Journal of Advances in Medical and Pharmaceutical Sciences

Artificial Intelligence and Multimodal Data Approaches for Diagnosis, Prognosis, and Treatment Decision Support in Diffuse Large B-Cell Lymphoma and Acute Myeloid Leukaemia: A Systematic Review

2026-09-12T12:47:17+00:00

Aims: To synthesise and critically appraise evidence on artificial intelligence (AI) and multimodal data approaches for diagnosis, prognosis, and treatment decision support in diffuse large B-cell lymphoma (DLBCL) and acute myeloid leukaemia (AML), and to compare how disease biology shapes model design and clinical readiness.

Study Design: Systematic review with narrative synthesis.

Place and Duration of Study: PubMed/MEDLINE, Embase, Scopus, Web of Science Core Collection, IEEE Xplore, and the Cochrane Library were searched from database inception to 29 July 2026.

Methodology: English-language original studies involving human participants, clinical images, human-derived samples, or patient-derived datasets were eligible. Two reviewers independently screened records, assessed full texts, and extracted study characteristics, data modalities, analytical methods, validation approaches, and performance measures. PROBAST+AI domains were used to guide appraisal of eligible patient-level prediction models; exploratory multi-omics, molecular-subtyping, biomarker-discovery, and segmentation studies underwent structured descriptive appraisal. TRIPOD+AI informed assessment of reporting completeness. Owing to substantial clinical and methodological heterogeneity, findings were synthesised narratively.

Results: Twenty-eight studies were included: 22 on DLBCL and six on AML. DLBCL research was dominated by PET/CT radiomics, deep imaging, digital pathology, and imaging-clinical-molecular fusion. Internally evaluated diagnostic models reported area under the curve values as high as 0.999, whereas externally validated prognostic models achieved values of 0.66-0.71 and showed inconsistent incremental improvement over the International Prognostic Index. AML studies mainly integrated genomic, transcriptomic, epigenomic, single-cell, proteomic, metabolic, and functional drug-response data. Prognostic models reported concordance indices of 0.72-0.81 and time-dependent area under the curve values of 0.795-0.899. The most frequent methodological concerns were retrospective sampling, high-dimensional modelling in modest cohorts, incomplete calibration reporting, and limited independent validation. Treatment-response models in both diseases remained retrospective or exploratory, and none demonstrated improved outcomes through AI-guided treatment allocation.

Conclusion: AI and multimodal data approaches show greatest maturity for prognostic stratification, but diagnostic replacement and treatment selection remain unproven. Prospective, multicentre clinical-impact validation is the principal requirement for translation into routine care.

Patient Characteristics and Treatment Outcomes among Patients with Drug-Resistant Tuberculosis in Meru County, Kenya

2026-09-19T07:04:47+00:00

Background: Drug-resistant tuberculosis (DR-TB) remains a public health challenge in Kenya despite advances in diagnosis and shorter, all-oral treatment regimens.

Aim: This study assessed patient characteristics influencing DR-TB treatment outcomes in Meru County, Kenya.

Methods: A retrospective descriptive study reviewed 201 de-identified records of patients diagnosed with DR-TB and enrolled for treatment between January 2020 and December 2023. Patient characteristics and treatment outcomes were summarised using descriptive statistics. Chi-square tests assessed associations, and multivariable binary logistic regression identified independent predictors of treatment outcomes at p < 0.05.

Results: Overall treatment success was 95%. Unfavourable outcomes comprised 3% loss to follow-up and 2% deaths. Most patients were adults, predominantly male, and most had pulmonary DR-TB. Education level was independently associated with favourable treatment outcomes (OR = 2.82; 95% CI: 1.04–7.65; p = 0.041). Age, gender, occupation, marital status, and alcohol use were not statistically significant independent predictors.

Conclusions: DR-TB treatment outcomes in Meru County were predominantly favourable in this retrospective sample. Education level was the only patient characteristic independently associated with treatment outcome. Patient education and support tailored to literacy levels may help sustain treatment success. Further research should examine behavioural, clinical, socioeconomic, and health-system factors that may contribute to variation in DR-TB outcomes.

Breast Cancer Awareness and Breast Self-Examination Practices among Female Students at Al-Mashreq University: A Cross-Sectional Study

2026-09-19T07:14:22+00:00

Background: Breast cancer remains the most common cancer among women worldwide and a major cause of preventable cancer mortality, particularly in resource-constrained settings where delayed presentation is common. Breast self-examination (BSE) does not replace clinical assessment or mammography, but breast self-awareness may promote early help-seeking among young women. This study assessed breast cancer awareness and BSE practices among female students at Al-Mashreq University.

Methods: A descriptive cross-sectional study was conducted among 215 female students at Al-Mashreq University, Jeddah Center, Saudi Arabia. Data were collected using a structured self-administered questionnaire covering sociodemographic characteristics, breast cancer risk factors, warning signs, screening knowledge, attitudes, BSE practice, and barriers. Descriptive statistics summarised participant characteristics and responses. Chi-square tests assessed associations between knowledge level and sociodemographic variables. Statistical significance was set at p<0.05.

Results: Most participants were aged 20 to <25 years (148/215, 68.8%), single (206/215, 95.8%), and had no family history of breast cancer (169/215, 78.6%). Overall, 115 students (53.5%) had good knowledge, 65 (30.2%) moderate knowledge, and 35 (16.3%) poor knowledge. Although 179 students (83.3%) had heard of BSE, only 69 (32.1%) practised it, and only 27 (12.6%) reported monthly practice. The most common barriers were lack of knowledge (82/215, 38.1%), forgetfulness (53/215, 24.7%), and fear of discovering an abnormality (40/215, 18.6%). Knowledge level was significantly associated with age, college, academic year, and family history of breast cancer.

Conclusion: Female students showed acceptable breast cancer awareness but inadequate BSE practice. Structured, practical, and culturally sensitive breast health education is needed to convert awareness into sustained early-detection behaviour.