Construction of a Diagnostic Algorithm for Diagnosis of Adult Asthma Using Machine Learning with Random Forest and XGBoost.

An evidence-based diagnostic algorithm for adult asthma is necessary for effective treatment and management. We present a diagnostic algorithm that utilizes a random forest (RF) and an optimized eXtreme Gradient Boosting (XGBoost) classifier to diagnose adult asthma as an auxiliary tool. Data were gathered from the medical records of 566 adult outpatients who visited Kindai University Hospital with complaints of nonspecific respiratory symptoms. Specialists made a thorough diagnosis of asthma based on symptoms, physical indicators, and objective testing, including airway hyperresponsiveness. We used two decision-tree classifiers to identify the diagnostic algorithms: RF and XGBoost. Bayesian optimization was used to optimize the hyperparameters of RF and XGBoost. Accuracy and area under the curve (AUC) were used as evaluation metrics. The XGBoost classifier outperformed the RF classifier with an accuracy of 81% and an AUC of 85%. A combination of symptom-physical signs and lung function tests was successfully used to construct a diagnostic algorithm on importance features for diagnosing adult asthma. These results indicate that the proposed model can be reliably used to construct diagnostic algorithms with selected features from objective tests in different settings.

Clinical characteristics for distinguishing between acute cardiogenic pulmonary edema and community-acquired pneumonia in elderly patients: a prospective observational study.

Heart failure and pneumonia are highly prevalent in elderly patients. We conducted a study to evaluate the differences in the patterns of symptoms, laboratory findings, and computed tomography (CT) results in elderly patients with acute cardiogenic pulmonary edema (ACPE) and community-acquired pneumonia (CAP). From January 1, 2015 to December 31, 2017, we studied 140 patients aged >75 years who were diagnosed with ACPE and CAP. Symptoms, laboratory findings, mean ostial pulmonary vein (PV) diameter and patterns on CT images were assessed. The primary measures of diagnostic accuracy were assessed using the positive likelihood ratio (LR+). The cutoff value of ostial PVs for differentiating patients with ACPE from CAP was evaluated using the receiver operating characteristic (ROC) analysis. Ninety-three patients with ACPE, 36 with CAP, and 11 with complicated ACPE/CAP were included. In patients with ACPE, edema (LR+ 5.4) was a moderate factor for rule-in, and a high brain natriuretic peptide level (LR+ 4.2) was weak. In patients with CAP, cough (LR+ 5.7) and leukocytosis (LR+ 5.2) were moderate factors for rule-in, while fever (LR+ 3.8) and a high C-reactive protein level (LR+ 4.8) were weak factors. The mean diameter of ostial PVs in patients with ACPE was significantly larger than that of patients with CAP (15.8±â€Š1.8 mm vs 9.6±1.5 mm, p< 0.01). ROC analysis revealed that an ostial PV diameter cutoff of 12.5 mm was strong evidence for distinguishing ACPE from CAP with an area under the ROC curve of 0.99 and LR+ 36.0. In conclusion, as ACPE and CAP have similar symptoms and laboratory findings, dilated ostial PVs were useful in characterizing CT images to distinguish ACPE from CAP.

Granulocyte-colony-stimulating Factor-resistant Neutropenia and Polyneuropathy Presenting as Severe Complications of Sjögren's Syndrome.

Primary Sjögren's syndrome (pSS) has multi-dimensional manifestations, including neutropenia and polyneuropathy. We herein report a 76-year-old woman with pSS initially presenting as severe granulocyte-colony-stimulating factor (G-CSF)-refractory neutropenia and axonal sensorimotor polyneuropathies (SMP). Systemic glucocorticoid administration had reduced neutrophil-associated immunoglobulin G (NAIgG) on the neutrophil surface as detected using flow cytometry, resulting in the development of neutropenia. A patient with pSS concomitant with axonal SMP might show severe neutropenia as aggressive autoimmune disease. Neutropenia can be treated with systemic glucocorticoids based on the assessment of NAIgG on the neutrophil surface.

Predictive Model for Adverse Events and Immune Response Based on the Production of Antibodies After the Second-Dose of the BNT162b2 mRNA Vaccine.

BACKGROUND: The BNT162b mRNA vaccine for coronavirus disease 2019, which is caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), mimics the immune response to natural infection. Few studies have predicted the adverse effects (AEs) after the second-dose vaccination. We present a predictive model for AEs and immune response after the second-dose of the BNT162b mRNA vaccine. METHODS: To predict AEs, 282 healthcare workers (HCWs) were enrolled in this prospective observational study. The classification and regression tree (CART) model was established, and its predictive efficacy was assessed. To predict immune response, 282 HCWs were included in the analysis. Moreover, the factors affected by anti-SARS-CoV-2 spike protein RBD antibody (s-IgG) were evaluated using serum samples collected 2 months after the second-dose vaccination. The s-IgG level was assessed using Lumipulse G1200. Multiple regression analyses were conducted to evaluate variables associated with anti-s-IgG titer levels. RESULTS: The most common AEs after the second-dose vaccination were pain (87.6%), redness (17.0%) at the injection site, fatigue (68.8%), headache (53.5%), and fever (37.5%). Based on the CART model, headache after the first-dose vaccination and age < 30 years were identified as the first and second discriminators for predicting the headache after the second-dose vaccination, respectively. In the multiple linear regression model, anti-s-IgG titer levels were associated with age, female sex, and AEs including headache and induration at the injection site after the second-dose vaccination. CONCLUSION: Headache after the first-dose vaccination can be a predictor of headache after the second-dose vaccination, and AEs are indicators of immune response.

Physical Characteristics of Injection Site Pain After COVID-19 mRNA BNT162b2 Vaccination.

BACKGROUND: BNT162b2, an mRNA COVID-19 vaccine, was launched in many countries as an intramuscular vaccination for COVID-19 infection. Few studies have assessed the physical indications of pain at the immunization site. This study aimed to characterize pain at the injection site and investigate morphological attributes using ultrasound. METHODS: Forty-three of 211 healthcare workers who received a second dose of BNT162b2 between February 2021 and March 2021 were enrolled in the study. The mean age of the subjects was 40 years. We evaluated patients' pain at the injection site using the Numerical Rating Pain Scale (NRPS). We also assessed the thickness of the deltoid muscle fascia at the injection site by ultrasound. Bayesian robust correlation was employed to explore the relationship between the pain intensity scores and ultrasound measurements. RESULTS: All eligible subjects complained of pain at the injection site. A median pain onset of 8 hours post-vaccination and a median peak intensity score of 4 were reported. Onset of relief occurred after 2 days. Ultrasound images demonstrated a 2.5-fold increase in fascia thickness at the injection site without intramuscular echogenicity change in all subjects. A correlation was established between the NRPS score and the non-injection-to-injection-side ratio of fascia thickness at the injection site (rho = 0.66). CONCLUSION: A sore arm was the most prevalent side effect of BNT162b2 vaccination and could be attributed to temporal fasciitis.

Early Intervention of Pulmonary Rehabilitation for Fibrotic Interstitial Lung Disease Is a Favorable Factor for Short-Term Improvement in Health-Related Quality of Life.

Patients with fibrosing interstitial lung disease (FILD) have poor health-related quality of life (HRQOL). We analyzed predictors of short-term improvement of HRQOL after starting pulmonary rehabilitation (PR) in moderate to severe FILD patients. This study involved 28 consecutive patients with FILD (20 males, median age of 77.5 years), who participated in PR program of our hospital for >6 weeks. The St. George's Respiratory Questionnaire (SGRQ) score and the 6-min walk distance (6MWD) were evaluated before and after PR, and the predictors of efficacy of PR were analyzed. The duration from diagnosis of FILD to start of PR showed a positive correlation with the increase in the SGRQ score, and the baseline SGRQ score showed a negative correlation with increase in the 6MWD. The FILD subtype, modified Medical Research Council score, and treatment history were not associated with the endpoints. According to the receiver operating characteristic curve (ROC) analyses, starting PR within 514 days after diagnosis of FILD was a significant favorable predictor of improvement in the SGRQ total score more than a minimal clinically important difference of 4. In this study, early intervention of PR and lower SGRQ score were associated with the favorable response to PR. PR for FILD should be initiated early before the disease becomes severe.

Characteristic appearance of the oropharynx in patients with postnasal drip (PND)-induced cough.

INTRODUCTION: Post-nasal drip (PND)-induced cough is a common cause of chronic cough. However, there is little known about the characteristic physical findings of this condition. OBJECTIVES: We investigated views of the pharyngeal wall in patients with PND-induced cough using a handy endoscopic images. METHODS: The subjects were 135 consecutive patients referred to our hospital with a sensation of something "dripping down the throat" as one of their symptoms. Physical findings for the oropharynx were examined using Wi-Fi endoscope camera. The difference in probability of symptoms in patients with acute cough and those with subacute/chronic cough was assessed using a Bayesian Fisher exact test on a 2 × 2 table. RESULTS: Among the patients, 105 (78%) complained of cough, 78 (58%) of acute cough, 20 (15%) of subacute cough, and 7 (5%) of chronic cough; and 71 (53%) had coexisting asthma. Using Bayesian inference, a sore or scratchy throat and fever were more common in patients with acute cough than in those with subacute/chronic cough. In endoscopic images of the oropharynx, a reddish curtain sign on the posterior pharyngeal wall behind the palatopharyngeal arch was found in 121 patients (90%). CONCLUSION: Patients with acute PND-induced cough have a component of acute upper respiratory infection, because of high probability of a sore or scratchy throat and fever as symptom. A reddish curtain sign may be a useful finding for identifying PND-induced cough in these cases.

Adult-onset Still's disease with concurrent thrombotic thrombocytopenic purpura: case report and literature review.

Thrombotic thrombocytopenic purpura (TTP) is rare complication resulting from adult-onset Still's disease (AOSD). We report the case of a 69-year-old Japanese man who initially presented with fever and joint pain and was diagnosed as having concurrent AOSD with TTP 1 month later. He had extremely high ferritin levels (32 696 ng/mL). He initially responded to plasma exchange but subsequently died of septic shock. AOSD accompanied by extremely high ferritin levels might be considered a sign of concurrent TTP.

Deep learning facilitates the diagnosis of adult asthma.

BACKGROUND: We explored whether the use of deep learning to model combinations of symptom-physical signs and objective tests, such as lung function tests and the bronchial challenge test, would improve model performance in predicting the initial diagnosis of adult asthma when compared to the conventional machine learning diagnostic method. METHODS: The data were obtained from the clinical records on prospective study of 566 adult out-patients who visited Kindai University Hospital for the first time with complaints of non-specific respiratory symptoms. Asthma was comprehensively diagnosed by specialists based on symptom-physical signs and objective tests. Model performance metrics were compared to logistic analysis, support vector machine (SVM) learning, and the deep neural network (DNN) model. RESULTS: For the diagnosis of adult asthma based on symptom-physical signs alone, the accuracy of the DNN model was 0.68, whereas that for the SVM was 0.60 and for the logistic analysis was 0.65. When adult asthma was diagnosed based on symptom-physical signs, biochemical findings, lung function tests, and the bronchial challenge test, the accuracy of the DNN model increased to 0.98 and was significantly higher than the 0.82 accuracy of the SVM and the 0.94 accuracy of the logistic analysis. CONCLUSIONS: DNN is able to better facilitate diagnosing adult asthma, compared with classical machine learnings, such as logistic analysis and SVM. The deep learning models based on symptom-physical signs and objective tests appear to improve the performance for diagnosing adult asthma.

Single pembrolizumab treatment causing profound durable response in a patient with pulmonary pleomorphic carcinoma.

We report a case of a 73-year-old man diagnosed with pulmonary pleomorphic carcinoma who showed profound durable response after a single treatment with pembrolizumab. The patient underwent a diagnostic workup in our hospital due to a hoarseness of voice. Chest computed tomography revealed a massive pulmonary tumor in the left upper lobe and multiple nodules in the both lung fields. Histological examination of a transbronchial lung biopsy specimen revealed pulmonary pleomorphic carcinoma. First-line treatment with pembrolizumab was discontinued after a single administration due to treatment-related pneumonitis. However, durable response has been observed over 17 months to date.

Successful Treatment of Lung Adenocarcinoma with Epidermal Growth Factor Receptor Compound Mutations Involving Exon 19 Deletion and Exon 20 Insertion by Afatinib.

A 70-year-old woman was referred to our hospital after a nodular shadow was noted on chest X-ray. Chest computed tomography showed a pulmonary mass in the right upper lobe, and brain magnetic resonance imaging revealed a right-sided frontal lobe tumor. A histological examination of a transbronchial lung biopsy specimen revealed adenocarcinoma with epidermal growth factor receptor mutations involving both exon 19 deletion and exon 20 insertion. After stereotactic radiotherapy for brain metastasis, the patient was treated with afatinib, which resulted in a complete response. We observed a case in which a patient had non-small cell lung cancer with compound EGFR mutations involving both exon 19 deletion and exon 20 insertion mutations that responded well to afatinib therapy.

Disseminated Mycobacterium scrofulaceum Infection in an Immunocompetent Host.

A 56-year-old woman, without any immunocompromising diseases, was referred to our hospital because of a recurrence of pyogenic spondylitis. Computed tomography revealed multiple osteolytic changes in the whole body. Vertebral magnetic resonance imaging revealed osteomyelitis and spondylitis. Mycobacterium scrofulaceum was detected in sputum cultures, in abscesses from the right knee, and in a subcutaneous forehead abscess. Therefore, the patient was diagnosed with disseminated Mycobacterium scrofulaceum infection. The patient was treated with rifampicin, ethambutol, and clarithromycin, which resulted in symptomatic relief and radiological improvement. We herein report a rare case of disseminated Mycobacterium scrofulaceum infection in an immunocompetent host.