LIVIVO - Search results -

Search results

Result 1 - 10 of total 54

Search options

Article ; Online: Endocuff With or Without Artificial Intelligence-Assisted Colonoscopy in Detection of Colorectal Adenoma: A Randomized Colonoscopy Trial.

Lui, Thomas Ka-Luen / Lam, Carla Pui-Mei / To, Elvis Wai-Pan / Ko, Michael Kwan-Lung / Tsui, Vivien Wai Man / Liu, Kevin Sze-Hang / Hui, Cynthia Ka-Yin / Cheung, Michael Ka-Shing / Mak, Loey Lung-Yi / Hui, Rex Wan-Hin / Wong, Siu-Yin / Seto, Wai Kay / Leung, Wai K

The American journal of gastroenterology

2024

Abstract: Introduction: Both artificial intelligence (AI) and distal attachment devices have been shown to improve adenoma detection rate and reduce miss rate during colonoscopy. We studied the combined effect of Endocuff and AI on enhancing detection rates of ... ...

Abstract	Introduction: Both artificial intelligence (AI) and distal attachment devices have been shown to improve adenoma detection rate and reduce miss rate during colonoscopy. We studied the combined effect of Endocuff and AI on enhancing detection rates of various colonic lesions. Methods: This was a 3-arm prospective randomized colonoscopy study involving patients aged 40 years or older. Participants were randomly assigned in a 1:1:1 ratio to undergo Endocuff with AI, AI alone, or standard high-definition (HD) colonoscopy. The primary outcome was adenoma detection rate (ADR) between the Endocuff-AI and AI groups while secondary outcomes included detection rates of polyp (PDR), sessile serrated lesion (sessile detection rate [SDR]), and advanced adenoma (advanced adenoma detection rate) between the 2 groups. Results: A total of 682 patients were included (mean age 65.4 years, 52.3% male), with 53.7% undergoing diagnostic colonoscopy. The ADR for the Endocuff-AI, AI, and HD groups was 58.7%, 53.8%, and 46.3%, respectively, while the corresponding PDR was 77.0%, 74.0%, and 61.2%. A significant increase in ADR, PDR, and SDR was observed between the Endocuff-AI and AI groups (ADR difference: 4.9%, 95% CI: 1.4%-8.2%, P = 0.03; PDR difference: 3.0%, 95% CI: 0.4%-5.8%, P = 0.04; SDR difference: 6.4%, 95% CI: 3.4%-9.7%, P < 0.01). Both Endocuff-AI and AI groups had a higher ADR, PDR, SDR, and advanced adenoma detection rate than the HD group (all P < 0.01). Discussion: Endocuff in combination with AI further improves various colonic lesion detection rates when compared with AI alone.
Language	English
Publishing date	2024-03-18
Publishing country	United States
Document type	Journal Article
ZDB-ID	390122-1
ISSN	1572-0241 ; 0002-9270
ISSN (online)	1572-0241
ISSN	0002-9270
DOI	10.14309/ajg.0000000000002684
Database	MEDical Literature Analysis and Retrieval System OnLINE

In stock of ZB MED Cologne/Königswinter

Ui V Zs.36: Show issues

Location:
Je nach Verfügbarkeit (siehe Angabe bei Bestand)
bis Jg. 2021: Bestellungen von Artikeln über das Online-Bestellformular
ab Jg. 2022: Lesesaal (EG)

Order via subito

This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

Details ▾
- See ZB MED holdings
- Order with fees

Article ; Online: Characterization of chemical components of fresh and aged aerosol from vehicle exhaust emissions in Hong Kong.

Lui, Ka Hei / Lau, Yik-Sze / Poon, Hon Yin / Organ, Bruce / Chan, Man-Nin / Guo, Hai / Ho, Steven Sai Hang / Ho, K F

Chemosphere

2023 Volume 333, Page(s) 138940

Abstract: The chemical properties of fresh and aged aerosol emitted during controlled vehicular exhaust emissions were characterized in the analysis. Pyrene (10417.1 ± 534.9 ng ... ...

Abstract	The chemical properties of fresh and aged aerosol emitted during controlled vehicular exhaust emissions were characterized in the analysis. Pyrene (10417.1 ± 534.9 ng kg
MeSH term(s)	Vehicle Emissions/analysis ; Air Pollutants/analysis ; Hong Kong ; Succinic Acid/analysis ; Particulate Matter/analysis ; Gasoline/analysis ; Aerosols/analysis ; Pyrenes/analysis
Chemical Substances	Vehicle Emissions ; Air Pollutants ; terephthalic acid (6S7NKZ40BQ) ; Succinic Acid (AB6MNQ6J6L) ; Particulate Matter ; Gasoline ; Aerosols ; Pyrenes
Language	English
Publishing date	2023-05-16
Publishing country	England
Document type	Journal Article
ZDB-ID	120089-6
ISSN	1879-1298 ; 0045-6535 ; 0366-7111
ISSN (online)	1879-1298
ISSN	0045-6535 ; 0366-7111
DOI	10.1016/j.chemosphere.2023.138940
Database	MEDical Literature Analysis and Retrieval System OnLINE

In stock of ZB MED Cologne/Königswinter

Zs.A 2540: Show issues

Location:
Je nach Verfügbarkeit (siehe Angabe bei Bestand)
bis Jg. 1994: Bestellungen von Artikeln über das Online-Bestellformular
Jg. 1995 - 2021: Lesesall (2.OG)
ab Jg. 2022: Lesesaal (EG)

Order via subito

Details ▾
- See ZB MED holdings
- Order with fees

Article ; Online: Blue-light imaging or narrow-band imaging for proximal colonic lesions: a prospective randomized tandem colonoscopy study.

Leung, Wai K / Tsui, Vivien Wai Man / Mak, Loey Lung-Yi / Cheung, Michael Ka-Shing / Hui, Cynthia Ka-Yin / Lam, Carla Pui-Mei / Wong, Siu-Yin / Liu, Kevin Sze-Hang / Ko, Michael Kwan-Lung / To, Elvis Wai-Pan / Guo, Chuan-Guo / Lui, Thomas Ka-Luen

Gastrointestinal endoscopy

2023 Volume 98, Issue 5, Page(s) 813–821.e3

Abstract: Background and aims: Blue-light imaging (BLI) is a new image-enhanced endoscopy with a wavelength filter similar to narrow-band imaging (NBI). We compared the 2 with white-light imaging (WLI) on proximal colonic lesion detection and miss rates.: ... ...

Abstract	Background and aims: Blue-light imaging (BLI) is a new image-enhanced endoscopy with a wavelength filter similar to narrow-band imaging (NBI). We compared the 2 with white-light imaging (WLI) on proximal colonic lesion detection and miss rates. Methods: In this 3-arm prospective randomized study with tandem examination of the proximal colon, we enrolled patients aged ≥40 years. Eligible patients were randomized in 1:1:1 ratio to receive BLI, NBI, or WLI during the first withdrawal from the proximal colon. The second withdrawal was performed using WLI in all patients. Primary outcomes were proximal polyp (pPDRs) and adenoma (pADRs) detection rates. Secondary outcomes were miss rates of proximal lesions found on tandem examination. Results: Of 901 patients included (mean age, 64.7 years; 52.9% men), 48.1% underwent colonoscopy for screening or surveillance. The corresponding pPDRs of the BLI, NBI, and WLI groups were 45.8%, 41.6, and 36.6%, whereas the corresponding pADRs were 36.6%, 33.8%, and 28.3%. There was a significant difference in pPDR and pADR between BLI and WLI groups (difference, 9.2% [95% confidence interval {CI}, 3.3-16.9] and 8.3% [95% CI, 2.7-15.9]) and between NBI and WLI groups (difference, 5.0% [95% CI, 1.4-12.9] and 5.6% [95% CI, 2.1-13.3]). Proximal adenoma miss rates were significantly lower with BLI (19.4%) than with WLI (27.4%; difference, -8.0%; 95% CI, -15.8 to -.1) but not between NBI (27.2%) and WLI. Conclusions: Both BLI and NBI were superior to WLI on detecting proximal colonic lesions, but only BLI had lower proximal adenoma miss rates than WLI. (Clinical trial registration number: NCT03696992.).
Language	English
Publishing date	2023-06-10
Publishing country	United States
Document type	Journal Article
ZDB-ID	391583-9
ISSN	1097-6779 ; 0016-5107
ISSN (online)	1097-6779
ISSN	0016-5107
DOI	10.1016/j.gie.2023.06.004
Database	MEDical Literature Analysis and Retrieval System OnLINE

In stock of ZB MED Cologne/Königswinter

Zs.B 283: Show issues			Location: Je nach Verfügbarkeit (siehe Angabe bei Bestand) bis Jg. 2021: Bestellungen von Artikeln über das Online-Bestellformular ab Jg. 2022: Lesesaal (EG)
Zs.MO 519: Show issues

Order via subito

Details ▾
- See ZB MED holdings
- Order with fees

Article: Developing an Interpretable Machine Learning Model to Predict in-Hospital Mortality in Sepsis Patients: A Retrospective Temporal Validation Study.

Li, Shuhe / Dou, Ruoxu / Song, Xiaodong / Lui, Ka Yin / Xu, Jinghong / Guo, Zilu / Hu, Xiaoguang / Guan, Xiangdong / Cai, Changjie

Journal of clinical medicine

2023 Volume 12, Issue 3

Abstract: Background: Risk stratification plays an essential role in the decision making for sepsis management, as existing approaches can hardly satisfy the need to assess this heterogeneous population. We aimed to develop and validate a machine learning model ... ...

Abstract	Background: Risk stratification plays an essential role in the decision making for sepsis management, as existing approaches can hardly satisfy the need to assess this heterogeneous population. We aimed to develop and validate a machine learning model to predict in-hospital mortality in critically ill patients with sepsis. Methods: Adult patients fulfilling the definition of Sepsis-3 were included at a large tertiary medical center. Relevant clinical features were extracted within the first 24 h in ICU, re-classified into different genres, and utilized for model development under three strategies: "Basic + Lab", "Basic + Intervention", and "Whole" feature sets. Extreme gradient boosting (XGBoost) was compared with logistic regression (LR) and established severity scores. Temporal validation was conducted using admissions from 2017 to 2019. Results: The final cohort included 24,272 patients, of which 4013 patients formed the test cohort for temporal validation. The trained and fine-tuned XGBoost model with the whole feature set showed the best discriminatory ability in the test cohort with AUROC as 0.85, significantly higher than the XGBoost "Basic + Lab" model (0.83), the LR "Whole" model (0.82), SOFA (0.63), SAPS-II (0.73), and LODS score (0.74). The performance in varying subgroups remained robust, and predictors, such as increased urine output and supplemental oxygen therapy, were crucially correlated with improved survival when interpretability was explored. Conclusions: We developed and validated a novel XGBoost-based model and demonstrated significantly improved performance to LR and other scores in predicting the mortality risks of sepsis patients in the hospital using features in the first 24 h.
Language	English
Publishing date	2023-01-24
Publishing country	Switzerland
Document type	Journal Article
ZDB-ID	2662592-1
ISSN	2077-0383
ISSN	2077-0383
DOI	10.3390/jcm12030915
Database	MEDical Literature Analysis and Retrieval System OnLINE

Order via subito

Article ; Online: Structured postoperative handover protocol improves efficiency and quality of interdisciplinary communication and nursing care in surgical intensive care unit: a randomized controlled trial.

Qian, Xiayan / Lui, Ka Yin / Li, Shuhe / Song, Xiaodong / Xu, Jinghong / Dou, Ruoxu / Luo, Gen / Li, Liqiong / Cai, Changjie

Updates in surgery

2023 Volume 76, Issue 1, Page(s) 289–298

Abstract: This study aimed to evaluate the effectiveness of a structured postoperative handover protocol for postoperative transfer to the SICU. This study was a randomized controlled trial conducted in a comprehensive teaching hospital in China. Patients who were ...

Abstract	This study aimed to evaluate the effectiveness of a structured postoperative handover protocol for postoperative transfer to the SICU. This study was a randomized controlled trial conducted in a comprehensive teaching hospital in China. Patients who were transferred to the SICU after surgery were randomly divided into two groups. The intervention group underwent postoperative structured handover protocol, and the control group still applied conventional oral handover. A total of 101 postoperative patients and 50 clinicians were enrolled. Although the intervention group did not shorten the handover duration (6.18 ± 1.66 vs 5.94 ± 1.91; P = 0.505), the handover integrity was significantly improved, mainly reflected in fewer information omissions (1.44 ± 0.97 vs 0.67 ± 0.62; P < 0.001), fewer additional questions raised by ICU physicians (1.06 ± 1.04 vs 0.24 ± 0.43; P < 0.001) and fewer additional handovers via phone call (16% vs 3.9%; P = 0.042). The total score of satisfaction of the intervention group was significantly higher than that of the control group (76.44 ± 7.32 vs 81.24 ± 6.95; P = 0.001). With respect to critical care, the incidence of stage I pressure sore within 24 h was lower in the intervention group than in the control group (20% vs 3.9%, P = 0.029). Structured postoperative handover protocol improves the efficiency and quality of interdisciplinary communication and clinical care in SICU.Trial registration This study was registered in China on January 8th, 2022 at Chinese Clinical Trial Registry (ChiCTR2200055400).
MeSH term(s)	Humans ; Patient Handoff ; Interdisciplinary Communication ; Prospective Studies ; Intensive Care Units ; Hospitals, Teaching ; Critical Care ; Randomized Controlled Trials as Topic
Language	English
Publishing date	2023-06-05
Publishing country	Italy
Document type	Clinical Trial Protocol ; Journal Article
ZDB-ID	2572692-4
ISSN	2038-3312 ; 2038-131X
ISSN (online)	2038-3312
ISSN	2038-131X
DOI	10.1007/s13304-023-01551-2
Database	MEDical Literature Analysis and Retrieval System OnLINE

Full text online

Accessible to users with ZB MED library card

In stock of ZB MED Cologne/Königswinter

Zs.B 101: Show issues

Location:
Je nach Verfügbarkeit (siehe Angabe bei Bestand)
bis Jg. 2021: Bestellungen von Artikeln über das Online-Bestellformular
ab Jg. 2022: Lesesaal (EG)

Order via subito

Details ▾

Article ; Online: Multi-center prospective population pharmacokinetic study and the performance of web-based individual dose optimization application of intravenous vancomycin for adults in Hong Kong: A study protocol.

Hui, Ka Ho Matthew / Lui, Chung Yan Grace / Wu, Ka Lun Alan / Chen, Jason / Cheung, Yin Ting / Lam, Tai Ning Teddy

PloS one

2022 Volume 17, Issue 5, Page(s) e0267894

Abstract: A recent consensus guideline recommends migrating the therapeutic drug monitoring practice for intravenous vancomycin for the treatment of methicillin-resistant Staphylococcus aureus infection from the traditional trough-based approach to the Bayesian ... ...

Abstract	A recent consensus guideline recommends migrating the therapeutic drug monitoring practice for intravenous vancomycin for the treatment of methicillin-resistant Staphylococcus aureus infection from the traditional trough-based approach to the Bayesian approach based on area under curve to improve clinical outcomes. To support the implementation of the new strategy for hospitals under Hospital Authority, Hong Kong, this study is being proposed to (1) estimate and validate a population pharmacokinetic model of intravenous vancomycin for local adults, (2) develop a web-based individual dose optimization application for clinical use, and (3) evaluate the performance of the application by comparing the treatment outcomes and clinical satisfaction against the traditional approach. 300 adult subjects prescribed with intravenous vancomycin and not on renal replacement therapy will be recruited for population pharmacokinetic model development and validation. Sex, age, body weight, serum creatinine level, intravenous vancomycin dosing records, serum vancomycin concentrations etc. will be collected from several electronic health record systems maintained by Hospital Authority. Parameter estimation will be performed using non-linear mixed-effect modeling techniques. The web-based individual dose optimization application is based on a previously reported application and is built using R and the package shiny. Data from another 50 subjects will be collected during the last three months of the study period and treated as informed by the developed application and compared against historical control for clinical outcomes. Since the study will incur extra blood-taking procedures from patients, informed consent is required. Other than that, recruited subjects should receive medical treatments as usual. Identifiable patient data will be available only to site investigators and clinicians in each hospital. The study protocol and informed consent forms have been approved by the Joint Chinese University of Hong Kong-New Territories East Cluster Clinical Research Ethics Committee (reference number: NTEC-2021-0215) and registered at the Chinese Clinical Trial Registry (registration number: ChiCTR2100048714).
MeSH term(s)	Adult ; Anti-Bacterial Agents ; Bayes Theorem ; Hong Kong ; Humans ; Internet ; Methicillin-Resistant Staphylococcus aureus ; Multicenter Studies as Topic ; Prospective Studies ; Vancomycin
Chemical Substances	Anti-Bacterial Agents ; Vancomycin (6Q205EH1VU)
Language	English
Publishing date	2022-05-05
Publishing country	United States
Document type	Clinical Trial Protocol ; Journal Article
ZDB-ID	2267670-3
ISSN	1932-6203 ; 1932-6203
ISSN (online)	1932-6203
ISSN	1932-6203
DOI	10.1371/journal.pone.0267894
Database	MEDical Literature Analysis and Retrieval System OnLINE

Order via subito

Article ; Online: Developing an Interpretable Machine Learning Model to Predict in-Hospital Mortality in Sepsis Patients

Shuhe Li / Ruoxu Dou / Xiaodong Song / Ka Yin Lui / Jinghong Xu / Zilu Guo / Xiaoguang Hu / Xiangdong Guan / Changjie Cai

Journal of Clinical Medicine, Vol 12, Iss 915, p

A Retrospective Temporal Validation Study

2023 Volume 915

Abstract	Background: Risk stratification plays an essential role in the decision making for sepsis management, as existing approaches can hardly satisfy the need to assess this heterogeneous population. We aimed to develop and validate a machine learning model to predict in-hospital mortality in critically ill patients with sepsis. Methods: Adult patients fulfilling the definition of Sepsis-3 were included at a large tertiary medical center. Relevant clinical features were extracted within the first 24 h in ICU, re-classified into different genres, and utilized for model development under three strategies: “Basic + Lab”, “Basic + Intervention”, and “Whole” feature sets. Extreme gradient boosting (XGBoost) was compared with logistic regression (LR) and established severity scores. Temporal validation was conducted using admissions from 2017 to 2019. Results: The final cohort included 24,272 patients, of which 4013 patients formed the test cohort for temporal validation. The trained and fine-tuned XGBoost model with the whole feature set showed the best discriminatory ability in the test cohort with AUROC as 0.85, significantly higher than the XGBoost “Basic + Lab” model (0.83), the LR “Whole” model (0.82), SOFA (0.63), SAPS-II (0.73), and LODS score (0.74). The performance in varying subgroups remained robust, and predictors, such as increased urine output and supplemental oxygen therapy, were crucially correlated with improved survival when interpretability was explored. Conclusions: We developed and validated a novel XGBoost-based model and demonstrated significantly improved performance to LR and other scores in predicting the mortality risks of sepsis patients in the hospital using features in the first 24 h.
Keywords	sepsis ; mortality ; extreme gradient boosting ; temporal validation ; interpretability ; Medicine ; R
Subject code	310
Language	English
Publishing date	2023-01-01T00:00:00Z
Publisher	MDPI AG
Document type	Article ; Online
Database	BASE - Bielefeld Academic Search Engine (life sciences selection)

Full text online

Full text

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

Article ; Online: Comparison of assistance preferences of older adults with different functional dependence levels on domestic tasks performed by robots.

Lee, Linda Yin-King / Yeung, Chun-Kit / Choi, Chun-Wa / Leung, Man-Nga / Lui, Shing-Yan / Tam, Wing-Yi / Tang, Ka-Yi / Wong, Chun-San / Wong, Yuen-Shan / Yau, Cheuk-Yi / Yeung, Tik-Ling / Lee, Joseph Kok-Long / Chui, Debby Lee-Kuen

BMC geriatrics

2024 Volume 24, Issue 1, Page(s) 58

Abstract: Background: Robots have the potential to assist older adults in their home-based daily living tasks. Previous studies indicated that older adults generally accept robot assistance. However, the preferences of older adults with different functional ... ...

Abstract	Background: Robots have the potential to assist older adults in their home-based daily living tasks. Previous studies indicated that older adults generally accept robot assistance. However, the preferences of older adults with different functional dependence levels are lacking. These older adults encounter varying levels of difficulty in daily living and may have distinct preferences for robot assistance. This study aimed to describe and compare the preferences for robot assistance on domestic tasks in older adults with different functional dependence levels. Methods: This cross-sectional descriptive study recruited a convenience sample of 385 older adults in Hong Kong. They were categorized as independent, partially dependent, and dependent using the Katz Index of Independence in Activities of Daily Living. Their preferences for robot assistance on a list of 48 domestic tasks under six categories were assessed through the Assistance Preference Checklist. Differences in preferences between the three groups were compared using one-way ANOVA test. Results: Findings revealed the differences and similarities in preferences between participants with different dependence levels. In most domestic tasks under the personal care category, dependent and partially dependent older adults reported a significantly lower preferences for human assistance or a higher preferences for robot assistance (p < 0.001), compared with the independent ones. The effect size varied from medium to large (eta squared = 0.07 to 0.52). However, participants, regardless of functional dependence levels, preferred human to assist in some domestic tasks under the health and leisure activities category and preferred robot to assist in most of the domestic tasks under the chores, information management, and manipulating objects category. Conclusions: Older adults with different levels of functional dependence exhibit different preferences for robotic assistance. To effectively use robots and assist older adults as they age, the specific preferences of older adults must be considered before designing and introducing robots in domestic care.
MeSH term(s)	Humans ; Aged ; Activities of Daily Living ; Functional Status ; Robotics ; Cross-Sectional Studies ; Self Care
Language	English
Publishing date	2024-01-13
Publishing country	England
Document type	Journal Article
ZDB-ID	2059865-8
ISSN	1471-2318 ; 1471-2318
ISSN (online)	1471-2318
ISSN	1471-2318
DOI	10.1186/s12877-023-04567-w
Database	MEDical Literature Analysis and Retrieval System OnLINE

Order via subito

Article ; Online: Pharmacokinetics of Voriconazole in Peritoneal Fluid of Critically Ill Patients.

Lin, Xiao-Bin / Hu, Xiao-Guang / Tang, Zhao-Xia / Guo, Peng-Hao / Liu, Xiao-Man / Liang, Tao / Xia, Yan-Zhe / Lui, Ka Yin / Chen, Pan / Tang, Ke-Jing / Chen, Xiao / Cai, Chang-Jie

Antimicrobial agents and chemotherapy

2023 Volume 67, Issue 5, Page(s) e0172122

Abstract: Data on the distribution of voriconazole (VRC) in the human peritoneal cavity are sparse. This prospective study aimed to describe the pharmacokinetics of intravenous VRC in the peritoneal fluid of critically ill patients. A total of 19 patients were ... ...

Abstract	Data on the distribution of voriconazole (VRC) in the human peritoneal cavity are sparse. This prospective study aimed to describe the pharmacokinetics of intravenous VRC in the peritoneal fluid of critically ill patients. A total of 19 patients were included. Individual pharmacokinetic curves, drawn after single (first dose on day 1) and multiple (steady-state) doses, displayed a slower rise and lower fluctuation of VRC concentrations in peritoneal fluid than in plasma. Good but variable penetration of VRC into the peritoneal cavity was observed, and the median (range) peritoneal fluid/plasma ratios of the area under the concentration-time curve (AUC) were 0.54 (0.34 to 0.73) and 0.67 (0.63 to 0.94) for single and multiple doses, respectively. Approximately 81% (13/16) of the VRC steady-state trough concentrations (
MeSH term(s)	Humans ; Voriconazole/pharmacokinetics ; Ascitic Fluid ; Critical Illness ; Prospective Studies ; Antifungal Agents/pharmacokinetics ; Candida glabrata ; Microbial Sensitivity Tests
Chemical Substances	Voriconazole (JFU09I87TR) ; Antifungal Agents
Language	English
Publishing date	2023-04-06
Publishing country	United States
Document type	Journal Article ; Research Support, Non-U.S. Gov't
ZDB-ID	217602-6
ISSN	1098-6596 ; 0066-4804
ISSN (online)	1098-6596
ISSN	0066-4804
DOI	10.1128/aac.01721-22
Database	MEDical Literature Analysis and Retrieval System OnLINE

In stock of ZB MED Cologne/Königswinter

Zs.A 809: Show issues			Location: Je nach Verfügbarkeit (siehe Angabe bei Bestand) bis Jg. 1994: Bestellungen von Artikeln über das Online-Bestellformular Jg. 1995 - 2021: Lesesall (1.OG) ab Jg. 2022: Lesesaal (EG)
Einzelsignatur: Show issues

Order via subito

Details ▾
- See ZB MED holdings
- Order with fees

Article ; Online: An efficient approach to estimate the risk of coronary artery disease for people living with HIV using machine-learning-based retinal image analysis.

Lui, Grace / Leung, Ho Sang / Lee, Jack / Wong, Chun Kwok / Li, Xinxin / Ho, Mary / Wong, Vivian / Li, Timothy / Ho, Tracy / Chan, Yin Yan / Lee, Shui Shan / Lee, Alex Pw / Wong, Ka Tak / Zee, Benny

PloS one

2023 Volume 18, Issue 2, Page(s) e0281701

Abstract: Background: People living with HIV (PLWH) have increased risks of non-communicable diseases, especially cardiovascular diseases. Current HIV clinical management guidelines recommend regular cardiovascular risk screening, but the risk equation models are ...

Abstract	Background: People living with HIV (PLWH) have increased risks of non-communicable diseases, especially cardiovascular diseases. Current HIV clinical management guidelines recommend regular cardiovascular risk screening, but the risk equation models are not specific for PLWH. Better tools are needed to assess cardiovascular risk among PLWH accurately. Methods: We performed a prospective study to determine the performance of automatic retinal image analysis in assessing coronary artery disease (CAD) in PLWH. We enrolled PLWH with ≥1 cardiovascular risk factor. All participants had computerized tomography (CT) coronary angiogram and digital fundus photographs. The primary outcome was coronary atherosclerosis; secondary outcomes included obstructive CAD. In addition, we compared the performances of three models (traditional cardiovascular risk factors alone; retinal characteristics alone; and both traditional and retinal characteristics) by comparing the area under the curve (AUC) of receiver operating characteristic curves. Results: Among the 115 participants included in the analyses, with a mean age of 54 years, 89% were male, 95% had undetectable HIV RNA, 45% had hypertension, 40% had diabetes, 45% had dyslipidemia, and 55% had obesity, 71 (61.7%) had coronary atherosclerosis, and 23 (20.0%) had obstructive CAD. The machine-learning models, including retinal characteristics with and without traditional cardiovascular risk factors, had AUC of 0.987 and 0.979, respectively and had significantly better performance than the model including traditional cardiovascular risk factors alone (AUC 0.746) in assessing coronary artery disease atherosclerosis. The sensitivity and specificity for risk of coronary atherosclerosis in the combined model were 93.0% and 93.2%, respectively. For the assessment of obstructive CAD, models using retinal characteristics alone (AUC 0.986) or in combination with traditional risk factors (AUC 0.991) performed significantly better than traditional risk factors alone (AUC 0.777). The sensitivity and specificity for risk of obstructive CAD in the combined model were 95.7% and 97.8%, respectively. Conclusion: In this cohort of Asian PLWH at risk of cardiovascular diseases, retinal characteristics, either alone or combined with traditional risk factors, had superior performance in assessing coronary atherosclerosis and obstructive CAD. Summary: People living with HIV in an Asian cohort with risk factors for cardiovascular disease had a high prevalence of coronary artery disease (CAD). A machine-learning-based retinal image analysis could increase the accuracy in assessing the risk of coronary atherosclerosis and obstructive CAD.
MeSH term(s)	Humans ; Male ; Middle Aged ; Female ; Coronary Artery Disease/diagnosis ; Cardiovascular Diseases ; Prospective Studies ; Predictive Value of Tests ; Coronary Angiography/methods ; Risk Factors ; HIV Infections ; Machine Learning
Language	English
Publishing date	2023-02-24
Publishing country	United States
Document type	Journal Article ; Research Support, Non-U.S. Gov't
ZDB-ID	2267670-3
ISSN	1932-6203 ; 1932-6203
ISSN (online)	1932-6203
ISSN	1932-6203
DOI	10.1371/journal.pone.0281701
Database	MEDical Literature Analysis and Retrieval System OnLINE

Order via subito

To top

More links

Kategorien

In stock of ZB MED Cologne/Königswinter

Order via subito

More links

Kategorien

In stock of ZB MED Cologne/Königswinter

Order via subito

More links

Kategorien

In stock of ZB MED Cologne/Königswinter

Order via subito

More links

Kategorien

Order via subito

Full text online

More links

Kategorien

In stock of ZB MED Cologne/Königswinter

Order via subito

More links

Kategorien

Order via subito

Full text online

More links

Kategorien

Inter-library loan at ZB MED

More links

Kategorien

Order via subito

More links

Kategorien

In stock of ZB MED Cologne/Königswinter

Order via subito

More links

Kategorien

Order via subito