, according to the most recent published estimates, an E-sail of 1 N thrust and 100 kg mass could be built in the rather near future, providing a revolutionary level of propulsive performance (specific acceleration) for travel in the solar system. Here we give a review of the ongoing technical development work of the E-sail, covering tether construction, overall mechanical design alternatives, guidance and navigation strategies, and dynamical and orbital simulations.

[Optimization of verification photographs in thoracic wall irradiations (so-called tangential field technique) in breast carcinoma. A short technical-methodical report]

When irradiating under high voltage condition, verification photographs prove to be difficult to take if the Gantry position is not aligned to 0 degree respectively 180 degrees, since the patient is being irradiated diagonally. Under these conditions it is extremely difficult to align the X-ray-cartridge vertically to the central beam of the therapeutic radiation. This results in, amongst others, misprojections, so that definite dimensions of portrayed organ structures become practical impossible to determine. This paper presented describes how we have solved these problems on our high voltage units (tele-gamma cobalt unit and linear-accelerator). By using simple accessories, determination of dimensions of organ structures, as shown on the verification photographs, are made possible. We illustrate our method by using the so-called tangential fields technique when irradiating mamma carcinoma.