Search

Background: Sepsis is a life-threatening organ dysfunction and a major healthcare burden worldwide. Although sepsis is a medical emergency that requires immediate management, screening for the occurrence of sepsis is difficult. Herein, we propose a deep learning-based model (DLM) for screening sepsis using electrocardiography (ECG)., Methods: This retrospective cohort study included 46,017 patients who were admitted to two hospitals. A total of 1,548 and 639 patients had sepsis and septic shock, respectively. The DLM was developed using 73,727 ECGs from 18,142 patients, and internal validation was conducted using 7774 ECGs from 7,774 patients. Furthermore, we conducted an external validation with 20,101 ECGs from 20,101 patients from another hospital to verify the applicability of the DLM across centers., Results: During the internal and external validations, the area under the receiver operating characteristic curve (AUC) of the DLM using 12-lead ECG was 0.901 (95% confidence interval, 0.882-0.920) and 0.863 (0.846-0.879), respectively, for screening sepsis and 0.906 (95% confidence interval (CI), 0.877-0.936) and 0.899 (95% CI, 0.872-0.925), respectively, for detecting septic shock. The AUC of the DLM for detecting sepsis using 6-lead and single-lead ECGs was 0.845-0.882. A sensitivity map revealed that the QRS complex and T waves were associated with sepsis. Subgroup analysis was conducted using ECGs from 4,609 patients who were admitted with an infectious disease, and the AUC of the DLM for predicting in-hospital mortality was 0.817 (0.793-0.840). There was a significant difference in the prediction score of DLM using ECG according to the presence of infection in the validation dataset (0.277 vs. 0.574, p < 0.001), including severe acute respiratory syndrome coronavirus 2 (0.260 vs. 0.725, p = 0.018)., Conclusions: The DLM delivered reasonable performance for sepsis screening using 12-, 6-, and single-lead ECGs. The results suggest that sepsis can be screened using not only conventional ECG devices but also diverse life-type ECG machines employing the DLM, thereby preventing irreversible disease progression and mortality., (© 2021. The Author(s).)

Background: In-hospital cardiac arrest is a major burden in health care. Although several track-and-trigger systems are used to predict cardiac arrest, they often have unsatisfactory performances. We hypothesized that a deep-learning-based artificial intelligence algorithm (DLA) could effectively predict cardiac arrest using electrocardiography (ECG). We developed and validated a DLA for predicting cardiac arrest using ECG., Methods: We conducted a retrospective study that included 47,505 ECGs of 25,672 adult patients admitted to two hospitals, who underwent at least one ECG from October 2016 to September 2019. The endpoint was occurrence of cardiac arrest within 24 h from ECG. Using subgroup analyses in patients who were initially classified as non-event, we confirmed the delayed occurrence of cardiac arrest and unexpected intensive care unit transfer over 14 days., Results: We used 32,294 ECGs of 10,461 patients and 4483 ECGs of 4483 patients from a hospital were used as development and internal validation data, respectively. Additionally, 10,728 ECGs of 10,728 patients from another hospital were used as external validation data, which confirmed the robustness of the developed DLA. During internal and external validation, the areas under the receiver operating characteristic curves of the DLA in predicting cardiac arrest within 24 h were 0.913 and 0.948, respectively. The high risk group of the DLA showed a significantly higher hazard for delayed cardiac arrest (5.74% vs. 0.33%, P < 0.001) and unexpected intensive care unit transfer (4.23% vs. 0.82%, P < 0.001). A sensitivity map of the DLA displayed the ECG regions used to predict cardiac arrest, with the DLA focused most on the QRS complex., Conclusions: Our DLA successfully predicted cardiac arrest using diverse formats of ECG. The results indicate that cardiac arrest could be screened and predicted not only with a conventional 12-lead ECG, but also with a single-lead ECG using a wearable device that employs our DLA.

Background: In emergency medical services (EMSs), accurately predicting the severity of a patient's medical condition is important for the early identification of those who are vulnerable and at high-risk. In this study, we developed and validated an artificial intelligence (AI) algorithm based on deep learning to predict the need for critical care during EMS., Methods: We conducted a retrospective observation cohort study. The algorithm was established using development data from the Korean national emergency department information system, which were collected during visits in real time from 151 emergency departments (EDs). We validated the algorithm using EMS run sheets from two EDs. The study subjects comprised adult patients who visited EDs. The endpoint was critical care, and we used age, sex, chief complaint, symptom onset to arrival time, trauma, and initial vital signs as the predicted variables., Results: The number of patients in the development data was 8,981,181, and the validation data comprised 2604 EMS run sheets from two hospitals. The area under the receiver operating characteristic curve of the algorithm to predict the critical care was 0.867 (95% confidence interval, [0.864-0.871]). This result outperformed the Emergency Severity Index (0.839 [0.831-0.846]), Korean Triage and Acuity System (0.824 [0.815-0.832]), National Early Warning Score (0.741 [0.734-0.748]), and Modified Early Warning Score (0.696 [0.691-0.699])., Conclusions: The AI algorithm accurately predicted the need for the critical care of patients using information during EMS and outperformed the conventional triage tools and early warning scores.

Background: Krabbe disease is a rare neurodegenerative genetic disorder caused by deficiency of galactocerebrosidase. Patients with the infantile form of Krabbe disease can be treated at a presymptomatic stage with human stem cell transplantation which improves survival and clinical outcomes. However, without a family history, most cases of infantile Krabbe disease present after onset of symptoms and are ineligible for transplantation. In 2006, New York began screening newborns for Krabbe disease to identify presymptomatic cases. To ensure that those identified with infantile disease received timely treatment, New York public health and medical systems took steps to accurately diagnose and rapidly refer infants for human stem cell transplantation within the first few weeks of life. After 11 years of active screening in New York and the introduction of Krabbe disease newborn screening in other states, new information has been gained which can inform the design of newborn screening programs to improve infantile Krabbe disease outcomes., Findings: Recent information relevant to Krabbe disease screening, diagnosis, and treatment were assessed by a diverse group of public health, medical, and advocacy professionals. Outcomes after newborn screening may improve if treatment for infantile disease is initiated before 30 days of life. Newer laboratory screening and diagnostic tools can improve the speed and specificity of diagnosis and help facilitate this early referral. Given the rarity of Krabbe disease, most recommendations were based on case series or expert opinion., Conclusion: This report updates recommendations for Krabbe disease newborn screening to improve the timeliness of diagnosis and treatment of infantile Krabbe disease. In the United States, several states have begun or are considering Krabbe disease newborn screening. These recommendations can guide public health laboratories on methodologies for screening and inform clinicians about the need to promptly diagnose and treat infantile Krabbe disease. The timing of the initial referral after newborn screening, the speed of diagnostic confirmation of infantile disease, and the transplantation center's experience and ability to rapidly respond to a suspected patient with newly diagnosed infantile Krabbe disease are critical for optimal outcomes.

Background: Primary intestinal non-Hodgkin lymphoma (NHL) is a heterogeneous disease with regard to anatomic and histologic distribution. Thus, analyses focusing on primary intestinal NHL with large number of patients are warranted., Methods: We retrospectively analyzed 581 patients from 16 hospitals in Korea for primary intestinal NHL in this retrospective analysis. We compared clinical features and treatment outcomes according to the anatomic site of involvement and histologic subtypes., Results: B-cell lymphoma (n = 504, 86.7%) was more frequent than T-cell lymphoma (n = 77, 13.3%). Diffuse large B-cell lymphoma (DLBCL) was the most common subtype (n = 386, 66.4%), and extranodal marginal zone B-cell lymphoma of mucosa-associated lymphoid tissue (MALT) was the second most common subtype (n = 61, 10.5%). B-cell lymphoma mainly presented as localized disease (Lugano stage I/II) while T-cell lymphomas involved multiple intestinal sites. Thus, T-cell lymphoma had more unfavourable characteristics such as advanced stage at diagnosis, and the 5-year overall survival (OS) rate was significantly lower than B-cell lymphoma (28% versus 71%, P < 0.001). B symptoms were relatively uncommon (20.7%), and bone marrow invasion was a rare event (7.4%). The ileocecal region was the most commonly involved site (39.8%), followed by the small (27.9%) and large intestines (21.5%). Patients underwent surgery showed better OS than patients did not (5-year OS rate 77% versus 57%, P < 0.001). However, this beneficial effect of surgery was only statistically significant in patients with B-cell lymphomas (P < 0.001) not in T-cell lymphomas (P = 0.460). The comparison of survival based on the anatomic site of involvement showed that ileocecal regions had a better 5-year overall survival rate (72%) than other sites in consistent with that ileocecal region had higher proportion of patients with DLBCL who underwent surgery. Age > 60 years, performance status ≥ 2, elevated serum lactate dehydrogenase, Lugano stage IV, presence of B symptoms, and T-cell phenotype were independent prognostic factors for survival., Conclusions: The survival of patients with ileocecal region involvement was better than that of patients with involvement at other sites, which might be related to histologic distribution, the proportion of tumor stage, and need for surgical resection.

Backgrounds: Cisplatin-based chemotherapy, in combination with fluoropyrimidines or taxanes, have demonstrated efficacy against advanced gastric cancer (AGC). This retrospective study was performed with the data obtained from our cancer chemotherapy registry and eight another cancer centers., Methods: In 2008, a total of 283 AGC patients were treated with cisplatin-based doublet chemotherapy in the first-line setting: capecitabine plus cisplatin (XP, n = 77), S-1 plus cisplatin (SP, n = 97), taxanes (docetaxel, paclitaxel) plus cisplatin (TP, n = 72), and 5-fluorouracil plus platinum (FP, n = 37). The primary endpoint of this study was overall survival (OS) and the secondary endpoints were safety, response rate and progression-free survival (PFS)., Results: The median age was 54 years with a range of 28-78 years and median delivered number of chemotherapy cycles were XP: 4, SP: 5, TP: 5 and FP: 5, respectively. Objective tumor responses (38%; 95% CI, 32-43%) were 40% for XP, 42% for SP, 36% for DP, and 24% for FP. The estimated median PFS was 4.5 months (95% CI, 3.6-5.4 months) and the median OS was 12.3 months (95% CI, 10.8-13.7 months). No statistically significant difference was found between each regimen used as first-line chemotherapy. At multivariate analysis, independent prognostic parameters for OS were prior gastrectomy, peritoneal dissemination, performance status and hemoglobin level, Conclusion: All of the cisplatin-based doublet chemotherapy regimens appear to be active as first-line chemotherapy for AGC. With better patient selection according to clinical parameters and molecular markers, clinical outcomes of AGC patients in first-line setting can be improved.