An Advanced Machine Learning Model for a Web-Based Artificial Intelligence-Based Clinical Decision Support System Application: Model Development and Validation Study.

BACKGROUND: Breast cancer is a leading global health concern, necessitating advancements in recurrence prediction and management. The development of an artificial intelligence (AI)-based clinical decision support system (AI-CDSS) using ChatGPT addresses this need with the aim of enhancing both prediction accuracy and user accessibility. OBJECTIVE: This study aims to develop and validate an advanced machine learning model for a web-based AI-CDSS application, leveraging the question-and-answer guidance capabilities of ChatGPT to enhance data preprocessing and model development, thereby improving the prediction of breast cancer recurrence. METHODS: This study focused on developing an advanced machine learning model by leveraging data from the Tri-Service General Hospital breast cancer registry of 3577 patients (2004-2016). As a tertiary medical center, it accepts referrals from four branches-3 branches in the northern region and 1 branch on an offshore island in our country-that manage chronic diseases but refer complex surgical cases, including breast cancer, to the main center, enriching our study population's diversity. Model training used patient data from 2004 to 2012, with subsequent validation using data from 2013 to 2016, ensuring comprehensive assessment and robustness of our predictive models. ChatGPT is integral to preprocessing and model development, aiding in hormone receptor categorization, age binning, and one-hot encoding. Techniques such as the synthetic minority oversampling technique address the imbalance of data sets. Various algorithms, including light gradient-boosting machine, gradient boosting, and extreme gradient boosting, were used, and their performance was evaluated using metrics such as the area under the curve, accuracy, sensitivity, and F1-score. RESULTS: The light gradient-boosting machine model demonstrated superior performance, with an area under the curve of 0.80, followed closely by the gradient boosting and extreme gradient boosting models. The web interface of the AI-CDSS tool was effectively tested in clinical decision-making scenarios, proving its use in personalized treatment planning and patient involvement. CONCLUSIONS: The AI-CDSS tool, enhanced by ChatGPT, marks a significant advancement in breast cancer recurrence prediction, offering a more individualized and accessible approach for clinicians and patients. Although promising, further validation in diverse clinical settings is recommended to confirm its efficacy and expand its use.

Oropharyngeal dysphagia impact of pneumonia risk in neurological patients receiving enteral tube feeding: Insights from a gastroenterologist.

BACKGROUND: Oropharyngeal dysphagia is prevalent among neurological patients, often necessitating enteral tube feeding with a nasogastric tube (NGT) or percutaneous endoscopic gastrostomy (PEG). These patients are at significant risk of developing aspiration pneumonia. This study aimed to assess the impact of oropharyngeal dysphagia on pneumonia risk requiring hospitalization in neurological patients on long-term enteral tube feeding. METHODS: This retrospective observational study was conducted between 2015 and 2022. It included neurological patients who underwent upper gastrointestinal endoscopy combined with a Modified Flexible Endoscopic Evaluation of Swallowing (mFEES) for suspect dysphagia, characterized by difficulty or discomfort in swallowing. Participants were either orally fed or had been on long-term enteral tube feeding via NGT or PEG. A 2-year follow-up was conducted to monitor pneumonia cases requiring hospitalization. Multivariate analyses were conducted to identify risk factors for pneumonia requiring hospitalization. KEY RESULTS: A total of 226 orally fed and 152 enteral tube-fed patients were enrolled. Multivariate analyses showed a significantly increased risk of pneumonia in patients with a history of pneumonia and those receiving enteral tube feeding. Subgroup analysis indicated a significantly lower risk of pneumonia among enteral tube-fed patients with oropharyngeal dysphagia who PEG-fed patients compared to NGT-fed patients (adjusted HR: 0.21, 95% CI: 0.10-0.44, p < 0.001). The cumulative incidence of pneumonia requiring hospitalization was significantly lower in the PEG group than in the NGT group (p < 0.001). CONCLUSION: mFEES could be a screening tool for oropharyngeal dysphagia. PEG is preferred over NGT for long-term enteral feeding, as it significantly reduces the risk of pneumonia requiring hospitalization, especially in patients with oropharyngeal dysphagia.

Diagnostic Accuracy of the LabTurbo QuadAIO Common Flu Assay for Detecting Influenza A Virus, Influenza B Virus, RSV, and SARS-CoV-2.

Background: The coronavirus disease 2019 (COVID-19) pandemic has highlighted the urgent need for rapid and accurate diagnostic tools for upper respiratory tract infections (URTIs). Nucleic acid amplification tests (NAATs) have transformed URTI diagnostics by enabling the rapid detection of multiple pathogens simultaneously, thereby improving patient management and infection control. This study aimed to evaluate the diagnostic accuracy of the LabTurbo QuadAIO Common Flu Assay compared to that of the Xpert Xpress CoV-2/Flu/RSV Plus Assay for detecting SARS-CoV-2, Influenza A, Influenza B, and respiratory syncytial virus (RSV). Methods: A retrospective diagnostic accuracy study was conducted using nasopharyngeal samples from patients. Samples were tested using the LabTurbo QuadAIO Common Flu Assay and the comparator Xpert Xpress CoV-2/Flu/RSV Plus Assay. Positive and negative percent agreements (PPA and NPA) were calculated. Results: The LabTurbo Assay demonstrated a PPA of 100% and an NPA of 100% for SARS-CoV-2, Influenza A, and Influenza B, whereas it showed a PPA of 100% and an NPA of 98.3% for RSV. Conclusions: The LabTurbo QuadAIO Assay exhibited high diagnostic accuracy for detecting multiple respiratory pathogens, including SARS-CoV-2, Influenza A, Influenza B, and RSV. Despite the slight discrepancy in the NPA for RSV, the overall performance of the LabTurbo Assay supports its integration into routine diagnostic workflows to enhance patient management and infection control.

Artificial Intelligence-Clinical Decision Support System in Infectious Disease Control: Combatting Multidrug-Resistant Klebsiella pneumoniae with Machine Learning.

Purpose: The World Health Organization has identified Klebsiella pneumoniae (KP) as a significant threat to global public health. The rising threat of carbapenem-resistant Klebsiella pneumoniae (CRKP) leads to prolonged hospital stays and higher medical costs, necessitating faster diagnostic methods. Traditional antibiotic susceptibility testing (AST) methods demand at least 4 days, requiring 3 days on average for culturing and isolating the bacteria and identifying the species using matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS), plus an extra day for interpreting AST results. This lengthy process makes traditional methods too slow for urgent clinical situations requiring rapid decision-making, potentially hindering prompt treatment decisions, especially for fast-spreading infections such as those caused by CRKP. This research leverages a cutting-edge diagnostic method that utilizes an artificial intelligence-clinical decision support system (AI-CDSS). It incorporates machine learning algorithms for the swift and precise detection of carbapenem-resistant and colistin-resistant strains. Patients and Methods: We selected 4307 KP samples out of a total of 52,827 bacterial samples due to concerns about multi-drug resistance using MALDI-TOF MS and Vitek-2 systems for AST. It involved thorough data preprocessing, feature extraction, and machine learning model training fine-tuned with GridSearchCV and 5-fold cross-validation, resulting in high predictive accuracy, as demonstrated by the receiver operating characteristic and area under the curve (AUC) scores, laying the groundwork for our AI-CDSS. Results: MALDI-TOF MS analysis revealed distinct intensity profiles differentiating CRKP and susceptible strains, as well as colistin-resistant Klebsiella pneumoniae (CoRKP) and susceptible strains. The Random Forest Classifier demonstrated superior discriminatory power, with an AUC of 0.96 for detecting CRKP and 0.98 for detecting CoRKP. Conclusion: Integrating MALDI-TOF MS with machine learning in an AI-CDSS has greatly expedited the detection of KP resistance by approximately 1 day. This system offers timely guidance, potentially enhancing clinical decision-making and improving treatment outcomes for KP infections.

Artificial intelligence-clinical decision support system for enhanced infectious disease management: Accelerating ceftazidime-avibactam resistance detection in Klebsiella pneumoniae.

BACKGROUND: Effective and rapid diagnostic strategies are required to manage antibiotic resistance in Klebsiella pneumonia (KP). This study aimed to design an artificial intelligence-clinical decision support system (AI-CDSS) using matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS) and machine learning for the rapid detection of ceftazidime-avibactam (CZA) resistance in KP to improve clinical decision-making processes. METHODS: Out of 107,721 bacterial samples, 675 specimens of KP with suspected multi-drug resistance were selected. These specimens were collected from a tertiary hospital and four secondary hospitals between 2022 and 2023 to evaluate CZA resistance. We used MALDI-TOF MS and machine learning to develop an AI-CDSS with enhanced speed of resistance detection. RESULTS: Machine learning models, especially light gradient boosting machines (LGBM), exhibited an area under the curve (AUC) of 0.95, indicating high accuracy. The predictive models formed the core of our newly developed AI-CDSS, enabling clinical decisions quicker than traditional methods using culture and antibiotic susceptibility testing by a day. CONCLUSIONS: The study confirms that MALDI-TOF MS, integrated with machine learning, can swiftly detect CZA resistance. Incorporating this insight into an AI-CDSS could transform clinical workflows, giving healthcare professionals immediate, crucial insights for shaping treatment plans. This approach promises to be a template for future anti-resistance strategies, emphasizing the vital importance of advanced diagnostics in enhancing public health outcomes.

Innovative strategies against superbugs: Developing an AI-CDSS for precise Stenotrophomonas maltophilia treatment.

OBJECTIVES: The World Health Organization named Stenotrophomonas maltophilia (SM) a critical multi-drug resistant threat, necessitating rapid diagnostic strategies. Traditional culturing methods require up to 96 h, including 72 h for bacterial growth, identification with matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS) through protein profile analysis, and 24 h for antibiotic susceptibility testing. In this study, we aimed at developing an artificial intelligence-clinical decision support system (AI-CDSS) by integrating MALDI-TOF MS and machine learning to quickly identify levofloxacin and trimethoprim/sulfamethoxazole resistance in SM, optimizing treatment decisions. METHODS: We selected 8,662 SM from 165,299 MALDI-TOF MS-analysed bacterial specimens, collected from a major medical centre and four secondary hospitals. We exported mass-to-charge values and intensity spectral profiles from MALDI-TOF MS .mzML files to predict antibiotic susceptibility testing results, obtained with the VITEK-2 system using machine learning algorithms. We optimized the models with GridSearchCV and 5-fold cross-validation. RESULTS: We identified distinct spectral differences between resistant and susceptible SM strains, demonstrating crucial resistance features. The machine learning models, including random forest, light-gradient boosting machine, and XGBoost, exhibited high accuracy. We established an AI-CDSS to offer healthcare professionals swift, data-driven advice on antibiotic use. CONCLUSIONS: MALDI-TOF MS and machine learning integration into an AI-CDSS significantly improved rapid SM resistance detection. This system reduced the identification time of resistant strains from 24 h to minutes after MALDI-TOF MS identification, providing timely and data-driven guidance. Combining MALDI-TOF MS with machine learning could enhance clinical decision-making and improve SM infection treatment outcomes.

Evaluation of Oropharyngeal Dysphagia in Older Patients for Risk Stratification of Pneumonia.

Objective: Nasogastric tube (NGT) and percutaneous endoscopic gastrostomy (PEG) are widely used techniques to feed older patients with oropharyngeal dysphagia. Aspiration pneumonia is the most common cause of death in these patients. This study aimed to evaluate the role of oropharyngeal dysphagia in older patients on long-term enteral feeding for risk stratification of pneumonia requiring hospitalization. Methods: We performed modified flexible endoscopic evaluation of swallowing to evaluate oropharyngeal dysphagia in older patients and conducted prospective follow-up for pneumonia requiring hospitalization. A total of 664 oral-feeding patients and 155 tube-feeding patients were enrolled. Multivariate Cox analysis was performed to identify risk factors of pneumonia requiring hospitalization. Results: Multivariate analyses showed that the risk of pneumonia requiring hospitalization significantly increased in older patients and in patients with neurological disorders, tube feeding, and oropharyngeal dysphagia. Subgroup analysis revealed that the risk of pneumonia requiring hospitalization was significantly lower in patients with PEG than in those with NGT among the patients with oropharyngeal dysphagia (adjusted hazard ratio 0.26, 95% confidence interval: 0.11-0.63, P = 0.003). Conclusions: For older patients with oropharyngeal dysphagia requiring long-term enteral tube feeding, PEG is a better choice than NGT. Further research is needed to elucidate the role of oropharyngeal dysphagia in enteral feeding in older patients.

Amongst Women Stratified to Receive Endocrine Therapy on the Basis of Their Tumor Estrogen and Progesterone Receptor Levels, Those with Higher Tumor Progesterone Receptor Levels Had a Better Outcome Than Those with Lower Levels of Tumor Progesterone Receptor.

BACKGROUND: To realize the association between stratified expression levels of ER and PgR and long-term prognosis of breast cancer patients who received adjuvant hormone therapy, this study aimed to propose better prognostic cut-off levels for estrogen receptor (ER) and progesterone receptor (PgR). METHODS: Patients who received adjuvant hormone therapy after surgical intervention were selected. The ER and PgR status and their effects on breast cancer-specific survival (BCSS) and disease-free survival (DFS) over 5 and 10 years were evaluated. Next, subgroups were generated based on ER and PgR expression percentage and Allred scores. Survival curves were constructed using the Kaplan-Meier method. RESULTS: ER and PgR expression were significantly associated with better prognosis in 5 years, whereas only PgR expression was significantly associated during the 10-year follow-up. The optimal cut-off values for better 5-year BCSS were ER > 50%; ER Allred score > 7; PgR ≥ 1%; or PgR Allred score ≥ 3; the corresponding values for DFS were ER > 40%; ER Allred score > 6; PgR > 10%; or PgR Allred score ≥ 3. In the long-term follow-up, PgR of > 50% or Allred score of > 5 carriers revealed a better prognosis of both BCSS and DFS. CONCLUSION: Patients with a PgR expression > 50% or an Allred score > 5 exhibited better 10-year BCSS and DFS.

Refractory hyponatremia in neuromyelitis optica in a pediatric patient: A case report.

RATIONALE: Neuromyelitis optica spectrum disorders (NMOSD) is a rare autoimmune disease predominantly involving optic nerves and spinal cord, and possible comorbidities including syndrome of inappropriate antidiuretic hormone secretion or urinary complication. We reported a young girl diagnosed with NMOSD presented with refractory hyponatremia, acute urine retention, and general weakness. Clinical symptoms improved gradually after receiving intravenous immunoglobulin, high-dose methylprednisolone, and plasmapheresis. NMOSD should be kept in mind in adolescence with acute urine retention, intermittent fever, and hyponatremia. PATIENT CONCERNS: A 15-year-old girl admitted to our hospital due to no urination for 2 days. DIAGNOSIS: Aquaporin-4 antibodies were detected showing positive both in serum and cerebrospinal fluid. Long transverse myelitis in cervical and thoracic spinal cord and optic neuritis was revealed in magnetic resonance imaging. INTERVENTIONS: Intravenous immunoglobulin 2 g/kg was infused totally in 4 days, and methylprednisolone pulse therapy was subsequently followed in 5 days; followed by 5 courses of plasmapheresis a week later. OUTCOMES: Her muscle power, syndrome of inappropriate antidiuretic hormone secretion condition, and urinary function were all improved after immune-modulated treatment course; NMOSD relapsed twice within the first year after diagnosis, however no relapse of NMOSD in the subsequent 1 year. LESSONS: To the best of our knowledge, this was the first childhood case of NMO accompanied by refractory hyponatremia in the reported literature. In childhood cases presenting with refractory hyponatremia and limb weakness, NMO or NMOSD should be considered possible diagnoses despite their rarity in pediatric cases.