International Journal of Clinical Research and Medical Sciences

Vol. 1 No. 2

2026
June 2026 · 6 articles · Volume 1, Issue 2
Back to archives
ISSUE OVERVIEW

Intelligent systems. Real-world impact.

This issue of the International Journal of Clinical Research and Medical Sciences (IJCRMS) brings together a diverse range of research contributions spanning clinical medicine, pharmaceutical sciences, healthcare systems, medical informatics, and inclusive education. The featured studies investigate multimodal artificial intelligence for pharmaceutical representation learning, plant-derived therapeutic candidate discovery through protease-targeted screening, rehabilitation workforce readiness in acute care settings, and machine learning-based approaches for hematological malignancy identification. Additionally, the issue explores strategies for improving science access for learners with extensive cognitive support needs, reflecting a commitment to advancing innovation, evidence-based practice, and equitable healthcare outcomes through interdisciplinary research.

Published

June 2026

Contributions

6 articles

Access

Open access

June 2026 · 6 articles
Issue Cover
EXPLORE THIS ISSUE
Table of contents
6 articles

Explore the research published in this issue of ijcrms.

IN THIS ISSUE
Hematological Malignancy Identification via K-means based ROI Extraction

Lathakiran Krishna Rajendran

Identifying hematological diseases early on and classifying them helps give patients improved clinical options.  Moreover, it is of great difficulty to perform the analysis of the image of a smear of peripheral blood. In addition, the analysis takes more time. Generally, an expert pathologist has a fairly heavy study load, having to study large numbers of images, and suffers a delay because of inter and intra-observer variability. Consequently, a number of CAD schemes were developed that automatically diagnose hematology diseases. As a result, laboratory technicians and pathologists may devote their time to more complicated activities. Please consult the internet for more information. This paper describes the automated detection of blood disorders using image processing with a computer-aided diagnostic system (CAD).  The technique implements various image pre-processing operations to reduce noise and improve contrast and morphological enhancement of the image for better segmentation. Moreover, we also use K-means clustering to extract the Region of Interest(ROI). In essence, the algorithm could identify leukocyte areas from the blood smear image. Geometrical, statistical, and textural feature descriptors, calculated from the extracted ROI, will describe the patterns of abnormal cells. The feature vectors are used by the classifiers, kNN and Naive Bayes, to classify malignant and non-malignant blood cells. The constructed post-concomitant CDSS produces a classification accuracy of 92.8% when applied.

PDF
Identifying Determinants of Outcome in Post-Radiotherapy Cervical Carcinoma Requiring Adjuvant Surgery

Lathakiran Krishna Rajendran

Cervical carcinoma that persists definitively after chemoradiotherapy poses a major therapeutic challenge. Candidate selection for salvage surgery is vital to optimize outcomes. A multicenter retrospective cohort study was conducted to evaluate the clinical, surgical, and pathological factors affecting survival in patients undergoing salvage hysterectomy for residual cervical carcinoma following radiotherapy. A total of 99 patients who were treated across 25 institutions were evaluated using Cox proportional hazards regression analysis to find prognostic factors of progression-free survival (PFS). The duration of follow-up was adequate enough to assess prognosis. PFS was predicted independently by time from completion of RT to detection of residual disease, surgical margin status, and anatomic extent of residual disease according to multivariable analysis. Patients whose disease was detected early had negative surgical margins, and whose tumour was confined to the cervix had improved survival. Given these results, the SAL-HYS scoring system was created to risk-stratify patients, with patients labelled as low-risk achieving a 4-year PFS and overall survival of approximately 80%. These results highlight that surveillance on time, accurate pre-operative evaluation, and complete surgical resection enhance outcomes for persistent cervical carcinoma after radiotherapy.

PDF
Pharmacognosy-to-Candidate: Protease-Directed Prioritization of Plant-Derived Glycosides via Minimal Semi-Synthetic Optimization

Richa Singh

This study establishes an integrated pharmaceutical discovery pipeline from medicinal plant profiling to preclinical candidate identification, focusing on SARS-CoV-2 main protease (Mpro) inhibition. Comprehensive LC-ESI-TOF-MS/MS analysis of Cynanchum acutum L. identified 46 metabolites, with quercetin-3-O-β-galactoside (Q) characterized as the dominant flavonoid glycoside (3.71 mg/g crude extract) through validated HPTLC/HPLC methods. Strategic semi-synthetic optimization via selective O-alkylation generated two analogues (Q1: 7-benzyl; Q2: 7-bromoethyl) to enhance hydrophobicity and membrane permeability. Antiviral evaluation in Vero-E6 cells demonstrated significant SARS-CoV-2 inhibition, with the crude extract (IC₅₀ = 23.99 μg/mL, SI = 13.66) and benzyl derivative Q1 (IC₅₀ = 29.21 μg/mL, SI = 11.06) showing superior potency over the parent compound Q (IC₅₀ = 59.73 μg/mL, SI = 6.16). Molecular docking revealed preferential Mpro binding for Q1 (-8.34 kcal/mol) through conserved catalytic-site interactions with Cys145 and His41. The workflow exemplifies a minimal-chemistry approach from natural product hit to preclinical candidate, validated through orthogonal analytics and structure-activity relationships.

PDF
Specialized Rehabilitation Workforce Capacity and Acute Injury Management Readiness: A Tertiary Health System Competency Assessment

Shwetambari Korde

Rehabilitation services can play an important role in curtailing long-term disability and improving functional recovery in disasters and mass casualty incidents. The potential of the Physical Therapy workforce to assist complex trauma rehabilitation in a tertiary healthcare system is assessed.  Using population statistics, regulatory workforce records, and facility-level survey data, a competency-based assessment framework was developed for Bahrain. We conducted an analysis of their workforce density, demographic characteristics, sector distribution, postgraduate qualifications, and specialization profiles. The results show significant deficiencies in advanced rehabilitation readiness. For example, the physical therapist density is only 1.7/10,000 population, along with 19% post-graduate specialization coverage. Orthopedics was the largest specialist group, and disaster-relevant areas, including neurological rehab, burn care, amputation rehab, and acute trauma, were underdeveloped. The assessment also recognized a reliance on expatriate clinicians and a lack of inclusion of rehabilitation professionals in disaster preparedness planning. Reinforcing postgraduate education and extending specialized training pathways, alongside enhancement of workforce planning and the formal inclusion of Physical Therapists in the emergency response systems, will yield a more resilient health system and ensure rehabilitation service delivery during future emergencies.

PDF
Beyond Life Skills Reframing Science Access for Learners with Extensive Cognitive Support Needs

Shwetambari Korde

This paper develops alternate science content expectations and accessible assessments tailored for K–12 students who require substantial cognitive support, centering the work squarely within inclusive special education practice. A design methodology blending evidence‑guided assessment design with universal access principles was used to derive age‑appropriate, concept‑focused targets and item formats spanning elementary, middle, and high school levels. Development relied on iterative expert review by special educators and science specialists to ensure alignment with general curricula while reducing cognitive load, addressing communication needs, and maximizing accessibility. A multi‑state pilot involving 1,606 students across four states examined item performance and access thresholds, identifying patterns of difficulty and informing targeted revisions where barriers were detected. Findings indicate that most items met accessibility and content criteria and elicited meaningful student responses, with focused refinements improving components flagged for undue challenge. Implications for special education include teacher supports that elevate conceptual science understanding beyond rote procedures, accessible materials grounded in learner profiles, and assessment routines that validly capture progress. Future directions prioritize scaling educator resources and longitudinal evaluation of outcomes as accessible science instruction and assessment become embedded within special education systems.

PDF
A Unified Multi-Modal Mixture-of-Experts Model for Integrated Representation Learning in Pharmaceutical Sciences

Anushree Bhople & Aakash Kolekar

The rapid advancement of large language models (LLMs) has opened up opportunities for AI applications in pharmaceutical sciences. However, integrating diverse biological data modalities continues to remain challenging.  We propose SciMind, a multi-modal mixture-of-experts (MoE) having the capability of integrated representation learning from pharmaceutical data sources, including biomedical text, DNA sequence, protein sequence, and molecular structure. The proposed method includes method-specific tokenization strategies, sparse expert routing mechanisms, and cross-modal pre-training for improved knowledge transfer across multiple biological representations. An expert initialization approach based on limited K-means and adaptive top-k routing can use the parameters effectively while preserving domain-specific knowledge. Through experimental evaluations across four applications, including biomedical natural language processing, molecular understanding, promoter prediction and protein-related tasks, SciMind achieves competitive performance against existing domain-specific and general-purpose models.  According to the results, unified multi-modal learning can assist in the representation quality, drug reasoning capabilities, and applications in drug acceptance, molecule analysis, and personalized medicine.

PDF
Showing 6 of 6 articles in this issue
Research, freely accessible

Read the articles online or download individual PDFs from this issue.

Vol. 1 No. 2 (2026) | International Journal of Clinical Research and Medical Sciences