Integrating predictive coding and a user-centric interface for enhanced auditing and quality in cancer registry data.

Data curation for a hospital-based cancer registry heavily relies on the labor-intensive manual abstraction process by cancer registrars to identify cancer-related information from free-text electronic health records. To streamline this process, a natural language processing system incorporating a hybrid of deep learning-based and rule-based approaches for identifying lung cancer registry-related concepts, along with a symbolic expert system that generates registry coding based on weighted rules, was developed. The system is integrated with the hospital information system at a medical center to provide cancer registrars with a patient journey visualization platform. The embedded system offers a comprehensive view of patient reports annotated with significant registry concepts to facilitate the manual coding process and elevate overall quality. Extensive evaluations, including comparisons with state-of-the-art methods, were conducted using a lung cancer dataset comprising 1428 patients from the medical center. The experimental results illustrate the effectiveness of the developed system, consistently achieving F1-scores of 0.85 and 1.00 across 30 coding items. Registrar feedback highlights the system's reliability as a tool for assisting and auditing the abstraction. By presenting key registry items along the timeline of a patient's reports with accurate code predictions, the system improves the quality of registrar outcomes and reduces the labor resources and time required for data abstraction. Our study highlights advancements in cancer registry coding practices, demonstrating that the proposed hybrid weighted neural-symbolic cancer registry system is reliable and efficient for assisting cancer registrars in the coding workflow and contributing to clinical outcomes.

Comprehensive Factors for Predicting the Complications of Diabetes Mellitus: A Systematic Review.

BACKGROUND: This article focuses on extracting a standard feature set for predicting the complications of diabetes mellitus by systematically reviewing the literature. It is conducted and reported by following the guidelines of PRISMA, a well-known systematic review and meta-analysis method. The research articles included in this study are extracted using the search engine "Web of Science" over eight years. The most common complications of diabetes, diabetic neuropathy, retinopathy, nephropathy, and cardiovascular diseases are considered in the study. METHOD: The features used to predict the complications are identified and categorised by scrutinising the standards of electronic health records. RESULT: Overall, 102 research articles have been reviewed, resulting in 59 frequent features being identified. Nineteen attributes are recognised as a standard in all four considered complications, which are age, gender, ethnicity, weight, height, BMI, smoking history, HbA1c, SBP, eGFR, DBP, HDL, LDL, total cholesterol, triglyceride, use of insulin, duration of diabetes, family history of CVD, and diabetes. The existence of a well-accepted and updated feature set for health analytics models to predict the complications of diabetes mellitus is a vital and contemporary requirement. A widely accepted feature set is beneficial for benchmarking the risk factors of complications of diabetes. CONCLUSION: This study is a thorough literature review to provide a clear state of the art for academicians, clinicians, and other stakeholders regarding the risk factors and their importance.

Understanding Physicians' Motivation to Provide Healthcare Service Online in the Digital Age.

This study aims to investigate the factors that affect physicians' healthcare service provision behavior on healthcare service platforms. A research model was proposed based on the related literature and uses and gratifications theory and self-determination theory. The empirical data were collected from a popular Chinese healthcare service platform, and negative binomial regression was employed to test the proposed research model. The results indicate that competence satisfaction, autonomy satisfaction, and economic benefit have positive impacts on their service provision behavior and that when physicians have a higher level of offline status, they would be less likely to provide consultation service online if they have a higher level of competence satisfaction. This study contributes to the existing literature by integrating intrinsic and extrinsic motivations to investigate how they affect physicians' healthcare service provision behavior online. Findings from this study may derive recommendations for improving the features and design of healthcare service platforms.

Predicting Bacteremia among Septic Patients Based on ED Information by Machine Learning Methods: A Comparative Study.

INTRODUCTION: Bacteremia is a common but life-threatening infectious disease. However, a well-defined rule to assess patient risk of bacteremia and the urgency of blood culture is lacking. The aim of this study is to establish a predictive model for bacteremia in septic patients using available big data in the emergency department (ED) through logistic regression and other machine learning (ML) methods. MATERIAL AND METHODS: We conducted a retrospective cohort study at the ED of National Cheng Kung University Hospital in Taiwan from January 2015 to December 2019. ED adults (≥18 years old) with systemic inflammatory response syndrome and receiving blood cultures during the ED stay were included. Models I and II were established based on logistic regression, both of which were derived from support vector machine (SVM) and random forest (RF). Net reclassification index was used to determine which model was superior. RESULTS: During the study period, 437,969 patients visited the study ED, and 40,395 patients were enrolled. Patients diagnosed with bacteremia accounted for 7.7% of the cohort. The area under the receiver operating curve (AUROC) in models I and II was 0.729 (95% CI, 0.718-0.740) and 0.731 (95% CI, 0.721-0.742), with Akaike information criterion (AIC) of 16,840 and 16,803, respectively. The performance of model II was superior to that of model I. The AUROC values of models III and IV in the validation dataset were 0.730 (95% CI, 0.713-0.747) and 0.705 (0.688-0.722), respectively. There is no statistical evidence to support that the performance of the model created with logistic regression is superior to those created by SVM and RF. DISCUSSION: The advantage of the SVM or RF model is that the prediction model is more elastic and not limited to a linear relationship. The advantage of the LR model is that it is easy to explain the influence of the independent variable on the response variable. These models could help medical staff identify high-risk patients and prevent unnecessary antibiotic use. The performance of SVM and RF was not inferior to that of logistic regression. CONCLUSIONS: We established models that provide discrimination in predicting bacteremia among patients with sepsis. The reported results could inspire researchers to adopt ML in their development of prediction algorithms.

Is qSOFA Suitable for Early Diagnosis of Sepsis Among Bacteremia Patients in Emergency Departments? Time for a Reappraisal of Sepsis-3 Criteria.

Background: For early recognition of patients with sepsis, quick Sequential Organ Failure Assessment (qSOFA) was proposed by Sepsis-3 criteria as initial sepsis identification outside of intensive care units. However, the new definition has subsequently led to controversy and prompted much discussion for delayed treatment efforts. We aimed to validate Sepsis-3 criteria on bacteremia patients by investigating prognostic impacts of inappropriate administration of empirical antimicrobial therapy (EAT) and delayed source control (SC) compared to Sepsis-2 criteria. Methods: In the multicenter cohort of adults with community-onset bacteremia in emergency departments (EDs), adverse effects of delayed treatment efforts on 30-day mortality were examined in septic and non-septic patients by fulfilling the Sepsis-2 or Sepsis-3 criteria using the Cox regression model after adjusting independent determinants of mortality. Results: Of the 3,898 total adults, septic patients accounted for 92.8% (3,619 patients) by Sepsis-2 criteria (i.e., SIRS criteria). Using Sepsis-3 criteria, 1,827 (46.9%) patients were diagnosed with early sepsis (i.e., initial qSOFA scores ≥ 2) in EDs and 2,622 (67.3%) with sepsis during hospitalization (i.e., increased SOFA scores of ≥ 2 from ED arrival). The prognostic impacts of inappropriate EAT or delayed SC (for complicated bacteremia) were both significant in septic patients with fulfilling the Sepsis-2 or Sepsis-3 (i.e., SOFA) criteria, respectively. Meanwhile, these delayed treatment efforts trivially impact prognoses of non-septic patients recognized by the Sepsis-2 or Sepsis-3 (i.e., SOFA) definitions. Notably, prognostic effects of inappropriate EAT or delayed SC were disclosed for septic patients in EDs, specifically those with qSOFA scores of ≥ 2, and prognostic impacts of delayed treatment efforts remained significant for patients initially recognized early as being non-septic (i.e., initial qSOFA scores of <2). Conclusions: For patients with community-onset bacteremia, inappropriate EAT and delayed SC might result in unfavorable outcomes of patients early identified as being non-septic on ED arrival based on the qSOFA scores (by Sepsis-3 criteria). Accordingly, a more prudent diagnosis of sepsis adopted among bacteremia patients in the ED is necessary.

Blood Cultures and Appropriate Antimicrobial Administration after Achieving Sustained Return of Spontaneous Circulation in Adults with Nontraumatic Out-of-Hospital Cardiac Arrest.

We aimed to determine the incidence of bacteremia and prognostic effects of prompt administration of appropriate antimicrobial therapy (AAT) on nontraumatic out-of-hospital cardiac arrest (OHCA) patients achieving a sustained return of spontaneous circulation (sROSC), compared with non-OHCA patients. In the multicenter case-control study, nontraumatic OHCA adults with bacteremia episodes after achieving sROSC were defined as case patients, and non-OHCA patients with community-onset bacteremia in the emergency department were regarded as control patients. Initially, case patients had a higher bacteremia incidence than non-OHCA visits (231/2171, 10.6% vs. 10,430/314,620, 3.3%; p < 0.001). Compared with the matched control (2288) patients, case (231) patients experienced more bacteremic episodes due to low respiratory tract infections, fewer urosepsis events, fewer Escherichia coli bacteremia, and more streptococcal and anaerobes bacteremia. Antimicrobial-resistant organisms, such as methicillin-resistant Staphylococcus aureus and extended-spectrum beta-lactamase-producing Enterobacteriaceae, were frequently evident in case patients. Notably, each hour delay in AAT administration was associated with an average increase of 10.6% in crude 30-day mortality rates in case patients, 0.7% in critically ill control patients, and 0.3% in less critically ill control patients. Conclusively, the incidence and characteristics of bacteremia differed between the nontraumatic OHCA and non-OHCA patients. The incorporation of blood culture samplings and rapid AAT administration as first-aids is essential for nontraumatic OHCA patients after achieving sROSC.

The Outcome and Implications of Public Precautionary Measures in Taiwan-Declining Respiratory Disease Cases in the COVID-19 Pandemic.

With the rapid development of the COVID-19 pandemic, countries are trying to cope with increasing medical demands, and, at the same time, to reduce the increase of infected numbers by implementing a number of public health measures, namely non-pharmaceutical interventions (NPIs). These public health measures can include social distancing, frequent handwashing, and personal protective equipment (PPE) at the personal level; at the community and the government level, these measures can range from canceling activities, avoiding mass gatherings, closing facilities, and, at the extreme, enacting national or provincial lockdowns. Rather than completely stopping the infectious disease, the major purpose of these NPIs in facing an emerging infectious disease is to reduce the contact rate within the population, and reduce the spread of the virus until the time a vaccine or reliable medications become available. The idea is to avoid a surge of patients with severe symptoms beyond the capacity of the hospitals' medical resources, which would lead to more mortality and morbidity. While many countries have experienced steep curves in new cases, some, including Hong Kong, Vietnam, South Korea, New Zealand, and Taiwan, seem to have controlled or even eliminated the infection locally. From its first case of COVID-19 on the 21 January until the 12 May, Taiwan had 440 cases, including just 55 local infections, and seven deaths in total, representing 1.85 cases per 100,000 population and a 1.5% death rate (based on the Worldometer 2020 statistics of Taiwan's population of 23.8 million). This paper presents evidence that spread prevention involving mass masking and universal hygiene at the early stage of the COVID-19 pandemic resulted in a 50% decline of infectious respiratory diseases, based on historical data during the influenza season in Taiwan. These outcomes provide potential support for the effectiveness of widely implementing public health precaution measures in controlling COVID-19 without a lockdown policy.