Prevalence of Malnutrition in Patients with Hepatocellular Carcinoma: A Comparative Study of GLIM Criteria, NRS2002, and PG-SGA, and Identification of Independent Risk Factors.

AIM: Malnutrition is prevalent in hepatocellular carcinoma (HCC) patients, linked to poor outcomes, necessitating early intervention. This study aimed to investigate malnutrition in HCC patients, assess Nutrition Risk Screening 2002 (NRS-2002) and Patient-Generated Subjective Global Assessment (PG-SGA) vs. Global Leadership Initiative on Malnutrition (GLIM) criteria, and identify independent risk factors. METHOD: A cross-sectional retrospective study was conducted on 207 patients with HCC. Nutritional screening/assessment results and blood samples were collected within 72 h of admission. This study assessed the prevalence of malnutrition using the NRS-2002 and PG-SGA and retrospectively using the GLIM criteria. The performance of the screening tools was evaluated using kappa (K) values. Logistic regression analyses were performed to determine whether laboratory parameters were associated with malnutrition as identified by the GLIM criteria. RESULTS: Of the participants, 30.4% were at risk of malnutrition according to NRS-2002. The agreement between the NRS-2002 and GLIM criteria was substantial. The GLIM criteria and PG-SGA diagnosed malnutrition in 43 and 54.6% of the participants, respectively. Age, anemia, and ascites correlated with malnutrition in regression. CONCLUSION: The GLIM criteria, along with NRS-2002 and PG-SGA, aid in diagnosing malnutrition in HCC patients. Recognizing risk factors improves accuracy, enabling timely interventions for better outcomes.

Automatic QRS complex detection using two-level convolutional neural network.

BACKGROUND: The QRS complex is the most noticeable feature in the electrocardiogram (ECG) signal, therefore, its detection is critical for ECG signal analysis. The existing detection methods largely depend on hand-crafted manual features and parameters, which may introduce significant computational complexity, especially in the transform domains. In addition, fixed features and parameters are not suitable for detecting various kinds of QRS complexes under different circumstances. METHODS: In this study, based on 1-D convolutional neural network (CNN), an accurate method for QRS complex detection is proposed. The CNN consists of object-level and part-level CNNs for extracting different grained ECG morphological features automatically. All the extracted morphological features are used by multi-layer perceptron (MLP) for QRS complex detection. Additionally, a simple ECG signal preprocessing technique which only contains difference operation in temporal domain is adopted. RESULTS: Based on the MIT-BIH arrhythmia (MIT-BIH-AR) database, the proposed detection method achieves overall sensitivity Sen = 99.77%, positive predictivity rate PPR = 99.91%, and detection error rate DER = 0.32%. In addition, the performance variation is performed according to different signal-to-noise ratio (SNR) values. CONCLUSIONS: An automatic QRS detection method using two-level 1-D CNN and simple signal preprocessing technique is proposed for QRS complex detection. Compared with the state-of-the-art QRS complex detection approaches, experimental results show that the proposed method acquires comparable accuracy.