Using artificial intelligence to predict adverse outcomes in emergency department patients with hyperglycemic crises in real time.

BACKGROUND: Hyperglycemic crises are associated with high morbidity and mortality. Previous studies have proposed methods to predict adverse outcomes of patients in hyperglycemic crises; however, artificial intelligence (AI) has never been used to predict adverse outcomes. We implemented an AI model integrated with the hospital information system (HIS) to clarify whether AI could predict adverse outcomes. METHODS: We included 2,666 patients with hyperglycemic crises from emergency departments (ED) between 2009 and 2018. The patients were randomized into a 70%/30% split for AI model training and testing. Twenty-two feature variables from the electronic medical records were collected. The performance of the multilayer perceptron (MLP), logistic regression, random forest, Light Gradient Boosting Machine (LightGBM), support vector machine (SVM), and K-nearest neighbor (KNN) algorithms was compared. We selected the best algorithm to construct an AI model to predict sepsis or septic shock, intensive care unit (ICU) admission, and all-cause mortality within 1 month. The outcomes between the non-AI and AI groups were compared after implementing the HIS and predicting the hyperglycemic crisis death (PHD) score. RESULTS: The MLP had the best performance in predicting the three adverse outcomes, compared with the random forest, logistic regression, SVM, KNN, and LightGBM models. The areas under the curves (AUCs) using the MLP model were 0.852 for sepsis or septic shock, 0.743 for ICU admission, and 0.796 for all-cause mortality. Furthermore, we integrated the AI predictive model with the HIS to assist decision making in real time. No significant differences in ICU admission or all-cause mortality were detected between the non-AI and AI groups. The AI model performed better than the PHD score for predicting all-cause mortality (AUC 0.796 vs. 0.693). CONCLUSIONS: A real-time AI predictive model is a promising method for predicting adverse outcomes in ED patients with hyperglycemic crises. Further studies recruiting more patients are warranted.

The beneficial effect of synbiotics consumption on Alzheimer's disease mouse model via reducing local and systemic inflammation.

Alzheimer's disease (AD) is a neurodegenerative disease that impairs multiple memory domains without an effective prevention or treatment approach. Amyloid plaque-induced neuroinflammation exacerbates neurodegeneration and cognitive impairment in AD. To reduce neuroinflammation, we applied prebiotics or synbiotics to modulate the gut-brain axis in the AD mouse model. AD-like deficits were reduced in mice treated with synbiotics, suggesting that dietary modulation of the gut-brain axis is a potential approach to delay AD progression.

Predicting outcomes in older ED patients with influenza in real time using a big data-driven and machine learning approach to the hospital information system.

BACKGROUND: Predicting outcomes in older patients with influenza in the emergency department (ED) by machine learning (ML) has never been implemented. Therefore, we conducted this study to clarify the clinical utility of implementing ML. METHODS: We recruited 5508 older ED patients (≥65 years old) in three hospitals between 2009 and 2018. Patients were randomized into a 70%/30% split for model training and testing. Using 10 clinical variables from their electronic health records, a prediction model using the synthetic minority oversampling technique preprocessing algorithm was constructed to predict five outcomes. RESULTS: The best areas under the curves of predicting outcomes were: random forest model for hospitalization (0.840), pneumonia (0.765), and sepsis or septic shock (0.857), XGBoost for intensive care unit admission (0.902), and logistic regression for in-hospital mortality (0.889) in the testing data. The predictive model was further applied in the hospital information system to assist physicians' decisions in real time. CONCLUSIONS: ML is a promising way to assist physicians in predicting outcomes in older ED patients with influenza in real time. Evaluations of the effectiveness and impact are needed in the future.

Management of incontinence-associated dermatitis with topical antibiotics and antifungal medication.

OBJECTIVE: The primary goals of managing incontinence-associated dermatitis (IAD) are to control the incontinence and to stop the progress of dermatitis. This study evaluated the effectiveness of using a combination of topical antibiotic and topical antifungal medication to manage IAD. METHOD: Patients with grade 2 IAD treated with a combination of topical antibiotic Biomycin (CBC Biotechnological and Pharmaceutical, Taiwan) and antifungal clotrimazole (Sinphar Group, Taiwan) between January 2017 and January 2019 were included in this retrospective study. Data collected included patients' age, sex, diagnosis, body mass index, comorbidities and surface area involved. Patients were reviewed fortnightly until the wounds had healed, the patient was discharged or had died. RESULTS: A total of 76 patients were included. There were 39 men and 37 women with a mean age of 74 years. In 58 (76%) patients, the surface area involved was >50cm2, in 13 (17%) patients the involved area was 20-50cm2 and in five (7%) patients the area involved was <20cm2. The mean number of days treated was 10.3 (range: 1-53). A total of 46 (61%) patients showed total healing of their IAD, 17 (22%) patients showed improvement of >50% of the involved area, seven (9%) patients showed improvement of 0-50%, five (7%) patients showed no improvement and one (1%) patient showed an increase in the area involved. CONCLUSION: This combination of treatment was effective in the management of IAD. It was cheap, easy to apply, easy to remove and easily accessible. It could be used efficiently by the hospital staff and the patient's family.

Effects of individual characteristics on insomnia severity trajectory among nurses: A prospective longitudinal study.

AIMS: To examine the longitudinal effects of individual characteristics on the change pattern of insomnia and the association of occupational stress with insomnia over time in newly graduated nurses. BACKGROUND: The association between individual factors and insomnia in nurses is inconclusive. Longitudinal research on insomnia in newly graduated nurses is limited. METHODS: This prospective longitudinal study included 200 participants generating 800 observations of insomnia severity during their first year of nursing. We employed growth mixture modelling for data analyses. Both time-varying covariate (occupational stress) and time-invariant covariates (nurses' characteristics) were entered into the model simultaneously. RESULTS: Nurses had a homogeneous insomnia trajectory during the whole year of survey. The educational level significantly predicted the growth rate of insomnia severity among nurses. Occupational stress at each time point was significantly associated with worse insomnia across time points (all p < .001). CONCLUSIONS: Nurses with a baccalaureate degree were more resilient to the development of severe insomnia. Additional studies have an opportunity to investigate the reason for the effects of the educational level on the pattern of insomnia. IMPLICATIONS FOR NURSING MANAGEMENT: Considering nurses' occupational stress and educational level would lead more effective management of stress and insomnia in newly graduated nurses.

[Facing Children Suffering From Physical Abuse: The Decision-Making Process of Non-Abusing Caregivers].

BACKGROUND: Physical abuse is the most common type of child maltreatment reported in Taiwan. The action of non-abusing caregivers is key to ending this maltreatment and to preventing future victimization in the home. PURPOSE: The purpose of this study was to explore the decision-making process used by non-abusing caregivers to take action after finding that children under their care were being physically abused at home. METHODS: A qualitative descriptive approach was adopted and purposive, snowball sampling was used to recruit 11 non-abusing caregivers of children less than 18 years of age who were experiencing physical abuse at home. Data were collected using semi-structured, in-depth interviews. Data analysis was performed using a constant comparison method that was based on grounded theory principles and techniques. RESULTS: The participants adopted a process that shifted over time from passive observation to active participation in dealing with children under their care being physically abused at home. The three main categories and five subcategories in this process are (1) inaction (shirking parental responsibility and rationalizing spouse's use of corporal punishment); (2) obscure action (family harmony first; strategic solutions); and (3) action (bottom line for asking for help). In this study, the decision-making process was influenced by personal, family, and sociocultural factors. CONCLUSIONS / IMPLICATIONS FOR PRACTICE: The decision of the non-abusing caregivers in this study whether or not to take action was influenced by situational factors, which led to various consequences for their children. Non-abusing caregivers should be provided with coping strategies and resources to help them make decisions that protect the best interests of the physically abused child.

A surface antigen of Orientia tsutsugamushi activates human monocyte-derived dendritic cells via nuclear factor-kB & p38 mitogen-activated protein kinase pathways.

BACKGROUND & OBJECTIVES: Scrub typhus is a chigger-borne disease caused by Orientia tsutsugamushi. The immunological reactions to O. tsutsugamushi infection are not completely understood. In this study, we investigated the response of dendritic cells (DCs) to a major 56-kDa scrub typhus antigen Sta56. METHODS: Monocyte-derived human DCs were incubated with different concentrations of recombinant Sta56 and analyzed for maturation based on phagocytic capacity, the ability to induce T-cell proliferation, expression of surface markers, cytokine secretion and activation of toll-like receptor (TLR)-dependent signalling pathways. RESULTS: Treatment of DCs with Sta56 induced cell surface expression of CD80, CD83, CD86 and MHC Class II increased the production of interleukin-12 (IL-12) p40, IL-12 p70 and IL-10 and decreased DC phagocytic capacity. Furthermore, Sta56 increased the ability of DCs to activate T-cell proliferation and interferon-γ secretion. TLR4-specific antibodies neutralized Sta56-elicited effects on DC maturation, suggesting direct interaction between Sta56 and TLR4. Moreover, Sta56 activated nuclear factor (NF)-κB and p38 mitogen-activated protein kinase (MAPK) signalling as evidenced by decrease in Sta56-induced cytokine production and surface marker expression by specific inhibitors helenalin and SB203580, respectively, and increase in IκBα and p38 phosphorylation and NF-κB-DNA binding. INTERPRETATION & CONCLUSIONS: Our results showed that the surface antigen of O. tsutsugamushi activated DCs through interaction with TLR4 and activation of MAPK and NF-κB signalling, suggesting Sta56 as a potential candidate molecule for the development of vaccine against scrub typhus.

[Ethical Debates Related to the Allocation of Medical Resources During the Response to the Mass Casualty Incident at Formosa Fun Coast Water Park].

Disasters are unpredictable and often result in mass casualties. Limited medical resources often affect the response to mass casualty incidents, undermining the ability of responders to adequately protect all of the casualties. Thus, the injuries of casualties are classified in hopes of fully utilizing medical resources efficiently in order to save the maximum possible number of people. However, as opinions on casualty prioritization are subjective, disagreements and disputes often arise regarding allocating medical resources. The present article focused on the 2015 explosion at Formosa Fun Coast, a recreational water park in Bali, New Taipei City, Taiwan as a way to explore the dilemma over the triage and resource allocation for casualties with burns over 90% and 50-60% of their bodies. The principles of utilitarianism and deontology in Western medicine were used to discuss the reasons and rationale behind the allocation of medical resources during this incident. Confucianism, a philosophical mindset that significantly influences Taiwanese society today, was then discussed to describe the "miracles" that happened during the incident, including the acquisition of assistance from the public and medical professionals. External supplies and professional help (social resources) were provided voluntarily after this incident, which had a profound impact on both the immediate response and the longer-term recovery efforts.

Developing a mobile electronic D2B checklist for treatment of ST elevation myocardial infarction patients who need a primary coronary intervention.

ST elevation myocardial infarction (STEMI), one main type of acute myocardial infarction with high mortality, requires percutaneous coronary intervention (PCI) with balloon inflation. Current guidelines recommend a door-to-balloon (D2B) interval (i.e., starts with the patient's arrival in the emergency department and ends when PCI with a catheter guidewire and balloon inflation crosses the culprit lesion) of no more than 90 min. However, promptly implementing PCI requires coordinating various medical teams. Checklists can be used to ensure consistency and operating sequences when executing complex tasks in a clinical routine. Developing an effective D2B checklist would enhance the care of STEMI patients who need PCI. Mobile information and communication technologies have the potential to greatly improve communication, facilitate access to information, and eliminate duplicated documentation without the limitations of space and time. In a research project by the Chi Mei Medical Center, "Developing a Mobile Electronic D2B Checklist for Managing the Treatment of STEMI Patients Who Need Primary Coronary Intervention," a prototype version of a mobile checklist was developed. This study describes the research project and the four phases of the system development life cycle, comprising system planning and selection, analysis, design, and implementation and operation. Face-to-face interviews with 16 potential users were conducted and revealed highly positive user perception and use intention toward the prototype. Discussion and directions for future research are also presented.

The immunologically active oligosaccharides isolated from wheatgrass modulate monocytes via Toll-like receptor-2 signaling.

Wheatgrass is one of the most widely used health foods, but its functional components and mechanisms remain unexplored. Herein, wheatgrass-derived oligosaccharides (WG-PS3) were isolated and found to induce CD69 and Th1 cytokine expression in human peripheral blood mononuclear cells. In particular, WG-PS3 directly activated the purified monocytes by inducing the expression of CD69, CD80, CD86, IL-12, and TNF-α but affected NK and T cells only in the presence of monocytes. After further purification and structural analysis, maltoheptaose was identified from WG-PS3 as an immunomodulator. Maltoheptaose activated monocytes via Toll-like receptor 2 (TLR-2) signaling, as discovered by pretreatment of blocking antibodies against Toll-like receptors (TLRs) and also determined by click chemistry. This study is the first to reveal the immunostimulatory component of wheatgrass with well defined molecular structures and mechanisms.

The difference in immune response and IL-12p35 methylation between newborns and adults.

BACKGROUND: The immune system of newborn is generally depressed by impaired production of Th1-cell associated cytokines, which results in increased susceptibility to intracellular pathogens and poor response to vaccinations. For avoiding abortion, the maternal and fetal immune systems tend to Th2-cell polarizing cytokines. Besides, IL-12p35 is a determining factor of the bioactivity of IL-12, which has an important role in the Th1 response. Recently methylated DNA is known to associate to inhibit transcription. Therefore, we explored the methylation status of CpG sites upstream of the coding sequence of the IL-12p35 gene to determine whether neonatal peripheral blood mononuclear cell (PBMC) synthesis lower level of IL-12 is related to methylated DNA. RESULTS: PBMCs from adults expressed higher levels of IL-12p40 (p = 0.303) and IL-12p70 (p = 0.045) and had a strong ability to produce IL-12p35 mRNA (p = 0.01). However, there was no difference in the methylation status of CpG sites in the promoter of IL-12p35 between adults and newborns. CONCLUSIONS: We found that PBMC synthesis of bioactive IL-12p70 was significantly impaired in the neonatal period, potentially though a reduction in IL-12p35 production. The reeducation in IL-12p35 production might not be due to methylation of the promoter gene. But, the impairment of IL-12p35 expression during the neonatal period might be caused by other epigenetic regulation occurs in the chromatin level.

Factors Associated with Evidence-Based Practice Competencies among Taiwanese Nurses: A Cross-Sectional Study.

Evidence-based practice (EBP) is an essential component of healthcare practice that ensures the delivery of high-quality care by integrating the best available evidence. This study aimed to explore factors influencing EBP among nursing professionals in Taiwan. A cross-sectional survey study was conducted with 752 registered nurses and nurse practitioners recruited from a regional teaching hospital in southern Taiwan. EBP competency was evaluated using the Taipei Evidence-Based Practice Questionnaire (TEBPQ). The results showed that participation in evidence-based courses or training within the past year had the strongest association with EBP competencies (Std. B = 0.157, p < 0.001). Holding a graduate degree (Std. B = 0.151, p < 0.001), working in gynecology or pediatrics (Std. B = 0.126, p < 0.001), searching the literature in electronic databases (Std. B = 0.072, p = 0.039), and able to read academic articles in English (Std. B = 0.088, p = 0.005) were significantly associated with higher TEBPQ scores. Younger age (Std. B = -0.105, p = 0.005) and male gender (Std. B = 0.089, p = 0.010) were also identified as factors contributing to higher EBP competencies. The study highlights the importance of ongoing professional development, including EBP training and language proficiency, in enhancing EBP competencies among nursing professionals in Taiwan.

Implementing Explainable Machine Learning Models for Practical Prediction of Early Neonatal Hypoglycemia.

Hypoglycemia is a common metabolic disorder that occurs in the neonatal period. Early identification of neonates at risk of developing hypoglycemia can optimize therapeutic strategies in neonatal care. This study aims to develop a machine learning model and implement a predictive application to assist clinicians in accurately predicting the risk of neonatal hypoglycemia within four hours after birth. Our retrospective study analyzed data from neonates born ≥35 weeks gestational age and admitted to the well-baby nursery between 1 January 2011 and 31 August 2021. We collected electronic medical records of 2687 neonates from a tertiary medical center in Southern Taiwan. Using 12 clinically relevant features, we evaluated nine machine learning approaches to build the predictive models. We selected the models with the highest area under the receiver operating characteristic curve (AUC) for integration into our hospital information system (HIS). The top three AUC values for the early neonatal hypoglycemia prediction models were 0.739 for Stacking, 0.732 for Random Forest and 0.732 for Voting. Random Forest is considered the best model because it has a relatively high AUC and shows no significant overfitting (accuracy of 0.658, sensitivity of 0.682, specificity of 0.649, F1 score of 0.517 and precision of 0.417). The best model was incorporated in the web-based application integrated into the hospital information system. Shapley Additive Explanation (SHAP) values indicated mode of delivery, gestational age, multiparity, respiratory distress, and birth weight < 2500 gm as the top five predictors of neonatal hypoglycemia. The implementation of our machine learning model provides an effective tool that assists clinicians in accurately identifying at-risk neonates for early neonatal hypoglycemia, thereby allowing timely interventions and treatments.

Real-time artificial intelligence predicts adverse outcomes in acute pancreatitis in the emergency department: Comparison with clinical decision rule.

OBJECTIVE: Artificial intelligence (AI) prediction is increasingly used for decision making in health care, but its application for adverse outcomes in emergency department (ED) patients with acute pancreatitis (AP) is not well understood. This study aimed to clarify this aspect. METHODS: Data from 8274 ED patients with AP in three hospitals from 2009 to 2018 were analyzed. Demographic data, comorbidities, laboratory results, and adverse outcomes were included. Six algorithms were evaluated, and the one with the highest area under the curve (AUC) was implemented into the hospital information system (HIS) for real-time prediction. Predictive accuracy was compared between the AI model and Bedside Index for Severity in Acute Pancreatitis (BISAP). RESULTS: The mean ± SD age was 56.1 ± 16.7 years, with 67.7% being male. The AI model was successfully implemented in the HIS, with Light Gradient Boosting Machine (LightGBM) showing the highest AUC for sepsis (AUC 0.961) and intensive care unit (ICU) admission (AUC 0.973), and eXtreme Gradient Boosting (XGBoost) showing the highest AUC for mortality (AUC 0.975). Compared to BISAP, the AI model had superior AUC for sepsis (BISAP 0.785), ICU admission (BISAP 0.778), and mortality (BISAP 0.817). CONCLUSIONS: The first real-time AI prediction model implemented in the HIS for predicting adverse outcomes in ED patients with AP shows favorable initial results. However, further external validation is needed to ensure its reliability and accuracy.

Topical Antibiotic Prophylaxis for Preventing Surgical Site Infections of Clean Wounds: A Systematic Review and Meta-Analysis.

Background: Topical antibiotic agents are not generally indicated for preventing of surgical site infections (SSIs) in clean incisions, and the drug concentrations that should be delivered to local incision sites remain uncertain. The aim of this study was to critically assess the efficacy of topical antibiotic agents in comparison with non-antibiotic agents for preventing SSIs in clean incisions by performing a systematic review and meta-analysis. Methods: We conducted a search of literature in PubMed, Embase, and Cochrane Databases and included randomized controlled trials (RCTs) on topical antibiotic use for patients with clean post-surgical incisions. The primary outcome was the incidence of SSI, presented as the event rate. Eleven RCTs were included. Results: Using random-effects modeling, the pooled risk ratio (RR) of developing a post-surgical incisions infection was 0.83 (95% confidence interval [CI], 0.61-1.16; I2, 0%). In subgroup analyses, no reductions in SSI were observed when topical antibiotic agents were used to treat incisions due to spinal (RR, 0.75; 95% CI, 0.40-1.38; I2, 0%), orthopedic (RR, 0.69; 95% CI, 0.37-1.29; I2, 0%), dermatologic (RR, 0.77; 95% CI, 0.39-1.55; I2, 65%), or cardiothoracic surgeries (RR, 1.31; 95% CI, 0.83-2.06; I2: 0%). The incidence of SSI across different operative phases did not differ for the application of topical antibiotic agents compared with non-antibiotic agents (RR, 0.80; 95% CI, 0.56-1.14; I2, 0%). Conclusions: The results of this meta-analysis show that topical antibiotic agents provide no clinical benefit for preventing SSI in clean incisions.

Factors influencing nurses' intentions toward the use of mobile electronic medical records.

The purpose of this study was to investigate the factors influencing nurses' intentions toward the use of mobile electronic medical records, based on the Theory of Diffusion of Innovations. The cross-sectional study used a structured questionnaire for data collection, focusing on the nurses of a large hospital in southern Taiwan. A total of 720 valid questionnaires were returned yielding a response rate of 82.0%. Multiple regression analysis of the responses identified three innovative characteristics, compatibility, complexity, and observability, as significantly influencing nurses' intentions toward adopting mobile electronic medical records, whereas relative advantage and trialability did not. In addition, nursing seniority affected nurses' intentions significantly toward adopting mobile electronic medical records. Implications of effects of the factors and future research directions are discussed.

Deep Learning Approach for Negation and Speculation Detection for Automated Important Finding Flagging and Extraction in Radiology Report: Internal Validation and Technique Comparison Study.

BACKGROUND: Negation and speculation unrelated to abnormal findings can lead to false-positive alarms for automatic radiology report highlighting or flagging by laboratory information systems. OBJECTIVE: This internal validation study evaluated the performance of natural language processing methods (NegEx, NegBio, NegBERT, and transformers). METHODS: We annotated all negative and speculative statements unrelated to abnormal findings in reports. In experiment 1, we fine-tuned several transformer models (ALBERT [A Lite Bidirectional Encoder Representations from Transformers], BERT [Bidirectional Encoder Representations from Transformers], DeBERTa [Decoding-Enhanced BERT With Disentangled Attention], DistilBERT [Distilled version of BERT], ELECTRA [Efficiently Learning an Encoder That Classifies Token Replacements Accurately], ERNIE [Enhanced Representation through Knowledge Integration], RoBERTa [Robustly Optimized BERT Pretraining Approach], SpanBERT, and XLNet) and compared their performance using precision, recall, accuracy, and F1-scores. In experiment 2, we compared the best model from experiment 1 with 3 established negation and speculation-detection algorithms (NegEx, NegBio, and NegBERT). RESULTS: Our study collected 6000 radiology reports from 3 branches of the Chi Mei Hospital, covering multiple imaging modalities and body parts. A total of 15.01% (105,755/704,512) of words and 39.45% (4529/11,480) of important diagnostic keywords occurred in negative or speculative statements unrelated to abnormal findings. In experiment 1, all models achieved an accuracy of >0.98 and F1-score of >0.90 on the test data set. ALBERT exhibited the best performance (accuracy=0.991; F1-score=0.958). In experiment 2, ALBERT outperformed the optimized NegEx, NegBio, and NegBERT methods in terms of overall performance (accuracy=0.996; F1-score=0.991), in the prediction of whether diagnostic keywords occur in speculative statements unrelated to abnormal findings, and in the improvement of the performance of keyword extraction (accuracy=0.996; F1-score=0.997). CONCLUSIONS: The ALBERT deep learning method showed the best performance. Our results represent a significant advancement in the clinical applications of computer-aided notification systems.

The structure, function, task, and effectiveness of hospital-based child protection teams in Taiwan.

BACKGROUND: Child protection teams (CPTs) are established in many countries with an intent to safeguard children at risk for maltreatment. However, the tasks and effectiveness of CPTs in Taiwan and many countries remain unclear. OBJECTIVE: A two-step, descriptive correlational study aimed to explore the implementation status and needs concerning the structure, functions, tasks, and effectiveness of hospital-based CPTs using a self-developed evaluation tool in Taiwan. PARTICIPANTS AND SETTING: Five experts and 10 CPT members were evaluated the psychometric properties of the evaluation tool. The main study participants comprised 153 CPT members in Taiwan in 2020. METHODS: Content validity, factor analysis, test-retest reliability, and internal consistency were used to evaluate the psychometric properties of the instrument. Descriptive and correlational statistics were to describe the implementation status and needs of the structure, functions, tasks, and effectiveness of hospital-based CPTs and their relationships. RESULTS: The psychometric properties of the tool were acceptable and satisfactory. The mean scores for each dimension of CPT implementation status were 2.77-2.93 (potential range 0-4) with the lowest for collaboration (mean = 1.97) and incentive (mean = 1.93). The average need scores for each dimension ranged 7.96-8.12 (potential range 0-10), indicating high needs for each dimension, particularly in support, cohesion, and incentive. The implementation status was significantly, weakly correlated with the needs. CONCLUSIONS: There is a need to further strengthen the structure and function of the CPTs and to improve its implementation in Taiwan. It is important to improve inter-agency collaboration and to establish an incentive mechanism for hospital CPTs. Working closely with community agencies is also needed to provide a good quality of care to the maltreated child and the family.

Implementation of a patient-centered mobile shared decision making platform and healthcare workers' evaluation: a case in a medical center.

Shared decision making is a patient-centered clinical decision-making process that allows healthcare workers to share the existing empirical medical outcomes with patients before making critical decisions. This study aims to explore a project in a medical center of developing a mobile SDM in Taiwan. Chi Mei Medical Center developed the mobile SDM platform and conducted a survey of evaluation from healthcare workers. A three-tier platform that based on cloud infrastructure with seven functionalities was developed. The survey revealed that healthcare workers with sufficient SDM knowledge have an antecedent effect on the three perceptive factors of acceptance of mobile SDM. Resistance to change and perceived ease of use show significant effect on behavioral intention. We provided a comprehensive architecture of mobile SDM and observed the implementation in a medical center. The majority of healthcare workers expressed their acceptancem; however, resistance to change still present. It is, therefore, necessary to be eliminated by continuously promoting activities that highlight the advantages of the Mobile SDM platform. In clinical practice, we validated that the mobile SDM provides patients and their families with an easy way to express their concerns to healthcare workers improving significantly their relationship with each other.

Using an Artificial Intelligence Approach to Predict the Adverse Effects and Prognosis of Tuberculosis.

BACKGROUND: Tuberculosis (TB) is one of the leading causes of death worldwide and a major cause of ill health. Without treatment, the mortality rate of TB is approximately 50%; with treatment, most patients with TB can be cured. However, anti-TB drug treatments may result in many adverse effects. Therefore, it is important to detect and predict these adverse effects early. Our study aimed to build models using an artificial intelligence/machine learning approach to predict acute hepatitis, acute respiratory failure, and mortality after TB treatment. MATERIALS AND METHODS: Adult patients (age ≥ 20 years) who had a TB diagnosis and received treatment from January 2004 to December 2021 were enrolled in the present study. Thirty-six feature variables were used to develop the predictive models with AI. The data were randomly stratified into a training dataset for model building (70%) and a testing dataset for model validation (30%). These algorithms included XGBoost, random forest, MLP, light GBM, logistic regression, and SVM. RESULTS: A total of 2248 TB patients in Chi Mei Medical Center were included in the study; 71.7% were males, and the other 28.3% were females. The mean age was 67.7 ± 16.4 years. The results showed that our models using the six AI algorithms all had a high area under the receiver operating characteristic curve (AUC) in predicting acute hepatitis, respiratory failure, and mortality, and the AUCs ranged from 0.920 to 0.766, 0.884 to 0.797, and 0.834 to 0.737, respectively. CONCLUSIONS: Our AI models were good predictors and can provide clinicians with a valuable tool to detect the adverse prognosis in TB patients early.