Usefulness of the heart rate variability test in predicting intradialytic hypotension in patients undergoing chronic haemodialysis.

Background: Intradialytic hypotension (IDH) is the primary complication of haemodialysis (HD); however, its diverse pathophysiology and inconsistent definitions complicate its prediction. Despite attempts using the heart rate variability (HRV) test for IDH prediction, studies on its usefulness for predicting IDH diagnosed per the nadir 90 criterion are lacking. We aimed to evaluate HRV test efficacy and reproducibility in predicting IDH based on the nadir 90 criterion. Methods: Seventy patients undergoing HD participated in this multicentre prospective observational study. The HRV test was performed during non-HD periods and IDH was monitored during 12 HD sessions. IDH was diagnosed according to the nadir 90 criterion, defined as a decrease in systolic blood pressure of ≤90 mmHg during HD. After monitoring, the HRV test was repeated. An HRV-IDH index was developed using multivariate logistic regression analysis employing HRV test parameters. The predictive power of the HRV-IDH index was analysed using the area under the receiver operating characteristics curve (AUROC). Reproducibility was evaluated using correlation analysis of two HRV tests on the same patient. Results: There were 37 and 33 patients in the IDH and non-IDH groups, respectively. The HRV-IDH index predicted IDH occurrence with AUROCs of 0.776 and 0.803 for patients who had experienced at least one or repeated IDH episodes, respectively. Spearman's correlation coefficient for HRV-IDH indices was 0.859 for the first and second HRV tests. Conclusions: The HRV test holds promise for predicting IDH, particularly for patients with recurring IDH diagnosed based on the nadir 90 criterion.

Importance of dialysis specialists in early mortality in elderly hemodialysis patients: a multicenter retrospective cohort study.

The early mortality rate in elderly patients undergoing hemodialysis is more than twice that in young patients, requiring more specialized healthcare. We investigated whether the number of professional dialysis specialists affected early mortality in elderly patients undergoing hemodialysis. This multicenter retrospective cohort study analyzed data from 1860 patients aged ≥ 70 years who started hemodialysis between January 2010 and December 2017. Study regions included Seoul, Gyeonggi-do, Gangwon-do, Daejeon/Chungcheong-do, Daegu/Gyeongsangbuk-do, and Busan/Ulsan/Gyeongsangnam-do. The number of patients undergoing hemodialysis per dialysis specialist was calculated using registered data from each hemodialysis center. Early mortality was defined as death within 6 months of hemodialysis initiation. Gangwon-do (28.3%) and Seoul (14.5%) showed the highest and lowest early mortality rate, respectively. Similarly, Gangwon-do (64.6) and Seoul (43.9) had the highest and lowest number of patients per dialysis specialist, respectively. Relatively consistent results were observed for the regional rankings of early mortality rate and number of patients per dialysis specialist. Multivariate Cox regression analysis-adjusted for previously known significant risk factors-revealed that the number of patients per dialysis specialist was an independent risk factor for early mortality (hazard ratio: 1.031, p < 0.001). This study underscores the growing need for dialysis specialists for elderly hemodialysis patients in Korea.

Elevated cholesterol in ATAD3 mutants is a compensatory mechanism that leads to membrane cholesterol aggregation.

Aberrant cholesterol metabolism causes neurological disease and neurodegeneration, and mitochondria have been linked to perturbed cholesterol homeostasis via the study of pathological mutations in the ATAD3 gene cluster. However, whether the cholesterol changes were compensatory or contributory to the disorder was unclear, and the effects on cell membranes and the wider cell were also unknown. Using patient-derived cells, we show that cholesterol perturbation is a conserved feature of pathological ATAD3 variants that is accompanied by an expanded lysosome population containing membrane whorls characteristic of lysosomal storage diseases. Lysosomes are also more numerous in Drosophila neural progenitor cells expressing mutant Atad3, which exhibit abundant membrane-bound cholesterol aggregates, many of which co-localize with lysosomes. By subjecting the Drosophila Atad3 mutant to nutrient restriction and cholesterol supplementation, we show that the mutant displays heightened cholesterol dependence. Collectively, these findings suggest that elevated cholesterol enhances tolerance to pathological ATAD3 variants; however, this comes at the cost of inducing cholesterol aggregation in membranes, which lysosomal clearance only partly mitigates.

Trends in Research on Patients With COVID-19 in Korean Medical Journals.

OBJECTIVES: This study was conducted to systematically summarize trends in research concerning patients with coronavirus disease 2019 (COVID-19) as reported in Korean medical journals. METHODS: We performed a literature search of KoreaMed from January 2020 to September 2022. We included only primary studies of patients with COVID-19. Two reviewers screened titles and abstracts, then performed full-text screening, both independently and in duplicate. We first identified the 5 journals with the greatest numbers of eligible publications, then extracted data pertaining to the general characteristics, study population attributes, and research features of papers published in these journals. RESULTS: Our analysis encompassed 142 primary studies. Of these, approximately 41.0% reported a funding source, while 3.5% disclosed a conflict of interest. In 2020, 42.9% of studies included fewer than 10 participants; however, by 2022, the proportion of studies with over 200 participants had increased to 40.6%. The most common design was the cohort study (48.6%), followed by case reports/series (35.2%). Only 3 randomized controlled trials were identified. Studies most frequently focused on prognosis (58.5%), followed by therapy/intervention (20.4%). Regarding the type of intervention/exposure, therapeutic clinical interventions comprised 26.1%, while studies of morbidity accounted for 13.4%. As for the outcomes measured, 50.7% of studies assessed symptoms/clinical status/improvement, and 14.1% evaluated mortality. CONCLUSIONS: Employing a systematic approach, we examined the characteristics of research involving patients with COVID-19 that was published in Korean medical journals from 2020 onward. Subsequent research should assess not only publication trends over a longer timeframe but also the quality of evidence provided.

Provably Secure Lightweight Mutual Authentication and Key Agreement Scheme for Cloud-Based IoT Environments.

A paradigm that combines cloud computing and the Internet of Things (IoT) allows for more impressive services to be provided to users while addressing storage and computational resource issues in the IoT environments. This cloud-based IoT environment has been used in various industries, including public services, for quite some time, and has been researched in academia. However, various security issues can arise during the communication between IoT devices and cloud servers, because communication between devices occurs in open channels. Moreover, issues such as theft of a user's IoT device or extraction of key parameters from the user's device in a remote location can arise. Researchers interested in these issues have proposed lightweight mutual authentication key agreement protocols that are safe and suitable for IoT environments. Recently, a lightweight authentication scheme between IoT devices and cloud servers has been presented. However, we found out their scheme had various security vulnerabilities, vulnerable to insider, impersonation, verification table leakage, and privileged insider attacks, and did not provide users with untraceability. To address these flaws, we propose a provably secure lightweight authentication scheme. The proposed scheme uses the user's biometric information and the cloud server's secret key to prevent the exposure of key parameters. Additionally, it ensures low computational costs for providing users with real-time and fast services using only exclusive OR operations and hash functions in the IoT environments. To analyze the safety of the proposed scheme, we use informal security analysis, Burrows-Abadi-Needham (BAN) logic and a Real-or-Random (RoR) model. The analysis results confirm that our scheme is secure against insider attacks, impersonation attacks, stolen verifier attacks, and so on; furthermore, it provides additional security elements. Simultaneously, it has been verified to possess enhanced communication costs, and total bit size has been shortened to 3776 bits, which is improved by almost 6% compared to Wu et al.'s scheme. Therefore, we demonstrate that the proposed scheme is suitable for cloud-based IoT environments.

Favorable Prognostic Factors for Survival Outcomes of Hepatocellular Carcinoma with Portal Vein Tumor Thrombosis After Hepatectomy.

BACKGROUND: This study aimed to investigate prognostic factors of recurrence and survival associated with hepatocellular carcinoma (HCC) with portal vein tumor thrombosis (PVTT). PATIENTS AND METHODS: This retrospective study included 161 patients with HCC with PVTT who underwent hepatectomy between January 2003 and January 2014 at the Asan Medical Center. Regression analyses were conducted to identify favorable predictive factors for overall survival (OS) and recurrence-free survival (RFS). RESULTS: The median follow-up was 15.9 months, while 1-, 3-, and 5-year OS was 65.0%, 38.4%, and 36.0%, respectively, and 1-year RFS was 25.5%. There were no significant differences in OS and RFS between the patients with portal vein invasion (Vp) 1-2 and Vp3-4 PVTT. Patients with intrahepatic recurrence had significantly better overall survival than patients with extrahepatic recurrence. Transcatheter arterial chemoembolization and radiofrequency ablation were the most effective treatments for intrahepatic metastasis, and surgery was the most effective treatment for extrahepatic metastasis. On multivariate analysis, absence of esophageal varices, maximal tumor size < 5 cm, tumor location in single lobe, and anatomical resection were favorable prognostic factors for OS and R0 resection, and absence of microvascular invasion was a favorable prognostic factor for RFS. CONCLUSION: The long-term outcome of patients with HCC with PVTT can be improved under consideration of favorable prognostic factors including absence of esophageal varices, maximal tumor size < 5 cm, tumor location in single lobe, and anatomical resection, R0 resection, and absence of microvascular invasion. In addition, recurrent HCC required aggressive management to prolong overall survival.

Clonally Selected Lines After CRISPR-Cas Editing Are Not Isogenic.

The CRISPR-Cas9 system has enabled researchers to precisely modify/edit the sequence of a genome. A typical editing experiment consists of two steps: (1) editing cultured cells; (2) cell cloning and selection of clones with and without intended edit, presumed to be isogenic. The application of CRISPR-Cas9 system may result in off-target edits, whereas cloning will reveal culture-acquired mutations. We analyzed the extent of the former and the latter by whole genome sequencing in three experiments involving separate genomic loci and conducted by three independent laboratories. In all experiments we hardly found any off-target edits, whereas detecting hundreds to thousands of single nucleotide mutations unique to each clone after relatively short culture of 10-20 passages. Notably, clones also differed in copy number alterations (CNAs) that were several kb to several mb in size and represented the largest source of genomic divergence among clones. We suggest that screening of clones for mutations and CNAs acquired in culture is a necessary step to allow correct interpretation of DNA editing experiments. Furthermore, since culture associated mutations are inevitable, we propose that experiments involving derivation of clonal lines should compare a mix of multiple unedited lines and a mix of multiple edited lines.

Comparison of the association intensity of creatinine and cystatin C with hyperphosphatemia and hyperparathyroidism in patients with chronic kidney disease.

Herein, we compared the association intensity of estimated glomerular filtration rate (eGFR) equations using creatinine (Cr) or cystatin C (CysC) with hyperphosphatemia and secondary hyperparathyroidism occurrence, which reflect the physiological changes occurring during chronic kidney disease (CKD) progression. This study included 639 patients treated between January 2019 and February 2022. The patients were divided into low- and high-difference groups based on the median value of the difference between the Cr-based eGFR (eGFRCr) and CysC-based eGFR (eGFRCysC). Sociodemographic and laboratory factors underlying a high difference between eGFRCr and eGFRCysC were analyzed. The association intensity of eGFRCr, eGFRCysC and both Cr- and CysC-based eGFR (eGFRCr-CysC) was compared using the area under the receiver operating characteristic curve (AuROC) values for hyperphosphatemia and hyperparathyroidism occurrence in the overall cohort and the low- and high-difference groups. Age > 70 years and CKD grade 3 based on eGFRCr were significant factors affecting the high differences. eGFRCysC and eGFRCr-CysC showed higher AuROC values than that of eGFRCr, especially in the high-difference group and in patients with CKD grade 3. Our results show that CysC should be evaluated in patients with significant factors, including age > 70 years and CKD grade 3, to accurately assess kidney function to better determine the physiological changes in CKD progression and predict prognosis accurately.

Provably Secure Mutual Authentication and Key Agreement Scheme Using PUF in Internet of Drones Deployments.

Internet of Drones (IoD), designed to coordinate the access of unmanned aerial vehicles (UAVs), is a specific application of the Internet of Things (IoT). Drones are used to control airspace and offer services such as rescue, traffic surveillance, environmental monitoring, delivery and so on. However, IoD continues to suffer from privacy and security issues. Firstly, messages are transmitted over public channels in IoD environments, which compromises data security. Further, sensitive data can also be extracted from stolen mobile devices of remote users. Moreover, drones are susceptible to physical capture and manipulation by adversaries, which are called drone capture attacks. Thus, the development of a secure and lightweight authentication scheme is essential to overcoming these security vulnerabilities, even on resource-constrained drones. In 2021, Akram et al. proposed a secure and lightweight user-drone authentication scheme for drone networks. However, we discovered that Akram et al.'s scheme is susceptible to user and drone impersonation, verification table leakage, and denial of service (DoS) attacks. Furthermore, their scheme cannot provide perfect forward secrecy. To overcome the aforementioned security vulnerabilities, we propose a secure mutual authentication and key agreement scheme between user and drone pairs. The proposed scheme utilizes physical unclonable function (PUF) to give drones uniqueness and resistance against drone stolen attacks. Moreover, the proposed scheme uses a fuzzy extractor to utilize the biometrics of users as secret parameters. We analyze the security of the proposed scheme using informal security analysis, Burrows-Abadi-Needham (BAN) logic, a Real-or-Random (RoR) model, and Automated Verification of Internet Security Protocols and Applications (AVISPA) simulation. We also compared the security features and performance of the proposed scheme and the existing related schemes. Therefore, we demonstrate that the proposed scheme is suitable for IoD environments that can provide users with secure and convenient wireless communications.

Validation of quantitative prognostic prediction using ADV score for resection of hepatocellular carcinoma: A Korea-Japan collaborative study with 9200 patients.

BACKGROUND: A score derived from the concentrations of α-fetoprotein (AFP) and des-γ-carboxy prothrombin (DCP) and tumor volume (TV), called ADV score, has been shown to be prognostic of hepatocellular carcinoma (HCC) recurrence following hepatic resection (HR) or liver transplantation. METHODS: This multicenter, multinational validation study included 9200 patients who underwent HR from 2010 to 2017 at 10 Korean and 73 Japanese centers, and were followed up until 2020. RESULTS: AFP, DCP, and TV showed weak correlations (ρ ≤ .463, r ≤ .189, p < .001). Disease-free survival (DFS), overall survival (OS), and post-recurrence survival rates were dependent on 1.0 log and 2.0 log intervals of ADV scores (p < .001). Receiver operating characteristic (ROC) curve analysis showed that ADV score cutoffs of 5.0 log for DFS and OS yielded the areas under the curve ≥ .577, with both being significantly prognostic of tumor recurrence and patient mortality at 3 years. ADV score cutoffs of ADV 4.0 log and 8.0 log, derived through K-adaptive partitioning method, showed higher prognostic contrasts in DFS and OS. ROC curve analysis showed that an ADV score cutoff of 4.2 log was suggestive of microvascular invasion, with both microvascular invasion and an ADV score cutoff of 4.2 log showing similar DFS rates. CONCLUSIONS: This international validation study demonstrated that ADV score is an integrated surrogate biomarker for post-resection prognosis of HCC. Prognostic prediction using ADV score can provide reliable information that can assist in planning treatment of patients with different stages of HCC and guide individualized post-resection follow-up based on the relative risk of HCC recurrence.

Electrochemical C(sp3)-H Lactonization of 2-Alkylbenzoic Acids toward Phthalides.

Herein, we report direct electrochemical C(sp3)-H lactonization of 2-alkylbenzoic acids toward phthalides. The reaction provides a wide substrate scope of 2-alkylbenzoic acids bearing primary to tertiary C(sp3)-H bonds by utilizing a graphite anode, dichloromethane (DCM) solvent, hexafluoroisopropanol (HFIP) cosolvent, and n-Bu4NClO4 electrolyte. Our synthetic approach offers a simple, intuitive, and atom-economical protocol to synthesize various phthalides (25 examples, up to 92% yield) and obtain other 5- and 6-membered lactones (10 examples, up to 83% yield).

Combined impact of the inter and intra-patient variability of tacrolimus blood level on allograft outcomes in kidney transplantation.

Introduction: Tacrolimus (TAC) has been widely used as an immunosuppressant after kidney transplantation (KT); however, the combined effects of intra-patient variability (IPV) and inter-patient variability of TAC-trough level (C0) in blood remain controversial. This study aimed to determine the combined impact of TAC-IPV and TAC inter-patient variability on allograft outcomes of KT. Methods: In total, 1,080 immunologically low-risk patients who were not sensitized to donor human leukocyte antigen (HLA) were enrolled. TAC-IPV was calculated using the time-weighted coefficient variation (TWCV) of TAC-C0, and values > 30% were classified as high IPV. Concentration-to-dose ratio (CDR) was used for calculating TAC inter-patient variability, and CDR < 1.05 ng•mg/mL was classified as rapid metabolizers (RM). TWCV was calculated based on TAC-C0 up to 1 year after KT, and CDR was calculated based on TAC-C0 up to 3 months after KT. Patients were classified into four groups according to TWCV and CDR: low IPV/non-rapid metabolizer (NRM), high IPV/NRM, low IPV/RM, and high IPV/RM. Subgroup analysis was performed for pre-transplant panel reactive antibody (PRA)-positive and -negative patients (presence or absence of non-donor-specific HLA-antibodies). Allograft outcomes, including deathcensored graft loss (DCGL) and biopsy-proven allograft rejection (BPAR), were compared. Results: The incidences of DCGL, BPAR, and overall graft loss were the highest in the high-IPV/RM group. In addition, a high IPV/RM was identified as an independent risk factor for DCGL. The hazard ratio of high IPV/RM for DCGL and the incidence of active antibody-mediated rejection were considerably increased in the PRA-positive subgroup. Discussion: High IPV combined with RM (inter-patient variability) was closely related to adverse allograft outcomes, and hence, more attention must be given to pre-transplant PRA-positive patients.

Combined Analysis of HLA Class II Eplet Mismatch and Tacrolimus Levels for the Prediction of De Novo Donor Specific Antibody Development in Kidney Transplant Recipients.

We investigated whether HLA class II eplet mismatch was related to dnDSA development and analyzed its combined impact with tacrolimus levels for kidney transplantation outcomes. A total of 347 kidney transplants were included. HLA Matchmaker was used for the single molecular eplet, total eplet, antibody (Ab)-verified eplet mismatch analyses, and Ab-verified single molecular analysis to identify HLA-DR/DQ molecular thresholds for the risk of dnDSA development. A time-weighted tacrolimus trough level (TAC-C0) of 5 ng/mL and a TAC-C0 time-weighted coefficient variability (TWCV) of 20% were applied to find the combined effects on dnDSA development. A high level of mismatch for single molecular eplet (DQ ≥ 10), total eplet (DQ ≥ 12), Ab-verified eplet (DQ ≥ 4), and Ab-verified single molecular eplet (DQ ≥ 4) significantly correlated with HLA class II dnDSA development. Class II dnDSA developed mostly in patients with low TAC-C0 and high eplet mismatch. In the multivariable analyses, low TAC-C0 and high eplet mismatch showed the highest hazard ratio for the development of dnDSA. No significant combined effect was observed in dnDSA development according to TWCV. In conclusion, the determination of HLA class II eplet mismatch may improve the risk stratification for dnDSA development, especially in conjunction with tacrolimus trough levels.

Building a Korean morphological analyzer using two Korean BERT models.

A morphological analyzer plays an essential role in identifying functional suffixes of Korean words. The analyzer input and output differ from each other in their length and strings, which can be dealt with by an encoder-decoder architecture. We adopt a Transformer architecture, which is an encoder-decoder architecture with self-attention rather than a recurrent connection, to implement a Korean morphological analyzer. Bidirectional Encoder Representations from Transformers (BERT) is one of the most popular pretrained representation models; it can present an encoded sequence of input words, considering contextual information. We initialize both the Transformer encoder and decoder with two types of Korean BERT, one of which is pretrained with a raw corpus, and the other is pretrained with a morphologically analyzed dataset. Therefore, implementing a Korean morphological analyzer based on Transformer is a fine-tuning process with a relatively small corpus. A series of experiments proved that parameter initialization using pretrained models can alleviate the chronic problem of a lack of training data and reduce the time required for training. In addition, we can determine the number of layers required for the encoder and decoder to optimize the performance of a Korean morphological analyzer.

Visible-Light-Induced Organophotocatalytic Difunctionallization: Open-Air Hydroxysulfurization of Aryl Alkenes with Aryl Thiols.

Herein, we report a regioselective visible-light-induced organophotoredox catalytic difunctionalization method to prepare ß-hydroxysulfides using aryl alkenes and aryl thiols as substrates. The reaction provides a wide substrate scope of aryl alkenes (from simple styrene to complex bioactive compounds) and aryl thiols (from diverse heteroaromatic thiols to nonheteroaromatic thiols) (total 45 examples, up to 88% yield). Based on the combined experimental and computational studies, we demonstrate that in situ generated hydroperoxyl radicals from O2 in air react with benzylic radicals, which restrains the reaction between benzylic radicals and the acidic form of thiols in a classical thiol-ene radical reaction. We show that difunctionalization is possible due to the choice of bases, diluted substrate concentrations, increment in catalyst loading, and selection of suitable aryl thiols under aerobic conditions. Considering the biological importance of heteroaromatic thiols and the lack of methods to install them, our approach offers a platform to derive various ß-hydroxysulfides that contain aromatic elements.

Ceria-Zirconia nanoparticles reduce intracellular globotriaosylceramide accumulation and attenuate kidney injury by enhancing the autophagy flux in cellular and animal models of Fabry disease.

BACKGROUND: Fabry disease (FD) is a lysosome storage disease (LSD) characterized by significantly reduced intracellular autophagy function. This contributes to the progression of intracellular pathologic signaling and can lead to organ injury. Phospholipid-polyethyleneglycol-capped Ceria-Zirconia antioxidant nanoparticles (PEG-CZNPs) have been reported to enhance autophagy flux. We analyzed whether they suppress globotriaosylceramide (Gb3) accumulation by enhancing autophagy flux and thereby attenuate kidney injury in both cellular and animal models of FD. RESULTS: Gb3 was significantly increased in cultured human renal proximal tubular epithelial cells (HK-2) and human podocytes following the siRNA silencing of α galactosidase A (α-GLA). PEG-CZNPs effectively reduced the intracellular accumulation of Gb3 in both cell models of FD and improved both intracellular inflammation and apoptosis in the HK-2 cell model of FD. Moreover these particles attenuated pro fibrotic cytokines in the human podocyte model of FD. This effect was revealed through an improvement of the intracellular autophagy flux function and a reduction in reactive oxygen species (ROS). An FD animal model was generated in which 4-week-old male B6;129-Glatm1Kul/J mice were treated for 8 weeks with 10 mg/kg of PEG-CZNPs (twice weekly via intraperitoneal injection). Gb3 levels were reduced in the kidney tissues of these animals, and their podocyte characteristics and autophagy flux functions were preserved. CONCLUSIONS: PEG-CZNPs alleviate FD associated kidney injury by enhancing autophagy function and thus provide a foundation for the development of new drugs to treat of storage disease.

Acute kidney injury due to intravenous detergent poisoning: A case report.

BACKGROUND: Detergent poisoning mostly occurs through oral ingestion (> 85%), ocular exposure (< 15%), or dermal exposure (< 8%). Reports of detergent poisoning through an intravenous injection are extremely rare. In addition, there are very few cases of renal toxicity directly caused by detergents. Here, we report a unique case of acute kidney injury caused by detergent poisoning through an accidental intravenous injection. CASE SUMMARY: A 61-year-old man was intravenously injected with 20 mL of detergent by another patient in the same room of a local hospital. The surfactant and calcium carbonate accounted for the largest proportion of the detergent. The patient complained of vascular pain, chest discomfort, and nausea, and was transferred to our institution. After hospitalization, the patient's serum creatinine level increased to 5.42 mg/dL, and his daily urine output decreased to approximately 300 mL. Renal biopsy findings noted that the glomeruli were relatively intact; however, diffuse acute tubular injury was observed. Generalized edema was also noted, and the patient underwent a total of four hemodiafiltration sessions. Afterward, the patient's urine output gradually increased whereas the serum creatinine level decreased. The patient was discharged in a stable status without any sequelae. CONCLUSION: Detergents appear to directly cause renal tubular injury by systemic absorption. In treating a patient with detergent poisoning, physicians should be aware that the renal function may also deteriorate. In addition, timely renal replacement therapy may help improve the patient's prognosis.

Machine learning-based survival rate prediction of Korean hepatocellular carcinoma patients using multi-center data.

AIM: To predict survival time of Korean hepatocellular carcinoma (HCC) patients using multi-center data as a foundation for the development of a predictive artificial intelligence model according to treatment methods based on machine learning. METHODS: Data of patients who underwent treatment for HCC from 2008 to 2015 was provided by Korean Liver Cancer Study Group and Korea Central Cancer Registry. A total of 10,742 patients with HCC were divided into two groups, with Group I (2920 patients) confirmed on biopsy and Group II (5562 patients) diagnosed as HCC according to HCC diagnostic criteria as outlined in Korean Liver Cancer Association guidelines. The data were modeled according to features of patient clinical characteristics. Features effective in predicting survival rate were analyzed retrospectively. Various machine learning methods were used. RESULTS: Target was overall survival time, which divided into approximately 60 months (= /< 60 m, > 60 m). Target distribution in Group I (total 514 samples) was 28.8%: (148 samples) less than 60 months, 71.2% (366 samples) greater than 60 months, and in Group II (total 757 samples) was 66.6% (504 samples) less than 60 months, 33.4% (253 samples) greater than 60 months. Using NG Boost method, its accuracy was 83%, precision 84%, sensitivity 95%, and F1 score 89% for more than 60 months survival time in Group I with surgical resection. Moreover, its accuracy was 79%, precision 82%, sensitivity 87%, and F1 score 84% for less than 60 months survival time in Group II with TACE. The feature importance with gain criterion indicated that pathology, portal vein invasion, surgery, metastasis, and needle biopsy features could be explained as important factors for prediction in case of biopsy (Group I). CONCLUSION: By developing a predictive model using machine learning algorithms to predict prognosis of HCC patients, it is possible to project optimized treatment by case according to liver function and tumor status.