Israel Medical Association Journal

Over the last decade the use of artificial intelligence (AI) has reformed academic research. While clinical diagnosis of psoriasis and psoriatic arthritis is largely straightforward, the determining factors of a clinical response to therapy, and specifically to biologic agents, have not yet been found. AI may meaningfully impact attempts to unravel the prognostic factors that affect response to therapy, assist experimental techniques being used to investigate immune cell populations, examine whether these populations are associated with treatment responses, and incorporate immunophenotype data in prediction models. The aim of this mini review was to present the current state of the AI-mediated attempts in the field. We executed a Medline search in October 2023. Selection and presentation of studies were conducted following the principles of a narrative–review design. We present data regarding the impact AI can have on the management of psoriatic disease by predicting responses utilizing clinical or biological parameters. We also reviewed the ways AI has been implemented to assist development of models that revolutionize the investigation of peripheral immune cell subsets that can be used as biomarkers of response to biologic treatment. Last, we discussed future perspectives and ethical considerations regarding the use of machine learning models in the management of immune-mediated diseases.

Objectives: To explore IL-17A-producing CD3+CD4+T cells in peripheral blood of patients with persistent AR and assess the degree of atopy, eosinophil count (Eo count), and bronchial hyper-responsiveness (BHR) to methacholine.

Methods: The study involved 61 patients and 30 controls. The percentage of CD3+CD4+IL-17A+T cells in peripheral blood was measured by flow cytometry, bronchial challenges with Mch were performed, as was skin prick tests with standard inhalant allergens, and Eo count was measured. Atopic status was determined by the number of positive SPT results and wheal mean diameter.

Results: A statistically significant difference in Th17 cell percentage was found in the AR and control groups (2.59 ± 1.32% and 1.24 ± 0.22% respectively, P = 0.001). Forty-one patients (67.2%) were polysensitized to indoor and outdoor allergens, while 20 (32.8%) had positive skin prick tests to indoor allergens. CD4+T cells were significantly higher in the patient group compared to the control group (2.91 ± 1.5% versus 1.91 ± 0.62%, P = 0.005), as was Eo count (4.48 ± 2.13 vs. 2.32 ± 1.83) (P = 0.0001). Forty-one in the AR group (67%) and 7 (23%) in the control group were Mch-positive (P = 0.001). The percentage of IL-17A-producing CD4+T cells was significantly higher in males compared to females (3.15 ± 1.8% versus 2.31 ± 0.9%, P = 0.02)

Conclusions: Polysensitized AR patients exhibited higher IL-17A-producing CD4+T cell levels and eosinophil counts. Male patients displayed a higher frequency of IL-17A-producing T cells. 

Objective: To evaluate the feasibility of using combined clinical and histomorphometric features to construct a prognostic score for the individual patient with localized renal cell carcinoma.

Patients and Methods: We studied 39 patients with pT1 and pT2 RCC who underwent radical nephrectomy between 1974 and 1983. Univariate and multivariate analyses were used to determine the association between various prognostic features and patient survival.

Results: The most important and independent predictors of survival were tumor angiogenesis (P=0.009), nuclear DNA ploidy (P=0.0071), mean nuclear area (P=0.013), and mean elongation factor (P=0.0346). Combination of these variables enabled prediction of outcome for the individual patient at a sensitivity and specificity of 78% and 89% respectively.

Conclusion: Our results indicate that no single parameter can accurately predict the outcome for patients with localized RCC. Combination of neovascularity, DNA content and morphometric shape descriptors enabled a more precise stratification of the patients into different risk categories.