Predicting the conversion from clinically isolated syndrome to multiple sclerosis: An explainable machine learning approach

INTRODUCTION

Predicting the conversion of clinically isolated syndrome (CIS) to clinically definite multiple sclerosis (CDMS) is critical to personalizing treatment planning and benefits for patients. The aim of this study is to develop an explainable machine learning (ML) model for predicting this conversion based on demographic, clinical, and imaging data.

METHOD

The ML model, Extreme Gradient Boosting (XGBoost), was employed on the public dataset of 273 Mexican mestizo CIS patients with 10-year follow-up. The data was divided into a training set for cross-validation and feature selection, and a holdout test set for final testing. Feature importance was determined using the SHapley Additive Explanations library (SHAP). Then, two experiments were conducted to optimize the model's performance by selectively adding variables and selecting the most contributive variables for the final model.

RESULTS

Nine variables including age, gender, schooling, motor symptoms, infratentorial and periventricular lesion at imaging, oligoclonal band in cerebrospinal fluid, lesion and symptoms types were significant. The model achieved an accuracy of 83.6 %, AUC of 91.8 %, sensitivity of 83.9 %, and specificity of 83.4 % in cross-validation. In the final testing, the model achieved an accuracy of 78.3 %, AUC of 85.8 %, sensitivity of 75 %, and specificity of 81.1 %. Finally, a web-based demo of the model was created for testing purposes.

CONCLUSION

The model, focusing on feature selection and interpretability, effectively stratifies risk for treatment decisions and disability prevention in MS patients. It provides a numerical risk estimate for CDMS conversion, enhancing transparency in clinical decision-making and aiding in patient care.

Congenital Heart Defects in Pregnancies Conceived by Assisted Reproductive Technology: Comparing Functional and Structural Defects

Introduction Congenital heart defects (CHD) are one of the most common congenital anomalies, and their association with assisted reproductive technology (ART) is controversial in different populations. The purpose of this study was to evaluate this association and to provide information about the necessity of specialized echocardiography during pregnancy with ART. Methods This retrospective study was performed on all pregnancies conceived by ART and referred for fetal echocardiography to the Rasoul Akram and Akbar Abadi hospitals in Tehran, Iran. A total of 109 patients were enrolled in the study (56 in the ART group and 53 in the non-ART). Two-dimensional and color Doppler echocardiography were performed on all patients to identify heart problems and anomalies and medical records of the patients were reviewed. The outcome was considered the presence of functional and structural heart defects on echocardiography. Results The study groups were similar in terms of maternal age and GA. The ART group consisted of 31 singletons (55%) and 25 multiples (45%). All pregnancies in the non-ART group were singletons. Following in vitro fertilization (33%), ovulation induction (25%) was the next most used method. The findings of echocardiography were one atrial septal defect (ASD) in ART and one in non-ART, six ventricular septal defects (VSD) in ART and three in non-ART, and one ASD and VSD in the ART group. These structural abnormalities showed no difference in the two groups (P value = 0.58). There was no significant difference in rhythm between the two groups (P = 0.51). Echocardiographic indices of both groups did not differ statistically except in the TR-PG index (P value = 0.02). Conclusions The structural defects of the two groups were not different, and no heart dysfunction was observed in ART fetuses. There was no association between ART and CHD in our study. We concluded that echocardiography by pediatric cardiologists is not necessary for these fetuses.

In Vitro Antileishmanial Activity of Achillea santolina Essential Oil against Leishmania infantum Promastigote by Methylthiazole Tetrazolium (MTT) and Trypan Blue Colorimetric Methods

Leishmaniasis causes parasitic infections, especially in developing countries. The disease has not yet been controlled because of the absence of an effective vaccine and low-cost treatment. Achillea santolina essential oil (ASEO) might control the disease as it has antimicrobial properties. This study investigated the in vitro antileishmanial activity of ASEO against Leishmania infantum promastigote using the methylthiazole tetrazolium (MTT) and trypan blue colorimetric methods. The standard strain of L. infantum (MCAN/IR/96/LON49) promastigotes was prepared and cultured in a 96-well Novy-MacNeal-Nicolle (NNN) medium. The effects of different concentrations of saline, ASEO, and glucantime (10, 50, 100, 200, 500, and 1000 mg/mL) were examined in 24-, 48-, and 72-hour intervals using the MTT and trypan blue test methods.The use of ASEO reduced viability in all concentrations compared to the control group in times of 48 (p<0.05) and 72 h (p<0.05). Treatment with glucantime and ASEO had similar efficiency with the concentration of 1000 mL/mg in both methods after 72 h. The results showed that viability was significantly lower in the ASEO group with increases in time using both methods (p<0.05). Cohen's Kappa coefficient showed a significant agreement between the obtained results for the two methods (Kappa=0.856; p<0.001).In sum, the results showed in vitro antileishmanial activity of ASEO, but more clinical studies are needed to confirm the efficiency. ASEO can be used as an agent and/or in combination with synthetic agents for the treatment of leishmaniasis disease.

Mendelian susceptibility to mycobacterial disease: Clinical and immunological findings of patients suspected for IL12Rβ1 deficiency

BACKGROUND

Mendelian susceptibility to mycobacterial disease (MSMD) is characterized by increased susceptibility to weakly virulent mycobacteria (Bacillus Calmette-Guérin [BCG] vaccines and environmental mycobacteria), Mycobacterium tuberculosis, Candida spp. and Salmonella spp. The aim of this study is to evaluate clinical features and immunological findings of MSMD patients with interleukin 12 receptor beta 1 (IL12Rβ1) deficiency.

METHODS

Among 117 screened patients with BCG infection following vaccination, 23 suspected MSMD subjects were recruited to this study by the exclusion of severe combined immunodeficiencies and chronic granulomatous diseases. Flow cytometric assessment for surface expression of IL12Rβ1 was performed. Moreover, the clinical and immunological data from the patients was evaluated.

RESULTS

A significant decrease (less than 1%) in the surface expression of IL12Rβ1 was reported in six cases which showed a significant increase in the count of lymphocytes (p=0.009) and CD8⁺ T cells (p=0.008) as compared to MSMD subjects with normal expression of surface IL12Rβ1. The frequency of disseminated BCGosis (50% vs. 20%, p=0.29), recurrent infection (83.3% vs. 40%, p=0.14) and salmonellosis (33.3% vs. 0.0%, p=0.07) was higher in IL12Rβ1 deficient subjects than IL12Rβ1 sufficient individuals.

CONCLUSION

MSMD patients with childhood onset of mycobacteriosis (mostly after BCG vaccination) and recurrent salmonellosis could be evaluated for IL12Rβ1 expression with flow cytometry for punctual diagnosis.

Automatic segmentation of inorganic nanoparticles in BF TEM micrographs

Transmission electron microscopy (TEM) represents a unique and powerful modality for capturing spatial features of nanoparticles, such as size and shape. However, poor statistics arise as a key obstacle, due to the challenge in accurately and automatically segmenting nanoparticles in TEM micrographs. Towards remedying this deficit, we introduce an automatic particle picking device that is based on the concept of variance hybridized mean local thresholding. Validation of this new segmentation model is accomplished by applying a program written in Matlab to a database of 150 bright field TEM micrographs containing approximately 2,000 nanoparticles. We compare the results to global thresholding, local thresholding, and manual segmentation. It is found that this novel automatic particle picking device reduces false positives and false negatives significantly, while increasing the number of individual particles picked on regions of particle overlap.

Synthesis, characterization and pH-controllable methotrexate release from biocompatible polymer/silica nanocomposite for anticancer drug delivery

The objective of this study was to develop pH-responsive silica nanoparticles by imidazole-based ionic liquid for controlled release of methotrexate. In this article, we synthesized pH-responsive cationic silica nanoparticles by graft copolymerization of vinyl functionalized silica nanoparticles and methacrylic acid (MAA) monomer. Imidazole-based ionic liquid (Im-IL) was verified by (1)HNMR and Fourier-transform infrared (FTIR) spectroscopy. The synthesized functionalized silica particles were characterized and confirmed by various technologies including the scanning electron microscopy (SEM), the infrared spectroscopy (IR) and the thermogravimetric analysis (TGA). SEM results reveal the uniformity in size/shape of silica particles. This nanosystem is modified for targeted delivery of an anticancer agent methotrexate. The nanocomposite-MTX complex was formed at physiological pH (7.4) due to the electrostatic interactions between anionic carboxylic group of MTX molecules and cationic rings in carrier, while, the release of which can be achieved through the cleavage of the nanocomposite-MTX complex by protonation of carboxyl groups in the MTX segment that are sensitive to variations in external pH at weak acidic conditions. FT-IR spectroscopy showed the presence of light interactions between the silicate silanols and the drug. MCF7 cells were incubated with the MTX-free nanocomposite and MTX-loaded nanocomposite at various concentrations for 24, 48 and 72 h, and the data showed that the nanocomposites themselves did not affect the growth of MCF7 cells. Antitumor activity of the MTX-loaded nanocomposites against the cells was kept over the whole experiment process. The results showed that the MTX could be released from the fibers without losing cytotoxicity.

Size- and shape-dependent separation of TiO2 colloidal sub-populations with gravitational field flow fractionation

The simplest field flow fractionation technique, which uses the earth's gravity as the external field is applied to isolate two populations, which differ in both shape and size, from a polydisperse sub-micron TiO2 powder of homogenous density. The fraction eluted first is spherical with an average diameter of 0.31 microm while the second fraction is ellipsoidal and can be associated with a 0.45 microm hydrodynamic diameter. Elution conditions appeared to be very sensitive to electrolyte and surfactant characteristics in the carrier phase as well as on the sample concentration. Using 25 microl (1%, w/w) sample suspension, separations of spherical from ovoid particles was performed in almost 2 h with a mobile phase of 0.001 M KNO3-0.01% (v/v) Fl-70 in water in a 0.025-cm thick channel made of polystyrene walls.

Experimental design methodology applied to the study of channel dimensions on the elution of red blood cells in gravitational field flow fractionation

Field flow fractionation (FFF) separation techniques have gained considerable success with micron-sized species. Living red blood cells (RBCs) of any origin have emerged as ideal models for cell separation development. Their elution mode is now described as "Lift-Hyperlayer". Certain separator dimension parameters are known to play a key role in the separation and band spreading process. Systematic studies of channel dimensions effects on RBC retention, band spreading, peak capacity and on a novel parameter described as "Particle Selectivity" were set up by means of a two-level factorial experimental design. From experimental results and statistical calculations it is confirmed that channel thickness plays a major role in retention ratio, peak variance, peak capacity and particle selectivity. Channel breadth strongly influences plate height, with lower impact on peak capacity and particle selectivity. Retention ratio, peak variance and peak capacity observed results are modulated by second-order interactions between channel dimensions. Preliminary rules for channel configurations are therefore set up and depend on separation goals. It is shown that a very polydisperse population is best disentangled in a thin and narrow channel whatever its length. If a mixture of many different micron-sized species is considered (each of limited polydispersities); a thick and broad channel should be preferred, with length modulating peak capacity to disentangle this polymodal mixture.

TiO2 colloidal suspension polydispersity analysed with sedimentation field flow fractionation and electron microscopy

Sedimentation field flow fractionation (SdFFF) operated at multi gravitational field is used to analyse a highly polydisperse TiO2 colloidal suspension. From the initial sample, time dependent eluted fractions are collected and submitted to electron microscopy (EM) shape and size analysis. To assess the accuracy of FFF in determining the average size of the different fractions, these are re-introduced into the channel by means of two different procedures, the on-channel concentration of the fractions and the direct re-injection of pre-concentrated fractions (DRI). Both methods appear accurate to determine the average size of every fraction, associated to a lower recovery in the case of DRI. The fractogram band spreading characteristics of the re-introduced fractions are correlated to the particle size distribution measured by EM. After density determination of fractionated particles, the fractogram is calibrated in terms of size and size distribution using data obtained from EM for each fraction. Quantitative analyses, based on particle counting showed high recovery (80-90%) of the eluted species. However, this loss limited the possibility to extend signal information to a quantitative one.