Predicting the Tumour Response to Radiation by Modelling the Five Rs of Radiotherapy Using PET Images

Despite the intensive use of radiotherapy in clinical practice, its effectiveness depends on several factors. Several studies showed that the tumour response to radiation differs from one patient to another. The non-uniform response of the tumour is mainly caused by multiple interactions between the tumour microenvironment and healthy cells. To understand these interactions, five major biologic concepts called the "5 Rs" have emerged. These concepts include reoxygenation, DNA damage repair, cell cycle redistribution, cellular radiosensitivity and cellular repopulation. In this study, we used a multi-scale model, which included the five Rs of radiotherapy, to predict the effects of radiation on tumour growth. In this model, the oxygen level was varied in both time and space. When radiotherapy was given, the sensitivity of cells depending on their location in the cell cycle was taken in account. This model also considered the repair of cells by giving a different probability of survival after radiation for tumour and normal cells. Here, we developed four fractionation protocol schemes. We used simulated and positron emission tomography (PET) imaging with the hypoxia tracer 18F-flortanidazole (18F-HX4) images as input data of our model. In addition, tumour control probability curves were simulated. The result showed the evolution of tumours and normal cells. The increase in the cell number after radiation was seen in both normal and malignant cells, which proves that repopulation was included in this model. The proposed model predicts the tumour response to radiation and forms the basis for a more patient-specific clinical tool where related biological data will be included.

Towards a universal definition of disease activity score thresholds: the AS135 score

OBJECTIVES

Many study groups have developed scores to reflect disease activity. The result of this fragmented process is a multitude of disease activity scores, even for a single disease. We aimed to identify and standardise disease activity scores in rheumatologyMETHODS: We conducted a literature review on disease activity criteria using both a manual approach and in-house computer software (BIBOT) that applies natural language processing to automatically identify and interpret important words in abstracts published in English between 1.1.1975 and 31.12.2018. We selected activity scores with cut-off values divided into four classes (remission and low, moderate and high disease activity). We used a linear interpolation to map disease activity scores to our new score, the AS135, and developed a smartphone application to perform the conversion.

RESULTS

A total of 108 activity criteria from various fields were identified, but it was in rheumatology that we found the most pronounced separation into four classes. We built the AS135 score modification for each selected score using a linear interpolation of the existing criteria. The score modification was defined on the interval [0,10], and values of 1, 3 and 5 were used as thresholds. These arbitrary thresholds were then associated with the thresholds of the existing criteria, and an interpolation was calculated, allowing conversion of the existing criteria into the AS135 criterion. Finally, we created a mobile application.

CONCLUSIONS

We developed an application for clinicians that enables the use of a single disease activity score for different inflammatory rheumatic diseases using an intuitive scale.

New criteria and new methodological tools for devising criteria sets of inflammatory rheumatic diseases

Rheumatologists use classification criteria to separate patients with inflammatory rheumatic diseases (IRD). They change over time, and the concepts of the diseases also change. The paradigm is currently moving as the goal of classification in the future will be more to select which patients may be relevant for a specific treatment rather than to describe their characteristics. Therefore, the challenge will be to reclassify multifactorial diseases on the basis of their biological mechanisms rather than their clinical phenotype. Currently, various projects are trying to reclassify diseases using bioinformatics approaches and in the near future the use of advanced machine learning algorithms with large omics datasets could lead to new classification models not only based on a clinical phenotype but also on complex biological profile and common sensitivity to targeted treatment. These models would highlight common biological pathways between patients classified in the same cluster and provide a deep understanding of the mechanisms involved in the patient's clinical phenotype. Such approaches would ultimately lead to classification models that rely more on biological causes than on symptoms. This overview on current classification of subgroups of IRD summarises the classification criteria that we use routinely, and how we will classify IRD in the future using bioinformatics and artificial intelligence techniques.

THU0617-HPR TOWARDS A UNIVERSAL DEFINITION OF DISEASE ACTIVITY SCORES THRESHOLDS

Background:

For rheumatologists monitoring patients with various diseases and dealing with multiple scores with different maximum values (9 for RA-DAS, 6.4 for AS-DAS and 60 for PMR-AS) and values thresholds to characterize the different levels of disease activity (low, intermediate and high) can be a tedious task. The same problematic could arise in other specialty than rheumatology. Normalization of these scores seems to be necessary to facilitate daily clinical practice (1).

Objectives:

To indentify and standardize scores of activity of inflammatory diseases.

Methods:

We conducted a literature review on activity criteria using both a manual approach and the BIBOT software (2) published in English between 1.1.1975 and 31.12.2018. Within all extracted disease activity scores, we selected those with cut off values in four classes (remission, low, moderate and high disease activity). We used a linear interpolation to map all these disease activity scores to our new score, the AS-135, and developed a smart-phone application to perform the conversion automatically.

Results:

1068 articles were analyzed by BIBOT, 86 were excluded on the basis of the language used for their writing and 11 were excluded on the basis of their publication date. 599 were selected based on their titles, abstracts and keywords. 108 activity criteria from various fields (rheumatology, dermatology, gastroenterology, psychiatry, neurology and pneumology) were identified, but it is in rheumatology that we find separation into four classes. 10 scores met our inclusion criteria and were implemented in the Android app. These are: DAS28 (ESR), DAS28 (CRP), SDAI, ASDAS (ESR), ASDAS (CRP), ESSDAI, SLEDAI-2K, DAPSA, PMR-AS (ESR) and PMR-AS (CRP). We built the AS135 score modification for each selected score using a linear interpolation of the existing criteria. It was defined on the interval [0,10] and values 1, 3 and 5 were used as thresholds. These arbitrary thresholds are then associated with the thresholds of the existing criteria and an interpolation can be calculated, allowing the conversion of the existing criteria into AS135 criterion. We have finally created a mobile application that allows each user to obtain both the original value of the activity criterion.

Conclusion:

We have created a mobile application that allows any user to obtain in a simple way the level of disease activity, whatever the criterion used to describe it, since the application returns, in addition to the value of the activity criterion calculated from data returned by the physician, the transformation of this value into AS135 criterion and its interpretation in terms of level of activity of the pathology. The application is now available for Android devices and we plan to start developing a version for iOS devices.

References:

[1]Saraux L, Devauchelle-Pensec V, Saraux A. Plea for standardization of disease activity scores. Rheumatol Oxf Engl. 2019 Aug 1;58(8):1500–1

[2]Orgeolet L, Foulquier N, Misery L, Redou P, Pers J-O, Devauchelle-Pensec V, et al. Can artificial intelligence replace manual search for systematic literature? Review on cutaneous manifestations in primary Sjögren’s syndrome. Rheumatol Oxf Engl. 2019 Aug 31;

Disclosure of Interests:

None declared

Can artificial intelligence replace manual search for systematic literature? Review on cutaneous manifestations in primary Sjögren’s syndrome

Objectives

Manual systematic literature reviews are becoming increasingly challenging due to the sharp rise in publications. The primary objective of this literature review was to compare manual and computer software using artificial intelligence retrieval of publications on the cutaneous manifestations of primary SS, but we also evaluated the prevalence of cutaneous manifestations in primary SS.

Methods

We compared manual searching and searching with the in-house computer software BIbliography BOT (BIBOT) designed for article retrieval and analysis. Both methods were used for a systematic literature review on a complex topic, i.e. the cutaneous manifestations of primary SS. Reproducibility was estimated by computing Cohen’s κ coefficients and was interpreted as follows: slight, 0–0.20; fair, 0.21–0.40; moderate, 0.41–0.60; substantial, 0.61–0.80; and almost perfect, 0.81–1.

Results

The manual search retrieved 855 articles and BIBOT 1042 articles. In all, 202 articles were then selected by applying exclusion criteria. Among them, 155 were retrieved by both methods, 33 by manual search only, and 14 by BIBOT only. Reliability (κ = 0.84) was almost perfect. Further selection was performed by reading the 202 articles. Cohort sizes and the nature and prevalence of cutaneous manifestations varied across publications. In all, we found 52 cutaneous manifestations reported in primary SS patients. The most described ones were cutaneous vasculitis (561 patients), xerosis (651 patients) and annular erythema (215 patients).

Conclusion

Among the final selection of 202 articles, 155/202 (77%) were found by the two methods but BIBOT was faster and automatically classified the articles in a chart. Combining the two methods retrieved the largest number of publications.

Pathogenesis-based treatments in primary Sjogren's syndrome using artificial intelligence and advanced machine learning techniques: a systematic literature review

Big data analysis has become a common way to extract information from complex and large datasets among most scientific domains. This approach is now used to study large cohorts of patients in medicine. This work is a review of publications that have used artificial intelligence and advanced machine learning techniques to study physio pathogenesis-based treatments in pSS. A systematic literature review retrieved all articles reporting on the use of advanced statistical analysis applied to the study of systemic autoimmune diseases (SADs) over the last decade. An automatic bibliography screening method has been developed to perform this task. The program called BIBOT was designed to fetch and analyze articles from the pubmed database using a list of keywords and Natural Language Processing approaches. The evolution of trends in statistical approaches, sizes of cohorts and number of publications over this period were also computed in the process. In all, 44077 abstracts were screened and 1017 publications were analyzed. The mean number of selected articles was 101.0 (S.D. 19.16) by year, but increased significantly over the time (from 74 articles in 2008 to 138 in 2017). Among them only 12 focused on pSS but none of them emphasized on the aspect of pathogenesis-based treatments. To conclude, medicine progressively enters the era of big data analysis and artificial intelligence, but these approaches are not yet used to describe pSS-specific pathogenesis-based treatment. Nevertheless, large multicentre studies are investigating this aspect with advanced algorithmic tools on large cohorts of SADs patients.

Multi-Scale Modeling and Oxygen Impact on Tumor Temporal Evolution: Application on Rectal Cancer During Radiotherapy

We present a multi-scale approach of tumor modeling in order to predict its evolution during radiotherapy. Within this context we focus on three different scales of tumor modeling: microscopic (individual cells in a voxel), mesoscopic (population of cells in a voxel) and macroscopic (whole tumor), with transition interfaces between these three scales. At the cellular level, the description is based on phase transfer probabilities in the cellular cycle. At the mesoscopic scale we represent populations of cells according to different stages in a cell cycle. Finally, at the macroscopic scale, the tumor description is based on the use of FDG PET image voxels. These three scales exist naturally: biological data are collected at the macroscopic scale, but the pathological behavior of the tumor is based on an abnormal cell-cycle at the microscopic scale. On the other hand, the introduction of a mesoscopic scale is essential in order to reduce the gap between the two extreme, in terms of resolution, description levels. It also reduces the computational burden of simulating a large number of individual cells. As an application of the proposed multi-scale model, we simulate the effect of oxygen on tumor evolution during radiotherapy. Two consecutive FDG PET images of 17 rectal cancer patients undergoing radiotherapy are used to simulate the tumor evolution during treatment. The simulated results are compared with those obtained on a third FDG PET image acquired two weeks after the beginning of the treatment.