Publishing type：Research paper (scientific journal)  

DOI： 10.69854/aicp.2026.0002

researchmap

Publishing type：Research paper (scientific journal)  

DOI： 10.3390/cancers18040671

researchmap

Publishing type：Research paper (scientific journal)  

DOI： 10.69854/jcq.2025.0014

researchmap

Language：English   Publishing type：Research paper (scientific journal)  

Community-acquired pneumonia (CAP) is associated with high mortality rates and often results in prolonged hospital stays. The potential of machine learning to enhance prediction accuracy in this context is significant, yet clinicians often lack the programming skills required for effective data mining. This study aimed to assess the effectiveness of a low-code approach for assisting clinicians with data mining for mortality and length of stay (LOS) prediction in patients with CAP. A retrospective study was conducted using a low-code platform and the PyCaret library in Google Colab on data from patients with community-acquired pneumonia (CAP) admitted between January 2013 and December 2021 to two medical facilities. Model performance was assessed using the area under the receiver operating characteristic curve (AUC) for mortality prediction and the R2 score for LOS prediction, with benchmarks set at AUC > 0.9 and R2 > 0.5. The Shapley Additive Explanations (SHAP) method was used for interpreting individual predictions. A total of 669 CAP patients were enrolled in the analysis.Fifteen models were evaluated for mortality prediction, and nineteen models were evaluated for LOS prediction utilizing the PyCaret library. The Light Gradient Boosting Machine model yielded the highest AUC (0.963) for mortality prediction. In predicting LOS, the Extratrees Regressor model achieved the highest R2 score of 0.585. Factors such as the severity of pneumonia and the Charlson Comorbidity Index (CCI) were significant factors influencing mortality. For the LOS, the CCI score, activities of daily living, and social support were significant predictors. The low-code approach enables medical professionals with limited technical expertise to effectively employ data science in their clinical decision-making process. This approach proved to be a valuable tool in the analysis of CAP patient data.

DOI： 10.1038/s41598-024-82615-0

PubMed

researchmap

Publishing type：Research paper (scientific journal)  

DOI： 10.1002/cam4.70166

researchmap

Publishing type：Research paper (scientific journal)  

DOI： 10.1080/02770903.2023.2297375

researchmap

Language：Japanese   Publisher：(一社)日本呼吸器学会  

researchmap

Language：English   Publishing type：Research paper (scientific journal)  

BACKGROUND: Central venous catheters (CVCs) are sometimes superior to peripheral vascular access for chemotherapy. Central line-associated bloodstream infections (CLABSIs) are an important complication of CVCs in chemotherapy. METHODS: A retrospective, observational study was conducted to investigate patients with implanted venous access ports (PORTs) from July 2010 to June 2021 in a teaching hospital. General conditions of the PORTs, backgrounds, and characteristics of patients were compared between CLABSI cases and uninfected cases to identify predictors of CLABSI. RESULTS: A total of 566 patients with PORTs who underwent chemotherapy were enrolled in this study, with CLABSI identified in 41 patients, for a total of 436,597 catheter-days. The median duration of PORT use was 26 vs. 494 days (P<0.001) in the CLABSI and uninfected groups, respectively. There were no significant differences in tumor classification, staging, white blood cell (WBC) count, neutrophil proportion, lymphocyte proportion, albumin, C-reactive protein (CRP), and performance status between the CLABSI and uninfected groups. Multivariable analysis showed that antibiotic usage within the previous week, total protein (TP), and immediate PORT use were independently associated with CLABSI, and their odds ratios (ORs) were 4.89 [95% confidence interval (CI): 1.67, 14.35], 1.95 (95% CI: 1.14, 3.53), and 3.13 (95% CI: 1.18, 8.30), respectively. The area under the curve (AUC) of the receiver-operating characteristic curve for TP was 0.63, and the cutoff value was 5.9 g/dL. CONCLUSIONS: PORT implantation should be avoided in patients who had antibiotic treatment episodes within 1 week, especially for those with low serum TP levels.

DOI： 10.21037/tcr-23-1217

PubMed

researchmap

Publishing type：Research paper (scientific journal)  

DOI： 10.3390/cancers15225346

researchmap

Publishing type：Research paper (scientific journal)  

DOI： 10.3390/diseases11040152

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：Elsevier {BV}  

DOI： 10.1016/j.cllc.2023.09.009

researchmap

Authorship：Lead author,　Corresponding author   Language：English  

DOI： 10.21037/tlcr-23-271

PubMed

researchmap

Authorship：Lead author   Publishing type：Research paper (scientific journal)  

<h4>Importance</h4>COVID-19 has adversely affected global healthcare infrastructure since 2019. Currently, there are no large-scale published reports on the efficacy of combination therapy of dexamethasone, remdesivir, and tocilizumab on COVID-19 patients.<h4>Objectives</h4>Is the combination therapy of dexamethasone, remdesivir, and tocilizumab superior to other treatments on hospitalized COVID-19 patients?<h4>Design</h4>This is a retrospective, comparative effectiveness study.<h4>Setting</h4>Single-center study PARTICIPANTS/INTERVENTIONS: We analyzed different inpatient COVID-19 treatment options available in the United States and their impact on hospital length of stay (LOS) and mortality. Hospitalized COVID-19 were categorized as "mild," "moderate" and "severe'' based on the highest level of oxygen required; room air, nasal cannula, or high flow/PAP/intubation, respectively. Patients were treated in accordance with the availability of medications and the latest treatment guidelines.<h4>Main outcomes</h4>The endpoints of the study are hospital discharges and death during hospitalization.<h4>Results</h4>1233 COVID-19 patients were admitted from 2020 to 2021. No treatment combinations showed a statistically significant decrease in hospital LOS in mild COVID-19 patients (p = 0.186). In moderate patients, the combination of remdesivir and dexamethasone slightly decreased LOS by 1 day (p = 0.007). In severe patients, the three-drug combination of remdesivir, dexamethasone, and tocilizumab decreased LOS by 8 days (p = 0.0034) when compared to nonviable treatments, such as hydroxychloroquine and convalescent plasma transfusion. However, it did not show any statistically significant benefit when compared to two-drug regimens (dexamethasone plus remdesivir) in severe COVID-19 (p = 0.116). No treatment arm appeared to show a statistically significant decrease in mortality for severe COVID-19 patients.<h4>Conclusions</h4>Our findings suggest that three-drug combination may decrease LOS in severe COVID-19 patients when compared to two-drug therapy. However, the trend was not supported by statistical analysis. Remdesivir may not be clinically beneficial for mild hospitalized COVID-19 patients; considering its cost, one could reserve it for moderate and severe patients. Triple drug therapies, while potentially reducing LOS for severe patients, do not affect overall mortality. Additional patient data may increase statistical power and solidify these findings.

DOI： 10.1186/s40001-023-01201-8

PubMed

researchmap

Authorship：Lead author   Language：English   Publishing type：Research paper (scientific journal)   Publisher：Elsevier {BV}  

DOI： 10.1016/j.jinf.2023.02.015

researchmap

Authorship：Lead author   Publishing type：Research paper (scientific journal)  

<h4>Objectives</h4>This study was designed to evaluate the effect of rehabilitation in preventing decreased functional status (FS) after community-acquired pneumonia (CAP) in elderly patients.<h4>Design</h4>This was a retrospective observational study.<h4>Setting</h4>Multicentre study was conducted in two medical facilities from January 2016 to December 2018.<h4>Participants</h4>Hospitalised patients with CAP aged over 64 years were enrolled. FS was assessed by the Barthel Index (BI) (range, 0-100, in 5-point increments) at admission and before discharge and graded into three categories: independent, BI 80-100; semidependent, BI 30-75; and dependent, BI 0-25. Multivariable analysis of factors contributing to decreased FS was conducted with two groups: with a decrease of at least one category (decreased group) or without a decrease of category (maintained group).<h4>Primary and secondary outcome measures</h4>The primary outcome was the effect of rehabilitation in preventing decreased FS. The secondary outcomes were factors associated with decreased FS.<h4>Results</h4>The maintained and decreased groups included 400 and 138 patients, respectively. A high frequency of rehabilitation therapy was observed in the decreased group (189 (47.3%) vs 104 (75.4%); p<0.001). Multivariable analysis showed that the factors affecting FS were aspiration pneumonia, Pneumonia Severity Index (PSI) category V, length of stay and age (OR 2.66, 95% CI 1.58 to 4.49; OR 1.92, 95% CI 1.29 to 3.44; OR 1.05, 95% CI 1.04 to 1.07; and OR 1.05, 95% CI 1.02 to 1.09, respectively). After adjusting for factors contributing to decreased FS, rehabilitation showed a limited effect in preventing decreased FS in 166 matched pairs by McNemar's test (p=0.327).<h4>Conclusions</h4>Aspiration and PSI played important roles in reducing FS. The effect of rehabilitation remains unclear in CAP.<h4>Trial registration number</h4>UMIN000046362.

DOI： 10.1136/bmjopen-2021-051307

PubMed

researchmap

Authorship：Lead author   Language：English   Publishing type：Research paper (scientific journal)   Publisher：Springer Science and Business Media {LLC}  

<jats:title>Abstract</jats:title><jats:sec>
<jats:title>Purpose</jats:title>
<jats:p>The diagnostic accuracy of the interferon-gamma release assay (IGRA) in immunosuppressed patients remains unclear.</jats:p>
</jats:sec><jats:sec>
<jats:title>Methods</jats:title>
<jats:p>A systematic review and meta-analysis were performed for diagnostic test accuracy of IGRA in tuberculosis (TB) infection among people living with HIV (PLWHIV). Summary estimates of sensitivity and specificity were calculated using both univariate and bivariate models.</jats:p>
</jats:sec><jats:sec>
<jats:title>Results</jats:title>
<jats:p>The meta-analysis included 45 of the 1,242 first-screened articles. The total number of PLWHIV was 6,525; 3,467 had TB disease, including 806 cases of LTBI and 2,661 cases of active TB. The overall diagnostic odds ratio (DOR) of IGRA in the diagnosis of TB disease was 10.0 (95% confidence interval (CI) 5.59, 25.07), with an area under the curve (AUC) of 0.729. The DOR was better for QFT (14.2 (95%CI 4.359, 46.463)) than T-SPOT (10.0 (95%CI 3.866 26.033)). The sensitivity and specificity of QFT and T-SPOT were 0.663 (95%CI 0.471, 0.813), 0.867 (95%CI 0.683 0.942), and 0.604 (95%CI 0.481, 0.715), 0.862 (95%CI 0.654, 0.954), respectively, in the bivariate model. The sensitivity of IGRA in the diagnosis of LTBI was 0.64 (95%CI 0.61, 0.66).</jats:p>
</jats:sec><jats:sec>
<jats:title>Conclusion</jats:title>
<jats:p>IGRA was useful in the diagnostic of TB disease in PLWHIV, and QFT showed a better tendency of DOR than T-SPOT. IGRA showed a limited effect to rule out LTBI in PLWHIV.</jats:p>
</jats:sec>

DOI： 10.1007/s15010-022-01789-9

researchmap

Authorship：Lead author   Language：English   Publishing type：Research paper (scientific journal)  

DOI： 10.1038/S41598-021-91234-Y

Web of Science

researchmap

Language：Japanese   Publisher：(NPO)日本肺癌学会  

researchmap

Authorship：Lead author   Language：English   Publishing type：Research paper (scientific journal)  

DOI： 10.1016/J.IJID.2021.01.057

Web of Science

researchmap

Authorship：Lead author   Language：English   Publishing type：Research paper (scientific journal)  

DOI： 10.2147/CIA.S296390

Web of Science

researchmap

Authorship：Lead author   Language：English   Publishing type：Research paper (scientific journal)   Publisher：Wiley  

DOI： 10.2139/ssrn.3887450

researchmap

Language：Japanese   Publisher：(一社)日本結核・非結核性抗酸菌症学会  

researchmap

Language：Japanese   Publisher：(一社)日本呼吸器学会  

researchmap

Language：Japanese   Publisher：(一社)日本呼吸器学会  

researchmap

Language：Japanese   Publisher：(一社)日本呼吸器学会  

researchmap

Language：Japanese   Publisher：(一社)日本呼吸器学会  

researchmap

Language：Japanese   Publisher：(一社)日本呼吸器学会  

researchmap

Authorship：Lead author   Language：English   Publishing type：Research paper (scientific journal)  

DOI： 10.2147/cia.s267349

Web of Science

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：Wiley  

DOI： 10.1111/1759-7714.13503

researchmap

Authorship：Lead author  

DOI： 10.21203/rs.3.rs-36714/v1

researchmap

Language：Japanese   Publisher：日本結核・非結核性抗酸菌症学会関東支部学会・日本呼吸器学会関東地方会  

researchmap

Language：Japanese   Publisher：日本結核・非結核性抗酸菌症学会関東支部学会・日本呼吸器学会関東地方会  

researchmap

Language：Japanese   Publisher：日本結核・非結核性抗酸菌症学会関東支部学会・日本呼吸器学会関東地方会  

researchmap

Language：Japanese   Publisher：(NPO)日本肺癌学会  

researchmap

Language：Japanese   Publisher：(NPO)日本肺癌学会  

researchmap

Language：Japanese   Publisher：日本結核病学会関東支部学会・日本呼吸器学会関東地方会  

researchmap

Language：Japanese   Publisher：(NPO)日本肺癌学会  

researchmap

Language：Japanese   Publisher：(NPO)日本肺癌学会  

researchmap

Language：Japanese   Publisher：(NPO)日本肺癌学会  

researchmap

Language：Japanese   Publisher：日本内科学会-関東地方会  

researchmap

Language：Japanese   Publisher：(一社)日本呼吸器学会  

researchmap

Language：Japanese   Publisher：(一社)日本呼吸器学会  

researchmap

Language：Japanese   Publisher：(一社)日本呼吸器学会  

researchmap

Language：Japanese   Publisher：(一社)日本呼吸器学会  

researchmap

Language：Japanese   Publisher：(一社)日本呼吸器学会  

researchmap

Language：Japanese   Publisher：(一社)日本呼吸器学会  

researchmap

Language：Japanese   Publisher：(一社)日本呼吸器学会  

researchmap

Language：Japanese   Publisher：(一社)日本呼吸器学会  

researchmap

Language：Japanese   Publisher：(一社)日本呼吸器学会  

researchmap

Language：Japanese   Publisher：(一社)日本呼吸器学会  

researchmap

Language：Japanese   Publisher：(NPO)日本肺癌学会  

researchmap

Language：Japanese  

CiNii Books

researchmap

Other Link： http://search.jamas.or.jp/link/ui/2020113493

Language：Japanese   Publisher：日本結核病学会関東支部学会・日本呼吸器学会関東地方会  

researchmap

Language：Japanese   Publisher：(NPO)日本呼吸器内視鏡学会  

researchmap

Language：Japanese   Publisher：(NPO)日本呼吸器外科学会  

researchmap

Type：Peer review 

researchmap

Type：Peer review 

researchmap

Type：Peer review 

researchmap