Fatih Sağlam

This study aimed to compare the clinical, demographic, and laboratory characteristics of multiple myeloma patients with spinal involvement who underwent surgical versus non-surgical management.This retrospective, single-center cohort study included 46 multıple myeloma patients with radiologically confirmed spinal involvement who were treated at Private Ümit Hospital between 2013 and 2025. Eighteen patients underwent surgical intervention, while 28 were managed medically. Demographic data, presenting symptoms, and laboratory parameters were compared between groups. Data were analyzed using SPSS 25.0. Normality was assessed by the Shapiro–Wilk test, and appropriate statistical tests (Student’s t-test, Mann–Whitney U, chi-square) were applied. The mean age was 63.3 ± 6.0 years in the surgical group and 67.3 ± 8.7 years in the non-surgical group. Back or low back pain was the most frequent presenting symptom in surgically treated patients, while systemic manifestations such as fatigue, weight loss, and diffuse musculoskeletal pain predominated in the non-surgical group. Laboratory comparisons revealed significantly higher BUN (p = 0.025), beta-2 microglobulin (p = 0.008), and ISS scores (p = 0.034) in the non-surgical cohort, indicating a greater systemic disease burden. No significant intergroup differences were observed in other biochemical parameters. Multiple myeloma patients with spinal involvement who undergo surgery tend to have lower systemic disease activity and better renal function compared to those treated conservatively. The presence of neurological or pain symptoms due to proximity to neural structures may lead to earlier diagnosis in these patients.

Most machine learning algorithms tend to bias towards the majority class when a dataset exhibits a skewed distribution in the class variable. This is called the class imbalance problem and is frequently encountered in real-life applications. One of the most prevalent methods for addressing class imbalance is data resampling, which generates or removes samples to balance the dataset. A well-known issue with oversampling is noise generation. Noise removal or hybrid resampling is used to deal with noise. However, these methods cause imbalance to re-emerge. In this study, a data relocation approach named DatRel is proposed to address the noise generation problem of oversampling without causing imbalance. The proposed approach utilizes pure and proper class cover catch digraphs (P-CCCD) to determine dominant points and cover areas for minority class. Then, new samples from oversampling are drawn to the dominant points until they are covered. This process ensures that newly generated samples never overlap with a negative sample. Imbalance is not affected since no sample is removed by undersampling. The proposed DatRel approach is applied to commonly used oversampling methods, namely SMOTE, ADASYN, and BLSMOTE. Moreover, the performance of the DatRel approach is compared to noise filtering methods such as Tomeklink, ENN, NEATER, and NearMiss after SMOTE. Several baseline classification algorithms are employed, and comparisons are made using various metrics. Results using 49 imbalanced datasets show that DatRel improves classifier performance in oversampling methods and demonstrates its value in comparison to other noise removal techniques according to AUC, BACC, F1, GMEAN, and MCC.