OBJECTIVE: To employ machine learning (ML) and stacked ensemble learning (EL) methods in predicting short- and long-term mortality in Asian patients diagnosed with NSTEMI/UA and to identify the associated features, subsequently evaluating these findings against established risk scores.
METHODS: We analyzed data from the National Cardiovascular Disease Database for Malaysia (2006-2019), representing a diverse NSTEMI/UA Asian cohort. Algorithm development utilized in-hospital records of 9,518 patients, 30-day data from 7,133 patients, and 1-year data from 7,031 patients. This study utilized 39 features, including demographic, cardiovascular risk, medication, and clinical features. In the development of the stacked EL model, four base learner algorithms were employed: eXtreme Gradient Boosting (XGB), Support Vector Machine (SVM), Naive Bayes (NB), and Random Forest (RF), with the Generalized Linear Model (GLM) serving as the meta learner. Significant features were chosen and ranked using ML feature importance with backward elimination. The predictive performance of the algorithms was assessed using the area under the curve (AUC) as a metric. Validation of the algorithms was conducted against the TIMI for NSTEMI/UA using a separate validation dataset, and the net reclassification index (NRI) was subsequently determined.
RESULTS: Using both complete and reduced features, the algorithm performance achieved an AUC ranging from 0.73 to 0.89. The top-performing ML algorithm consistently surpassed the TIMI risk score for in-hospital, 30-day, and 1-year predictions (with AUC values of 0.88, 0.88, and 0.81, respectively, all p < 0.001), while the TIMI scores registered significantly lower at 0.55, 0.54, and 0.61. This suggests the TIMI score tends to underestimate patient mortality risk. The net reclassification index (NRI) of the best ML algorithm for NSTEMI/UA patients across these periods yielded an NRI between 40-60% (p < 0.001) relative to the TIMI NSTEMI/UA risk score. Key features identified for both short- and long-term mortality included age, Killip class, heart rate, and Low-Molecular-Weight Heparin (LMWH) administration.
CONCLUSIONS: In a broad multi-ethnic population, ML approaches outperformed conventional TIMI scoring in classifying patients with NSTEMI and UA. ML allows for the precise identification of unique characteristics within individual Asian populations, improving the accuracy of mortality predictions. Continuous development, testing, and validation of these ML algorithms holds the promise of enhanced risk stratification, thereby revolutionizing future management strategies and patient outcomes.
METHODS: Oligo, low, medium and high molecular weight chitosan nanoparticles were prepared by nanospray drying technique. These nanoparticles were incubated with alveolar macrophages in vitro and had model drug sodium fluorescein added into the same cell culture. The diffusion characteristics of sodium fluorescein and nanoparticle behavior were investigated using fluorescence microscopy, scanning electron microscopy, differential scanning calorimetry and Fourier transform infrared spectroscopy techniques.
RESULTS: The oligochitosan nanoparticles enabled macrophage membrane fluidization with the extent of sodium fluorescein entry into macrophages being directly governed by the nanoparticle loading. Using nanoparticles made of higher molecular weight chitosan, sodium fluorescein permeation into macrophages was delayed due to viscous chitosan diffusion barrier at membrane boundary.
CONCLUSION: Macrophage-chitosan nanoparticle interaction at membrane interface dictates drug migration into cellular domains.
Methods: This study aims to develop a recombinant anti-mKRAS scFv-fused mutant Hydra actinoporin-like-toxin-1 (mHALT-1) immunotoxin that is capable of recognizing and eradicating codon-12 mutated k-ras antigen abnormal cells. One G13D peptide mimotope (164-D) and one G12V peptide mimotope (68-V) were designed to elicit antigen specific IgG titres against mutated K-ras antigens in immunised Balb/c mice. The RNA was extracted from splenocytes following ELISA confirmation on post-immunized mice sera and was reverse transcribed into cDNA. The scFv combinatorial library was constructed from cDNA repertoire of variable regions of heavy chain (VH) and light chain (VL) fusions connected by a flexible glycine-serine linker, using splicing by overlap extension PCR (SOE-PCR). Anti-mKRAS G12V and G13D scFvs were cloned in pCANTAB5E phagemid and superinfected with helper phage. After few rounds of bio-panning, a specific mKRAS G12V and G13D scFv antibody against G12V and G13D control mimotope was identified and confirmed using ELISA without any cross-reactivity with other mimotopes or controls. Subsequently, the anti-mKRAS scFv was fused to mHALT-1 using SOE-PCR and cloned in pET22b vector. Expressed recombinant immunotoxins were analyzed for their effects on cell proliferation by the MTT assay and targeted specificity by cell-based ELISA on KRAS-positive and KRAS-negative cancer cells.
Results: The VH and VL genes from spleen RNA of mice immunized with 164-D and 68-V were amplified and randomly linked together, using SOE-PCR producing band sizes about 750 bp. Anti-mKRAS G12V and G13D scFvs were constructed in phagemid pCANTAB5E vectors with a library containing 3.4 × 106 and 2.9 × 106 individual clones, respectively. After three rounds of bio-panning, the anti-mKRAS G12V-34 scFv antibody against G12V control mimotope was identified and confirmed without any cross-reactivity with other controls using ELISA. Anti-mKRAS G12V-34 scFv fragment was fused to mHALT-1 toxin and cloned in pET22b vector with expression as inclusion bodies in E. coli BL21(DE3) (molecular weight of ~46.8 kDa). After successful solubilization and refolding, the mHALT-1-scFv immunotoxin exhibited cytotoxic effects on SW-480 colorectal cancer cells with IC50 of 25.39 μg/mL, with minimal cytotoxicity effect on NHDF cells.
Discussion: These results suggested that the development of such immunotoxins is potentially useful as an immunotherapeutic application against KRAS-positive malignancies.
Methods: The cytotoxicity of the Ligno TG-K against human breast (MCF7), prostate (PC3) and lung (A549) adenocarcinoma cell lines was evaluated using MTT cytotoxicity assay. The cytotoxic mechanisms of the active high molecular weight proteins (HMWp) fraction were investigated through detection of caspases activity and apoptotic-related proteins expression by Western blotting. The in vivo antitumor activity of the isolated HMWp was examined using MCF7 mouse xenograft model. Shotgun LC-MS/MS analysis was performed to identify the proteins in the HMWp.
Results and Discussion: Cold water extract of the sclerotia inhibited proliferation of MCF7, A549 and PC3 cells with IC50 ranged from 28.9 to 95.0 µg/mL. Bioassay guided fractionation of the extract revealed that HMWp exhibited selective cytotoxicity against MCF7 cells via induction of cellular apoptosis by the activation of extrinsic and intrinsic signaling pathways. HMWp activated expression of caspase-8 and -9 enzymes, and pro-apoptotic Bax protein whilst inhibiting expression of tumor survivor protein, Bcl-2. HMWp induced tumor-cell apoptosis and suppressed growth of tumor in MCF-7 xenograft mice. Lectins, serine proteases, RNase Gf29 and a 230NA deoxyribonuclease are the major cytotoxic proteins that accounted for 55.93% of the HMWp.
Conclusion: The findings from this study provided scientific evidences to support the traditional use of the L. tigris sclerotia for treatment of breast cancer. Several cytotoxic proteins with high abundance have been identified in the HMWp of the sclerotial extract and these proteins have potential to be developed into new anticancer agents or as adjunct cancer therapy.
Methods: This comparative cross-sectional study was conducted among healthy women. The cases included those women exposed to SHS, and the controls included those women not exposed to SHS. SHS exposure was defined as being exposed to SHS for at least 15 min for 2 days per week. Venous blood was taken to measure the metabolic markers (high molecular weight adiponectin, insulin level, insulin resistance, and nonesterified fatty acids), oxidative stress markers (oxidized low density lipoprotein cholesterol and 8-isoprostane), and inflammatory markers (high-sensitivity C-reactive protein and interleukin-6). A hair nicotine analysis was also performed. An analysis of covariance and a simple linear regression analysis were conducted.
Results: There were 101 women in the SHS exposure group and 91 women in the non-SHS exposure group. The mean (with standard deviation) of the hair nicotine levels was significantly higher in the SHS exposure group when compared to the non-SHS exposure group [0.22 (0.62) vs. 0.04 (0.11) ng/mg; P = 0.009]. No significant differences were observed in the high molecular weight adiponectin, insulin and insulin resistance, nonesterified fatty acids, 8-isoprostane, oxidized low density lipoprotein cholesterol, interleukin-6, and high-sensitivity C-reactive protein between the two groups. The serum high molecular weight adiponectin was negatively associated with the insulin level and insulin resistance in the women exposed to SHS. However, no significant relationships were seen between the high molecular weight adiponectin and nonesterified fatty acids, 8-isoprostane, oxidized low density lipoprotein cholesterol, high-sensitivity C-reactive protein in the SHS group.
Discussion: There were no significant differences in the metabolic, oxidative stress, and inflammatory markers between the SHS exposure and non-SHS exposure healthy women. A low serum level of high molecular weight adiponectin was associated with an increased insulin level and resistance in the women exposed to SHS.