RESUMO
Herein, a novel series of naphthamide derivatives has been rationally developed, synthesized, and evaluated for their inhibitory activity against monoamine oxidase (MAO) and cholinesterase (ChE) enzymes. Compared to the reported naphthalene-based hit IV, the new naphthamide hybrids 2a, 2c, 2g and 2h exhibited promising MAO inhibitory activities; with an IC50 value of 0.294 µM, compound 2c most potently inhibited MAO-A, while compound 2g exhibited most potent MAO-B inhibitory activity with an IC50 value of 0.519 µM. Compounds 2c and 2g showed selectivity index (SI) values of 6.02 for MAO-A and 2.94 for MAO-B, respectively. On the other hand, most compounds showed weak inhibitory activity against ChEs except 2a and 2h over butyrylcholinesterase (BChE). The most potent compounds 2c and 2g were found to be competitive and reversible MAO inhibitors based on kinetic and reversibility studies. Plausible interpretations of the observed biological effects were provided through molecular docking simulations. The drug-likeness predicted by SwissADME and Osiris property explorer showed that the most potent compounds (2a, 2c, 2g, and 2h) obey Lipinski's rule of five. Accordingly, in the context of neurological disorders, hybrids 2c and 2g may contribute to the identification of safe and potent therapeutic approaches in the near future.
RESUMO
The Hedgehog (Hh) signaling pathway plays important roles in various physiological functions. Several malignancies, such as basal cell carcinoma (BCC) and medulloblastoma (MB), have been linked to the aberrant activation of Hh signaling. Although therapeutic drugs have been developed to inhibit Hh pathway-dependent cancer growth, drug resistance remains a major obstacle in cancer treatment. Here, we show that the newly identified, 2-{3-[1-(benzylsulfonyl)-1,2,3,6-tetrahydropyridin-4-yl]-2-methyl-1H-indol-1-yl}-1-(pyrrolidin-1-yl)ethenone analog (LKD1214) exhibits comparable potency to vismodegib in suppressing the Hh pathway activation. LKD1214 represses Smoothened (SMO) activity by blocking its ciliary translocation. Interestingly, we also identified that it has a distinctive binding interface with SMO compared with other SMO-regulating chemicals. Notably, it maintains an inhibitory activity against the SmoD477H mutant, as observed in a patient with vismodegib-resistant BCC. Furthermore, LKD1214 inhibits tumor growth in the mouse model of MB. Collectively, these findings suggest that LKD1214 has the therapeutic potential to overcome drug-resistance in Hh-dependent cancers.
RESUMO
The biological activities and related mechanisms of curcumin, a major polyphenolic compound in turmeric, the rhizome of Curcuma longa, have been extensively investigated. Due to its poor solubility in water, the analysis of curcumin's biological activities is limited in most aqueous experimental systems. In the present study, the effects of polyvinyl alcohol (PVA), a dietary-compatible vehicle, on the solubility, stability, cellular uptake, and bioactivities of curcumin were investigated. Curcumin solubility was improved significantly by PVA; the color intensity of curcumin aqueous solution in the presence of PVA increased concentration-dependently with its peak shift to a shorter wavelength. Improved suspension stability and photostability of curcumin in an aqueous solution were also observed in the presence of PVA, even at 62.5 µg/mL. The scavenging activities of curcumin against DPPH, ABTS, AAPH radicals, and nitric oxide were enhanced significantly in the presence of PVA. PVA at 250 µg/mL also significantly enhanced the cytotoxic activity of curcumin against both HCT 116 colon cancer and INT 407 (HeLa-derived) embryonic intestinal cells by reducing the IC50 from 16 to 11 µM and 25 to 15 µM, respectively. PVA improved the cellular uptake of curcumin in a concentration-dependent manner in INT 407 cells; it increased the cellular levels more effectively at lower curcumin treatment concentrations. The present results indicate that PVA improves the solubility and stability of curcumin, and changes in these chemical behaviors of curcumin in aqueous systems by PVA could enhance the bioavailability and pharmacological efficacy of curcumin.
Assuntos
Curcumina , Álcool de Polivinil , Solubilidade , Curcumina/farmacologia , Curcumina/química , Álcool de Polivinil/química , Humanos , Estabilidade de Medicamentos , Células HCT116 , Células HeLa , Sequestradores de Radicais Livres/química , Sequestradores de Radicais Livres/farmacologia , Sobrevivência Celular/efeitos dos fármacosRESUMO
Acute myeloid leukemia (AML) is the most prevalent type of hematopoietic malignancy. Despite recent therapeutic advancements, the high relapse rate associated with extramedullary involvement remains a challenging issue. Moreover, therapeutic targets that regulate the extramedullary infiltration of AML cells are still not fully elucidated. The Aryl Hydrocarbon Receptor (AHR) is known to influence the progression and migration of solid tumors; however, its role in AML is largely unknown. This study explored the roles of AHR in the invasion and migration of AML cells. We found that suppressed expression of AHR target genes correlated with an elevated relapse rate in AML. Treatment with an AHR agonist on patient-derived AML cells significantly decreased genes associated with leukocyte trans-endothelial migration, cell adhesion, and regulation of the actin cytoskeleton. These results were further confirmed in THP-1 and U937 AML cell lines using AHR agonists (TCDD and FICZ) and inhibitors (SR1 and CH-223191). Treatment with AHR agonists significantly reduced Matrigel invasion, while inhibitors enhanced it, regardless of the Matrigel's stiffness. AHR agonists significantly reduced the migration rate and chemokinesis of both cell lines, but AHR inhibitors enhanced them. Finally, we found that the activity of AHR and the expression of NMIIA are negatively correlated. These findings suggest that AHR activity regulates the invasiveness and motility of AML cells, making AHR a potential therapeutic target for preventing extramedullary infiltration in AML.
Assuntos
Movimento Celular , Leucemia Mieloide Aguda , Cadeias Pesadas de Miosina , Invasividade Neoplásica , Receptores de Hidrocarboneto Arílico , Receptores de Hidrocarboneto Arílico/metabolismo , Receptores de Hidrocarboneto Arílico/genética , Receptores de Hidrocarboneto Arílico/agonistas , Humanos , Leucemia Mieloide Aguda/metabolismo , Leucemia Mieloide Aguda/patologia , Leucemia Mieloide Aguda/genética , Cadeias Pesadas de Miosina/metabolismo , Cadeias Pesadas de Miosina/genética , Miosina não Muscular Tipo IIA/metabolismo , Miosina não Muscular Tipo IIA/genética , Linhagem Celular Tumoral , Feminino , Masculino , Regulação Leucêmica da Expressão Gênica , Pessoa de Meia-Idade , Idoso , Células THP-1 , Células U937 , Adulto , Fatores de Transcrição Hélice-Alça-Hélice BásicosRESUMO
BACKGROUND: The role of visiting health services has been proven to be effective in promoting the health of older populations. Hence, developing a web system for nurses may help improve the quality of visiting health services for community-dwelling frail older adults. This study was conducted to develop a web application that reflects the needs of visiting nurses. METHODS: Visiting nurses of public health centers and community centers in South Korea participated in the design and evaluation process. Six nurses took part in the focus group interviews, and 21 visiting nurses and community center managers participated in the satisfaction evaluation. Focus group interviews were conducted to identify the needs of visiting nurses with respect to system function. Based on the findings, a web application that can support the effective delivery of home visiting services in the community was developed. An artificial intelligence (AI) algorithm was also developed to recommend health and welfare services according to each patient's health status. After development, a structured survey was conducted to evaluate user satisfaction with system features using Kano's model. RESULTS: The new system can be used with mobile devices to increase the mobility of visiting nurses. The system includes 13 features that support the management of patient data and enhance the efficiency of visiting services (e.g., map, navigation, scheduler, protocol archives, professional advice, and online case conferencing). The user satisfaction survey revealed that nurses showed high satisfaction with the system. Among all features, the nurses were most satisfied with the care plan, which included AI-based recommendations for community referral. CONCLUSIONS: The system developed from the study has attractive features for visiting nurses and supports their essential tasks. The system can help with effective case management for older adults requiring in-home care and reduce nurses' workload. It can also improve communication and networking between healthcare and long-term care institutions.
Assuntos
Inteligência Artificial , Enfermeiros de Saúde Comunitária , Humanos , Idoso , Nigéria , Atenção à Saúde , InternetRESUMO
Mealworms (Tenebrio molitor) have been used as an alternative source of proteins and lipids. Triacylglycerols (TAGs) are major sources of energy and have been used to provide essential fatty acids. They are also the main components of mealworm oil, and their composition and content are extensively linked to its physical and chemical properties. However, because of the complexity of TAG molecules, their identification and quantitation are challenging. This study employed electrospray ionization tandem mass spectrometry (ESI-MS/MS) with multiple neutral loss scans (NLS) to analyze the TAG composition and content in mealworm oil. Identifying and quantifying TAGs using ESI-MS/MS in combination with multiple NLS was an efficient way to improve accuracy and timeliness. For the accurate quantification of TAGs, isotopic deconvolution and correlation factors were applied. A total of 57 TAGs were identified and quantified: C52:2 (16:0/18:1/18:1) (1549.4 nmol/g, 18.20%), C52:3 (16:0/18:1/18:2) (1488.1 nmol/g, 17.48%), C54:4 (18:1/18:1/18:2) (870.1 nmol/g, 10.23%), C54:6 (18:1/18:2/18:2) (659.8 nmol/g, 7.76%) and C52:4 (16:0/18:2/18:2) (600.5 nmol/g, 7.06%), which were the most abundant TAGs present in the mealworm oil. The fundamental properties of mealworm oil, including its degree of oxidation, nutritional effect and physical properties, were elucidated.
RESUMO
Sufficient liver regeneration after a right hepatectomy is important in living donors for preventing postoperative hepatic insufficiency; however, it differs for each living donor so we investigated the clinical factors affecting the rate of liver regeneration after hepatic resection. This retrospective case-control study investigated fifty-four living donors who underwent a right hepatectomy from July 2015 to March 2023. Patients were classified into 2 groups by the remnant/total volume ratio (RTVR): Group A (RTVR < 30%, n = 9) and Group B (RTVR ≥ 30%, n = 45). The peak postoperative level of total bilirubin was more elevated in Group A than in Group B (3.0 ± 1.1 mg/dL vs. 2.3 ± 0.8 mg/dL, p = 0.046); however, no patients had hepatic insufficiency or major complications. The rates of residual liver volume (RLV) growth at Postoperative Week 1 (89.1 ± 26.2% vs. 53.5 ± 23.7%, p < 0.001) were significantly greater in Group A, and its significant predictors were RTVR (ß = -0.478, p < 0.001, variance inflation factor (VIF) = 1.188) and intraoperative blood loss (ß = 0.247, p = 0.038, VIF = 1.182). In conclusion, as the RLV decreases, compensatory liver regeneration after hepatic resection becomes more prominent, resulting in comparable operative outcomes. Further studies are required to investigate the relationship between hematopoiesis and the rate of liver regeneration.
RESUMO
BACKGROUND: Predicting the bed occupancy rate (BOR) is essential for efficient hospital resource management, long-term budget planning, and patient care planning. Although macro-level BOR prediction for the entire hospital is crucial, predicting occupancy at a detailed level, such as specific wards and rooms, is more practical and useful for hospital scheduling. OBJECTIVE: The aim of this study was to develop a web-based support tool that allows hospital administrators to grasp the BOR for each ward and room according to different time periods. METHODS: We trained time-series models based on long short-term memory (LSTM) using individual bed data aggregated hourly each day to predict the BOR for each ward and room in the hospital. Ward training involved 2 models with 7- and 30-day time windows, and room training involved models with 3- and 7-day time windows for shorter-term planning. To further improve prediction performance, we added 2 models trained by concatenating dynamic data with static data representing room-specific details. RESULTS: We confirmed the results of a total of 12 models using bidirectional long short-term memory (Bi-LSTM) and LSTM, and the model based on Bi-LSTM showed better performance. The ward-level prediction model had a mean absolute error (MAE) of 0.067, mean square error (MSE) of 0.009, root mean square error (RMSE) of 0.094, and R2 score of 0.544. Among the room-level prediction models, the model that combined static data exhibited superior performance, with a MAE of 0.129, MSE of 0.050, RMSE of 0.227, and R2 score of 0.600. Model results can be displayed on an electronic dashboard for easy access via the web. CONCLUSIONS: We have proposed predictive BOR models for individual wards and rooms that demonstrate high performance. The results can be visualized through a web-based dashboard, aiding hospital administrators in bed operation planning. This contributes to resource optimization and the reduction of hospital resource use.
RESUMO
Hypoxia-inducible factor (HIF)-1α is a crucial transcription factor associated with cancer metabolism and is regarded as a potent anticancer therapeutic strategy within the hypoxic microenvironment of cancer. In this study, stilbenoid derivatives were designed, synthesized, and assessed for their capacity to inhibit HIF-1α-associated cancer metabolism and evaluated for inhibition of cancer cell viability and HIF activation. Through the structure-activity relationship studies, compound 28e was identified as the most potent derivative. Specifically, under the hypoxic condition, 28e reduced the accumulation of HIF-1α protein and the expression of its target genes related to glucose metabolism without affecting the expression of HIF-1α mRNA. Furthermore, 28e inhibited glucose uptake, glycolytic metabolism, and mitochondrial respiration, decreasing cellular ATP production under hypoxic conditions. In addition, 28e displayed significant anti-tumor effects and effectively suppressed the accumulation of HIF-1α protein in tumor tissue in vivo xenograft model. These findings suggest that our stilbenoid derivatives exert their anticancer effects by targeting HIF-1α-centered cancer metabolism under hypoxic conditions.
Assuntos
Subunidade alfa do Fator 1 Induzível por Hipóxia , Estilbenos , Animais , Humanos , Camundongos , Antineoplásicos/farmacologia , Hipóxia Celular/efeitos dos fármacos , Linhagem Celular Tumoral , Sobrevivência Celular/efeitos dos fármacos , Glucose/metabolismo , Glicólise/efeitos dos fármacos , Subunidade alfa do Fator 1 Induzível por Hipóxia/metabolismo , Subunidade alfa do Fator 1 Induzível por Hipóxia/antagonistas & inibidores , Camundongos Endogâmicos BALB C , Camundongos Nus , Neoplasias/tratamento farmacológico , Neoplasias/metabolismo , Neoplasias/patologia , Estilbenos/farmacologia , Relação Estrutura-Atividade , Ensaios Antitumorais Modelo de XenoenxertoRESUMO
Loop diuretics are prevailing drugs to manage fluid overload in heart failure. However, adjusting to loop diuretic doses is strenuous due to the lack of a diuretic guideline. Accordingly, we developed a novel clinician decision support system for adjusting loop diuretics dosage with a Long Short-Term Memory (LSTM) algorithm using time-series EMRs. Weight measurements were used as the target to estimate fluid loss during diuretic therapy. We designed the TSFD-LSTM, a bi-directional LSTM model with an attention mechanism, to forecast weight change 48 h after heart failure patients were injected with loop diuretics. The model utilized 65 variables, including disease conditions, concurrent medications, laboratory results, vital signs, and physical measurements from EMRs. The framework processed four sequences simultaneously as inputs. An ablation study on attention mechanisms and a comparison with the transformer model as a baseline were conducted. The TSFD-LSTM outperformed the other models, achieving 85% predictive accuracy with MAE and MSE values of 0.56 and 1.45, respectively. Thus, the TSFD-LSTM model can aid in personalized loop diuretic treatment and prevent adverse drug events, contributing to improved healthcare efficacy for heart failure patients.
Assuntos
Insuficiência Cardíaca , Humanos , Insuficiência Cardíaca/tratamento farmacológico , Masculino , Feminino , Idoso , Algoritmos , Pessoa de Meia-Idade , Peso Corporal , Diuréticos/administração & dosagem , Inibidores de Simportadores de Cloreto de Sódio e Potássio/administração & dosagem , Memória de Curto Prazo/efeitos dos fármacosRESUMO
The sedimentation of organic carbon in the Ulleung Basin, in the southwestern East Sea (Japan Sea) was investigated using radiocarbon and sterols. The accumulation rates of organic carbon and the contents of brassicasterol and dinosterol were higher on the slope than in the central basin, reflecting the surface water productivity, whereas cholesterol showed similar or higher contents in the central basin. The coprostanol concentration in surface sediments reflected the dispersion of sewage dumped in this region. The vertical distribution showed that the coprostanol concentration was the highest in the top 5-cm layer near the Korea Strait, close to one of the two dumping sites. A high coprostanol concentration was also found near the coast further north, where the content peaked at â¼10 cm depth. The vertical distribution of coprostanol helped to estimate the sediment accumulation rate at sites where radiocarbon gradient was too small or the values were too variable.
Assuntos
Monitoramento Ambiental , Sedimentos Geológicos , Esgotos , Esteróis , Sedimentos Geológicos/química , Esgotos/química , Esteróis/análise , Oceanos e Mares , Japão , Poluentes Químicos da Água/análiseRESUMO
Antipsychotic polypharmacy is commonly used in clinical settings, with a growing trend in using long-acting injections to mitigate many side effects of polypharmacy. A previous study demonstrated that long-acting aripiprazole once-monthly (AOM) injection increased treatment adherence, restored functionality, and improved symptoms. However, there is insufficient evidence to demonstrate the therapeutic effects of AOM in polypharmacy practice. This observational study aimed to investigate the real-world clinical benefits and effectiveness of AOM by assessing changes in drug dosage, the number of drugs, clinical functioning, psychotic symptoms, and the duration of drug efficacy. Study participants were recruited from eight study sites, with the baseline visit marking the initiation of drug treatment. Clinical and demographic data were collected from medical records at screening, baseline, and months 1, 3, 6, 9, and 12. Over 12 months, we analyzed changes in drug dosage, the number of drugs, and scores of the Positive and Negative Syndrome Scale-6 (PANSS-6), Global Assessment of Functioning (GAF), and Clinical Global Impression-Severity (CGIS). Data from 139 participants were analyzed. Total 12-month antipsychotic doses calculated in chlorpromazine equivalents (CPE) were reduced by 32.6%. A comparison of total monthly antipsychotic doses in CPE between the first and last months showed a 24.6% reduction in the dose. Additionally, the quantity of benzodiazepine tablets/capsules, total benzodiazepine doses calculated in lorazepam equivalents, and quantity of tablets/capsules of mood stabilizers, anticholinergics, and beta blockers were significantly reduced. GAF scores increased by 14.1% over 12 months, and PANSS-6 total scores reduced by 17.3% over 12 months, with significant differences observed from month 1 and baseline, respectively. The scores steadily improved until month 9 compared to those of the previous months, continuing to improve through month 12. The CGI-S score reduced by 14.3% over 12 months, showing a significant decrease from month 1 and a steady improvement until month 6, maintaining this improvement until month 12. In conclusion, this study demonstrated the early effectiveness of AOM in treating Korean patients with schizophrenia on polypharmacy. AOM improved function and clinical symptoms in patients with schizophrenia from treatment onset and caused a decrease in the quantity and dosage of drugs taken by the patients.
RESUMO
High-rate production of multicarbon chemicals via the electrochemical CO2 reduction can be achieved by efficient CO2 mass transport. A key challenge for C-C coupling in high-current-density CO2 reduction is how to promote *CO formation and dimerization. Here, we report molecularly enhanced CO2-to-*CO conversion and *CO dimerization for high-rate ethylene production. Nanoconfinement of ascorbic acid by graphene quantum dots enables immobilization and redox reversibility of ascorbic acid in heterogeneous electrocatalysts. Cu nanowire with ascorbic acid nanoconfined by graphene quantum dots (cAA-CuNW) demonstrates high-rate ethylene production with a Faradaic efficiency of 60.7% and a partial current density of 539 mA/cm2, a 2.9-fold improvement over that of pristine CuNW. Furthermore, under low CO2 ratio of 33%, cAA-CuNW still exhibits efficient ethylene production with a Faradaic efficiency of 41.8%. We find that cAA-CuNW increases *CO coverage and optimizes the *CO binding mode ensemble between atop and bridge for efficient C-C coupling. A mechanistic study reveals that ascorbic acid can facilitate *CO formation and dimerization by favorable electron and proton transfer with strong hydrogen bonding.
RESUMO
Background and Objective: Although interest in predicting drug-drug interactions is growing, many predictions are not verified by real-world data. This study aimed to confirm whether predicted polypharmacy side effects using public data also occur in data from actual patients. Methods: We utilized a deep learning-based polypharmacy side effects prediction model to identify cefpodoxime-chlorpheniramine-lung edema combination with a high prediction score and a significant patient population. The retrospective study analyzed patients over 18 years old who were admitted to the Asan medical center between January 2000 and December 2020 and took cefpodoxime or chlorpheniramine orally. The three groups, cefpodoxime-treated, chlorpheniramine-treated, and cefpodoxime & chlorpheniramine-treated were compared using inverse probability of treatment weighting (IPTW) to balance them. Differences between the three groups were analyzed using the Kaplan-Meier method and Cox proportional hazards model. Results: The study population comprised 54,043 patients with a history of taking cefpodoxime, 203,897 patients with a history of taking chlorpheniramine, and 1,628 patients with a history of taking cefpodoxime and chlorpheniramine simultaneously. After adjustment, the 1-year cumulative incidence of lung edema in the patient group that took cefpodoxime and chlorpheniramine simultaneously was significantly higher than in the patient groups that took cefpodoxime or chlorpheniramine only (p=0.001). Patients taking cefpodoxime and chlorpheniramine together had an increased risk of lung edema compared to those taking cefpodoxime alone [hazard ratio (HR) 2.10, 95% CI 1.26-3.52, p<0.005] and those taking chlorpheniramine alone, which also increased the risk of lung edema (HR 1.64, 95% CI 0.99-2.69, p=0.05). Conclusions: Validation of polypharmacy side effect predictions with real-world data can aid patient and clinician decision-making before conducting randomized controlled trials. Simultaneous use of cefpodoxime and chlorpheniramine was associated with a higher long-term risk of lung edema compared to the use of cefpodoxime or chlorpheniramine alone.
RESUMO
Despite increased awareness and availability of genetic testing for hereditary breast and ovarian cancer (HBOC) syndrome for over 20 years, there is still significant underuse of cascade genetic testing among at-risk relatives. This scoping review synthesized evidence regarding psychosocial barriers and facilitators of family communication and/or uptake of cascade genetic testing in relatives from HBOC families. Search terms included 'hereditary breast and ovarian cancer' and 'cascade genetic testing' for studies published from 2012-2022. Through searching common databases, and manual search of references, 480 studies were identified after excluding duplications. Each article was reviewed by two researchers independently and 20 studies were included in the final analysis. CASP, RoBANS 2.0, RoB 2.0, and MMAT were used to assess the quality of included studies. A convergent data synthesis method was used to integrate evidence from quantitative and narrative data into categories and subcategories. Evidence points to 3 categories and 12 subcategories of psychosocial barriers and facilitators for cascade testing: (1) facilitators (belief in health protection and prevention; family closeness; decisional empowerment; family support, sense of responsibility; self-efficacy; supportive health professionals); (2) bidirectional concepts (information; perception of genetic/cancer consequences; negative emotions and attitude); and (3) barriers (negative reactions from family and negative family dynamics). Healthcare providers need to systematically evaluate these psychosocial factors, strengthen facilitators and alleviate barriers to promote informed decision-making for communication of genetic test results and uptake of genetic testing. Bidirectional factors merit special consideration and tailored approaches, as they can potentially have a positive or negative influence on family communication and uptake of genetic testing.
Assuntos
Predisposição Genética para Doença , Testes Genéticos , Humanos , Feminino , Predisposição Genética para Doença/psicologia , Neoplasias Ovarianas/genética , Neoplasias Ovarianas/psicologia , Neoplasias Ovarianas/diagnóstico , Síndrome Hereditária de Câncer de Mama e Ovário/genética , Síndrome Hereditária de Câncer de Mama e Ovário/psicologia , Síndrome Hereditária de Câncer de Mama e Ovário/diagnóstico , Neoplasias da Mama/genética , Neoplasias da Mama/psicologia , Neoplasias da Mama/diagnóstico , Família/psicologiaRESUMO
As warfarin has a narrow therapeutic window and obvious response variability among individuals, it is difficult to rapidly determine personalized warfarin dosage. Adverse drug events(ADE) resulting from warfarin overdose can be critical, so that typically physicians adjust the warfarin dosage through the INR monitoring twice a week when starting warfarin. Our study aimed to develop machine learning (ML) models that predicts the discharge dosage of warfarin as the initial warfarin dosage using clinical data derived from electronic medical records within 2 days of hospitalization. During this retrospective study, adult patients who were prescribed warfarin at Asan Medical Center (AMC) between January 1, 2018, and October 31, 2020, were recruited as a model development cohort (n = 3168). Additionally, we created an external validation dataset (n = 891) from a Medical Information Mart for Intensive Care III (MIMIC-III). Variables for a model prediction were selected based on the clinical rationale that turned out to be associated with warfarin dosage, such as bleeding. The discharge dosage of warfarin was used the study outcome, because we assumed that patients achieved target INR at discharge. In this study, four ML models that predicted the warfarin discharge dosage were developed. We evaluated the model performance using the mean absolute error (MAE) and prediction accuracy. Finally, we compared the accuracy of the predictions of our models and the predictions of physicians for 40 data point to verify a clinical relevance of the models. The MAEs obtained using the internal validation set were as follows: XGBoost, 0.9; artificial neural network, 0.9; random forest, 1.0; linear regression, 1.0; and physicians, 1.3. As a result, our models had better prediction accuracy than the physicians, who have difficulty determining the warfarin discharge dosage using clinical information obtained within 2 days of hospitalization. We not only conducted the internal validation but also external validation. In conclusion, our ML model could help physicians predict the warfarin discharge dosage as the initial warfarin dosage from Korean population. However, conducting a successfully external validation in a further work is required for the application of the models.