LIVIVO - The Search Portal for Life Sciences

zur deutschen Oberfläche wechseln
Advanced search

Search results

Result 1 - 10 of total 76

Search options

  1. Article ; Online: Magnitude and patterns of severe Plasmodium vivax monoinfection in Vietnam

    Minh Cuong Duong / Oanh Kieu Nguyet Pham / Thanh Truc Thai / Rogan Lee / Thanh Phong Nguyen / Van Vinh Chau Nguyen / Hoan Phu Nguyen

    Frontiers in Medicine, Vol

    a 4-year single-center retrospective study

    2023  Volume 10

    Abstract: IntroductionInfection with Plasmodium vivax is a recognized cause of severe malaria including deaths. The exact burden and patterns of severe P. vivax monoinfections is however still not well quantified, especially in P. vivax endemic regions. We ... ...

    Abstract IntroductionInfection with Plasmodium vivax is a recognized cause of severe malaria including deaths. The exact burden and patterns of severe P. vivax monoinfections is however still not well quantified, especially in P. vivax endemic regions. We examined the magnitude and patterns of severe malaria caused by monoinfections of P. vivax and associated predictors among patients admitted to a tertiary care center for malaria in Vietnam.MethodsA retrospective cohort study was conducted based on the patients’ medical records at the Hospital for Tropical Diseases from January 2015 to December 2018. Extracted information included demographic, epidemiologic, clinical, laboratory and treatment characteristics.ResultsMonoinfections with P. vivax were found in 153 (34.5, 95% CI 30.3–39.1%) patients of whom, uncomplicated and severe malaria were documented in 89.5% (137/153, 95% CI 83.7–93.5%) and 10.5% (16/153, 95% CI 6.5–16.3%), respectively. Patterns of severe malaria included jaundice (8 cases), hypoglycemia (3 cases), shock (2 cases), anemia (2 cases), and cerebral malaria (1 case). Among 153 patients, 73 (47.7%) had classic malaria paroxysm, 57 (37.3%) had >7 days of illness at the time of admission, and 40 (26.1%) were referred from other hospitals. A misdiagnosis as having other diseases from malaria cases coming from other hospitals was up to 32.5% (13/40). Being admitted to hospital after day 7th of illness (AOR = 6.33, 95% CI 1.14–35.30, p = 0.035) was a predictor of severe malaria. Severe malaria was statistically associated with longer hospital length of stay (p = 0.035). Early and late treatment failures and recrudescence were not recorded. All patients recovered completely.DiscussionThis study confirms the emergence of severe vivax malaria in Vietnam which is associated with delayed hospital admission and increased hospital length of stay. Clinical manifestations of P. vivax infection can be misdiagnosed which results in delayed treatment. To meet the goal of malaria elimination by 2030, it is crucial that ...
    Keywords Plasmodium vivax ; monoinfection ; severe malaria ; delayed hospital admission ; hospital length of stay ; Vietnam ; Medicine (General) ; R5-920
    Subject code 616
    Language English
    Publishing date 2023-05-01T00:00:00Z
    Publisher Frontiers Media S.A.
    Document type Article ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    More links

    Kategorien

  2. Article ; Online: Predictors of treatment failures of plasmodium falciparum malaria in Vietnam

    Minh Cuong Duong / Oanh Kieu Nguyet Pham / Phong Thanh Nguyen / Van Vinh Chau Nguyen / Phu Hoan Nguyen

    Malaria Journal, Vol 20, Iss 1, Pp 1-

    a 4-year single‐centre retrospective study

    2021  Volume 13

    Abstract: Abstract Background Drug-resistant falciparum malaria is an increasing public health burden. This study examined the magnitude of Plasmodium falciparum infection and the patterns and predictors of treatment failure in Vietnam. Methods Medical records of ... ...

    Abstract Abstract Background Drug-resistant falciparum malaria is an increasing public health burden. This study examined the magnitude of Plasmodium falciparum infection and the patterns and predictors of treatment failure in Vietnam. Methods Medical records of all 443 patients with malaria infection admitted to the Hospital for Tropical Diseases between January 2015 and December 2018 were used to extract information on demographics, risk factors, symptoms, laboratory tests, treatment, and outcome. Results More than half (59.8%, 265/443, CI 55.1–64.4%) of patients acquired Plasmodium falciparum infection of whom 21.9% (58/265, CI 17.1–27.4%) had severe malaria, while 7.2% (19/265, CI 4.6–10.9%) and 19.2% (51/265, CI 14.7–24.5%) developed early treatment failure (ETF) and late treatment failure (LTF) respectively. Among 58 patients with severe malaria, 14 (24.1%) acquired infection in regions where artemisinin resistance has been documented including Binh Phuoc (11 patients), Dak Nong (2 patients) and Gia Lai (1 patient). Under treatment with intravenous artesunate, the median (IQR) parasite half-life of 11 patients coming from Binh Phuoc was 3 h (2.3 to 8.3 h), two patients coming from Dak Nong was 2.8 and 5.7 h, and a patient coming from Gia Lai was 6.5 h. Most patients (98.5%, 261/265) recovered completely. Four patients with severe malaria died. Severe malaria was statistically associated with receiving treatment at previous hospitals (P < 0.001), hepatomegaly (P < 0.001) and number of inpatient days (P < 0.001). Having severe malaria was a predictor of ETF (AOR 6.96, CI 2.55–19.02, P < 0.001). No predictor of LTF was identified. Conclusions Plasmodium falciparum remains the prevalent malaria parasite. Despite low mortality rate, severe malaria is not rare and is a significant predictor of ETF. To reduce the risk for ETF, studies are needed to examine the effectiveness of combination therapy including parenteral artesunate and a parenteral partner drug for severe malaria. The study alerts the possibility ...
    Keywords Plasmodium falciparum ; Severe malaria ; Early treatment failure ; Late treatment failure ; Vietnam ; Arctic medicine. Tropical medicine ; RC955-962 ; Infectious and parasitic diseases ; RC109-216
    Subject code 616
    Language English
    Publishing date 2021-04-01T00:00:00Z
    Publisher BMC
    Document type Article ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    More links

    Kategorien

  3. Article ; Online: The compensatory reserve index predicts recurrent shock in patients with severe dengue.

    Trieu, Huynh Trung / Khanh, Lam Phung / Ming, Damien Keng Yen / Quang, Chanh Ho / Phan, Tu Qui / Van, Vinh Chau Nguyen / Deniz, Ertan / Mulligan, Jane / Wills, Bridget Ann / Moulton, Steven / Yacoub, Sophie

    BMC medicine

    2022  Volume 20, Issue 1, Page(s) 109

    Abstract: Background: Dengue shock syndrome (DSS) is one of the major clinical phenotypes of severe dengue. It is defined by significant plasma leak, leading to intravascular volume depletion and eventually cardiovascular collapse. The compensatory reserve Index ( ...

    Abstract Background: Dengue shock syndrome (DSS) is one of the major clinical phenotypes of severe dengue. It is defined by significant plasma leak, leading to intravascular volume depletion and eventually cardiovascular collapse. The compensatory reserve Index (CRI) is a new physiological parameter, derived from feature analysis of the pulse arterial waveform that tracks real-time changes in central volume. We investigated the utility of CRI to predict recurrent shock in severe dengue patients admitted to the ICU.
    Methods: We performed a prospective observational study in the pediatric and adult intensive care units at the Hospital for Tropical Diseases, Ho Chi Minh City, Vietnam. Patients were monitored with hourly clinical parameters and vital signs, in addition to continuous recording of the arterial waveform using pulse oximetry. The waveform data was wirelessly transmitted to a laptop where it was synchronized with the patient's clinical data.
    Results: One hundred three patients with suspected severe dengue were recruited to this study. Sixty-three patients had the minimum required dataset for analysis. Median age was 11 years (IQR 8-14 years). CRI had a negative correlation with heart rate and moderate negative association with blood pressure. CRI was found to predict recurrent shock within 12 h of being measured (OR 2.24, 95% CI 1.54-3.26), P < 0.001). The median duration from CRI measurement to the first recurrent shock was 5.4 h (IQR 2.9-6.8). A CRI cutoff of 0.4 provided the best combination of sensitivity and specificity for predicting recurrent shock (0.66 [95% CI 0.47-0.85] and 0.86 [95% CI 0.80-0.92] respectively).
    Conclusion: CRI is a useful non-invasive method for monitoring intravascular volume status in patients with severe dengue.
    MeSH term(s) Blood Pressure/physiology ; Child ; Heart Rate/physiology ; Humans ; Prospective Studies ; Severe Dengue/diagnosis ; Shock/diagnosis
    Language English
    Publishing date 2022-04-07
    Publishing country England
    Document type Journal Article ; Observational Study ; Research Support, Non-U.S. Gov't
    ZDB-ID 2131669-7
    ISSN 1741-7015 ; 1741-7015
    ISSN (online) 1741-7015
    ISSN 1741-7015
    DOI 10.1186/s12916-022-02311-6
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  4. Article: Utility of SOFA score, management and outcomes of sepsis in Southeast Asia: a multinational multicenter prospective observational study.

    Lie, Khie Chen / Lau, Chuen-Yen / Van Vinh Chau, Nguyen / West, T Eoin / Limmathurotsakul, Direk

    Journal of intensive care

    2018  Volume 6, Page(s) 9

    Abstract: Background: Sepsis is a global threat but insufficiently studied in Southeast Asia. The objective was to evaluate management, outcomes, adherence to sepsis bundles, and mortality prediction of maximum Sequential Organ Failure Assessment (SOFA) scores in ...

    Abstract Background: Sepsis is a global threat but insufficiently studied in Southeast Asia. The objective was to evaluate management, outcomes, adherence to sepsis bundles, and mortality prediction of maximum Sequential Organ Failure Assessment (SOFA) scores in patients with community-acquired sepsis in Southeast Asia.
    Methods: We prospectively recruited hospitalized adults within 24 h of admission with community-acquired infection at nine public hospitals in Indonesia (
    Results: From December 2013 to December 2015, 454 adult patients presenting with community-acquired sepsis due to diverse etiologies were enrolled. Compliance with sepsis bundles within 24 h of admission was low: broad-spectrum antibiotics in 76% (344/454), ≥ 1500 mL fluid in 50% of patients with hypotension or lactate ≥ 4 mmol/L (115/231), and adrenergic agents in 71% of patients with hypotension (135/191). Three hundred and fifty-five patients (78%) were managed outside of ICUs. Ninety-nine patients (22%) died. Total SOFA score on admission of those who subsequently died was significantly higher than that of those who survived (6.7 vs. 4.6,
    Conclusions: Community-acquired sepsis in Southeast Asia due to a variety of pathogens is usually managed outside the ICU and with poor compliance to sepsis bundles. In this population, calculation of SOFA scores is feasible and SOFA scores are associated with mortality.
    Trial registration: ClinicalTrials.gov, NCT02157259. Registered 5 June 2014, retrospectively registered.
    Language English
    Publishing date 2018-02-14
    Publishing country England
    Document type Journal Article
    ZDB-ID 2739853-5
    ISSN 2052-0492
    ISSN 2052-0492
    DOI 10.1186/s40560-018-0279-7
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  5. Article ; Online: Dengue human infection models supporting drug development.

    Whitehorn, James / Van, Vinh Chau Nguyen / Simmons, Cameron P

    The Journal of infectious diseases

    2014  Volume 209 Suppl 2, Page(s) S66–70

    Abstract: Dengue is a arboviral infection that represents a major global health burden. There is an unmet need for effective dengue therapeutics to reduce symptoms, duration of illness and incidence of severe complications. Here, we consider the merits of a dengue ...

    Abstract Dengue is a arboviral infection that represents a major global health burden. There is an unmet need for effective dengue therapeutics to reduce symptoms, duration of illness and incidence of severe complications. Here, we consider the merits of a dengue human infection model (DHIM) for drug development. A DHIM could allow experimentally controlled studies of candidate therapeutics in preselected susceptible volunteers, potentially using smaller sample sizes than trials that recruited patients with dengue in an endemic country. In addition, the DHIM would assist the conduct of intensive pharmacokinetic and basic research investigations and aid in determining optimal drug dosage. Furthermore, a DHIM could help establish proof of concept that chemoprophylaxis against dengue is feasible. The key challenge in developing the DHIM for drug development is to ensure the model reliably replicates the typical clinical and laboratory features of naturally acquired, symptomatic dengue.
    MeSH term(s) Antiviral Agents/therapeutic use ; Clinical Trials as Topic ; Dengue/drug therapy ; Dengue/prevention & control ; Dengue Vaccines/therapeutic use ; Dengue Virus ; Humans ; Models, Biological ; Research Design
    Chemical Substances Antiviral Agents ; Dengue Vaccines
    Language English
    Publishing date 2014-05-28
    Publishing country United States
    Document type Journal Article ; Research Support, Non-U.S. Gov't
    ZDB-ID 3019-3
    ISSN 1537-6613 ; 0022-1899
    ISSN (online) 1537-6613
    ISSN 0022-1899
    DOI 10.1093/infdis/jiu062
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  6. Article ; Online: Direct Medical Costs of Tetanus, Dengue, and Sepsis Patients in an Intensive Care Unit in Vietnam.

    Hung, Trinh Manh / Van Hao, Nguyen / Yen, Lam Minh / McBride, Angela / Dat, Vu Quoc / van Doorn, H Rogier / Loan, Huynh Thi / Phong, Nguyen Thanh / Llewelyn, Martin J / Nadjm, Behzad / Yacoub, Sophie / Thwaites, C Louise / Ahmed, Sayem / Van Vinh Chau, Nguyen / Turner, Hugo C

    Frontiers in public health

    2022  Volume 10, Page(s) 893200

    Abstract: Background: Critically ill patients often require complex clinical care by highly trained staff within a specialized intensive care unit (ICU) with advanced equipment. There are currently limited data on the costs of critical care in low-and middle- ... ...

    Abstract Background: Critically ill patients often require complex clinical care by highly trained staff within a specialized intensive care unit (ICU) with advanced equipment. There are currently limited data on the costs of critical care in low-and middle-income countries (LMICs). This study aims to investigate the direct-medical costs of key infectious disease (tetanus, sepsis, and dengue) patients admitted to ICU in a hospital in Ho Chi Minh City (HCMC), Vietnam, and explores how the costs and cost drivers can vary between the different diseases.
    Methods: We calculated the direct medical costs for patients requiring critical care for tetanus, dengue and sepsis. Costing data (stratified into different cost categories) were extracted from the bills of patients hospitalized to the adult ICU with a dengue, sepsis and tetanus diagnosis that were enrolled in three studies conducted at the Hospital for Tropical Diseases in HCMC from January 2017 to December 2019. The costs were considered from the health sector perspective. The total sample size in this study was 342 patients.
    Results: ICU care was associated with significant direct medical costs. For patients that did not require mechanical ventilation, the median total ICU cost per patient varied between US$64.40 and US$675 for the different diseases. The costs were higher for patients that required mechanical ventilation, with the median total ICU cost per patient for the different diseases varying between US$2,590 and US$4,250. The main cost drivers varied according to disease and associated severity.
    Conclusion: This study demonstrates the notable cost of ICU care in Vietnam and in similar LMIC settings. Future studies are needed to further evaluate the costs and economic burden incurred by ICU patients. The data also highlight the importance of evaluating novel critical care interventions that could reduce the costs of ICU care.
    MeSH term(s) Adult ; Cross Infection ; Dengue/therapy ; Humans ; Intensive Care Units ; Sepsis/therapy ; Tetanus/therapy ; Vietnam
    Language English
    Publishing date 2022-06-20
    Publishing country Switzerland
    Document type Journal Article ; Research Support, Non-U.S. Gov't
    ZDB-ID 2711781-9
    ISSN 2296-2565 ; 2296-2565
    ISSN (online) 2296-2565
    ISSN 2296-2565
    DOI 10.3389/fpubh.2022.893200
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  7. Article ; Online: The seroincidence of childhood Shigella sonnei infection in Ho Chi Minh City, Vietnam.

    Jones, Nick K / Thu, Trang Nguyen Hoang / de Alwis, Ruklanthi / Thompson, Corinne / Tuyen, Ha Thanh / Nhu, Tran Do Hoang / Phat, Voong Vinh / Trung, Pham Duc / Lam, Phung Khanh / Tien, Bui Thi Thuy / Tuyet, Hoang Thi Diem / Vi, Lu Lan / Van Vinh Chau, Nguyen / Le Thi Quynh, Nhi / Baker, Stephen

    PLoS neglected tropical diseases

    2023  Volume 17, Issue 10, Page(s) e0011728

    Abstract: Background: Shigella sonnei is a pathogen of growing global importance as a cause of diarrhoeal illness in childhood, particularly in transitional low-middle income countries (LMICs). Here, we sought to determine the incidence of childhood exposure to S. ...

    Abstract Background: Shigella sonnei is a pathogen of growing global importance as a cause of diarrhoeal illness in childhood, particularly in transitional low-middle income countries (LMICs). Here, we sought to determine the incidence of childhood exposure to S. sonnei infection in a contemporary transitional LMIC population, where it represents the dominant Shigella species.
    Methods: Participants were enrolled between the age of 12-36 months between June and December 2014. Baseline characteristics were obtained through standardized electronic questionnaires, and serum samples were collected at 6-month intervals over two years of follow-up. IgG antibody against S. sonnei O-antigen (anti-O) was measured using an enzyme-linked immunosorbent assay (ELISA). A four-fold increase in ELISA units (EU) with convalescent IgG titre >10.3 EU was taken as evidence of seroconversion between timepoints.
    Results: A total of 3,498 serum samples were collected from 748 participants; 3,170 from the 634 participants that completed follow-up. Measures of anti-O IgG varied significantly by calendar month (p = 0.03). Estimated S. sonnei seroincidence was 21,451 infections per 100,000 population per year (95% CI 19,307-23,834), with peak incidence occurring at 12-18 months of age. Three baseline factors were independently associated with the likelihood of seroconversion; ever having breastfed (aOR 2.54, CI 1.22-5.26), history of prior hospital admission (aOR 0.57, CI 0.34-0.95), and use of a toilet spray-wash in the household (aOR 0.42, CI 0.20-0.89).
    Conclusions: Incidence of S. sonnei exposure in Ho Chi Minh City is substantial, with significant reduction in the likelihood of exposure as age increases beyond 2 years.
    MeSH term(s) Humans ; Infant ; Child, Preschool ; Child ; Adolescent ; Young Adult ; Adult ; Shigella sonnei ; Vietnam/epidemiology ; Shigella ; O Antigens ; Immunoglobulin G ; Dysentery, Bacillary/epidemiology
    Chemical Substances O Antigens ; Immunoglobulin G
    Language English
    Publishing date 2023-10-30
    Publishing country United States
    Document type Journal Article
    ZDB-ID 2429704-5
    ISSN 1935-2735 ; 1935-2735
    ISSN (online) 1935-2735
    ISSN 1935-2735
    DOI 10.1371/journal.pntd.0011728
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  8. Article: A combination of annual and nonannual forces drive respiratory disease in the tropics.

    Yang, Fuhan / Servadio, Joseph L / Le Thanh, Nguyen Thi / Lam, Ha Minh / Choisy, Marc / Thai, Pham Quang / Nhu Thao, Tran Thi / Thao Vy, Nguyen Ha / Phuong, Huynh Thi / Nguyen, Tran Dang / Hoai Tam, Dong Thi / Hanks, Ephraim M / Vinh, Ha / Bjornstad, Ottar N / Van Vinh Chau, Nguyen / Boni, Maciej F

    medRxiv : the preprint server for health sciences

    2023  

    Abstract: Background: It is well known that influenza and other respiratory viruses are wintertime-seasonal in temperate regions. However, respiratory disease seasonality in the tropics remains elusive. In this study, we aimed to characterize the seasonality of ... ...

    Abstract Background: It is well known that influenza and other respiratory viruses are wintertime-seasonal in temperate regions. However, respiratory disease seasonality in the tropics remains elusive. In this study, we aimed to characterize the seasonality of influenza-like illness (ILI) and influenza virus in Ho Chi Minh City (HCMC), Vietnam.
    Methods: We monitored the daily number of ILI patients in 89 outpatient clinics from January 2010 to December 2019. We collected nasal swabs and tested for influenza from a subset of clinics from May 2012 to December 2019. We used spectral analysis to describe the periodicities in the system. We evaluated the contribution of these periodicities to predicting ILI and influenza patterns through lognormal and gamma hurdle models.
    Findings: During ten years of community surveillance, 66,799 ILI reports were collected covering 2.9 million patient visits; 2604 nasal swabs were collected 559 of which were PCR-positive for influenza virus. Both annual and nonannual cycles were detected in the ILI time series, with the annual cycle showing 8.9% lower ILI activity (95% CI: 8.8%-9.0%) from February 24 to May 15. Nonannual cycles had substantial explanatory power for ILI trends (ΔAIC = 183) compared to all annual covariates (ΔAIC = 263). Near-annual signals were observed for PCR-confirmed influenza but were not consistent along in time or across influenza (sub)types.
    Interpretation: Our study reveals a unique pattern of respiratory disease dynamics in a tropical setting influenced by both annual and nonannual drivers. Timing of vaccination campaigns and hospital capacity planning may require a complex forecasting approach.
    Language English
    Publishing date 2023-03-29
    Publishing country United States
    Document type Preprint
    DOI 10.1101/2023.03.28.23287862
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  9. Article ; Online: Applying artificial intelligence and digital health technologies, Viet Nam.

    Chanh, Ho Quang / Ming, Damien K / Nguyen, Quang Huy / Duc, Tran Minh / Phuoc An, Luu / Trieu, Huynh Trung / Karolcik, Stefan / Hernandez, Bernard / Perez / Van Nuil, Jennifer / Lyle, Ngan Nguyen / Kestelyn, Evelyne / Thwaites, Louise / Georgiou, Pantelis / Paton, Chris / Holmes, Alison / Van Vinh Chau, Nguyen / Yacoub, Sophie

    Bulletin of the World Health Organization

    2023  Volume 101, Issue 7, Page(s) 487–492

    Abstract: Problem: Direct application of digital health technologies from high-income settings to low- and middle-income countries may be inappropriate due to challenges around data availability, implementation and regulation. Hence different approaches are ... ...

    Abstract Problem: Direct application of digital health technologies from high-income settings to low- and middle-income countries may be inappropriate due to challenges around data availability, implementation and regulation. Hence different approaches are needed.
    Approach: Within the Viet Nam ICU Translational Applications Laboratory project, since 2018 we have been developing a wearable device for individual patient monitoring and a clinical assessment tool to improve dengue disease management. Working closely with local staff at the Hospital for Tropical Diseases, Ho Chi Minh City, we developed and tested a prototype of the wearable device. We obtained perspectives on design and use of the sensor from patients. To develop the assessment tool, we used existing research data sets, mapped workflows and clinical priorities, interviewed stakeholders and held workshops with hospital staff.
    Local setting: In Viet Nam, a lower middle-income country, the health-care system is in the nascent stage of implementing digital health technologies.
    Relevant changes: Based on patient feedback, we are altering the design of the wearable sensor to increase comfort. We built the user interface of the assessment tool based on the core functionalities selected by workshop attendees. The interface was subsequently tested for usability in an iterative manner by the clinical staff members.
    Lessons learnt: The development and implementation of digital health technologies need an interoperable and appropriate plan for data management including collection, sharing and integration. Engagements and implementation studies should be conceptualized and conducted alongside the digital health technology development. The priorities of end-users, and understanding context and regulatory landscape are crucial for success.
    MeSH term(s) Humans ; Vietnam ; Artificial Intelligence ; Risk Factors ; Delivery of Health Care
    Language English
    Publishing date 2023-05-26
    Publishing country Switzerland
    Document type Journal Article
    ZDB-ID 80213-x
    ISSN 1564-0604 ; 0042-9686 ; 0366-4996 ; 0510-8659
    ISSN (online) 1564-0604
    ISSN 0042-9686 ; 0366-4996 ; 0510-8659
    DOI 10.2471/BLT.22.289423
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  10. Article ; Online: Clinical benefit of AI-assisted lung ultrasound in a resource-limited intensive care unit.

    Nhat, Phung Tran Huy / Van Hao, Nguyen / Tho, Phan Vinh / Kerdegari, Hamideh / Pisani, Luigi / Thu, Le Ngoc Minh / Phuong, Le Thanh / Duong, Ha Thi Hai / Thuy, Duong Bich / McBride, Angela / Xochicale, Miguel / Schultz, Marcus J / Razavi, Reza / King, Andrew P / Thwaites, Louise / Van Vinh Chau, Nguyen / Yacoub, Sophie / Gomez, Alberto

    Critical care (London, England)

    2023  Volume 27, Issue 1, Page(s) 257

    Abstract: Background: Interpreting point-of-care lung ultrasound (LUS) images from intensive care unit (ICU) patients can be challenging, especially in low- and middle- income countries (LMICs) where there is limited training available. Despite recent advances in ...

    Abstract Background: Interpreting point-of-care lung ultrasound (LUS) images from intensive care unit (ICU) patients can be challenging, especially in low- and middle- income countries (LMICs) where there is limited training available. Despite recent advances in the use of Artificial Intelligence (AI) to automate many ultrasound imaging analysis tasks, no AI-enabled LUS solutions have been proven to be clinically useful in ICUs, and specifically in LMICs. Therefore, we developed an AI solution that assists LUS practitioners and assessed its usefulness in  a low resource ICU.
    Methods: This was a three-phase prospective study. In the first phase, the performance of four different clinical user groups in interpreting LUS clips was assessed. In the second phase, the performance of 57 non-expert clinicians with and without the aid of a bespoke AI tool for LUS interpretation was assessed in retrospective offline clips. In the third phase, we conducted a prospective study in the ICU where 14 clinicians were asked to carry out LUS examinations in 7 patients with and without our AI tool and we interviewed the clinicians regarding the usability of the AI tool.
    Results: The average accuracy of beginners' LUS interpretation was 68.7% [95% CI 66.8-70.7%] compared to 72.2% [95% CI 70.0-75.6%] in intermediate, and 73.4% [95% CI 62.2-87.8%] in advanced users. Experts had an average accuracy of 95.0% [95% CI 88.2-100.0%], which was significantly better than beginners, intermediate and advanced users (p < 0.001). When supported by our AI tool for interpreting retrospectively acquired clips, the non-expert clinicians improved their performance from an average of 68.9% [95% CI 65.6-73.9%] to 82.9% [95% CI 79.1-86.7%], (p < 0.001). In prospective real-time testing, non-expert clinicians improved their baseline performance from 68.1% [95% CI 57.9-78.2%] to 93.4% [95% CI 89.0-97.8%], (p < 0.001) when using our AI tool. The time-to-interpret clips improved from a median of 12.1 s (IQR 8.5-20.6) to 5.0 s (IQR 3.5-8.8), (p < 0.001) and clinicians' median confidence level improved from 3 out of 4 to 4 out of 4 when using our AI tool.
    Conclusions: AI-assisted LUS can help non-expert clinicians in an LMIC ICU improve their performance in interpreting LUS features more accurately, more quickly and more confidently.
    MeSH term(s) Humans ; Artificial Intelligence ; Prospective Studies ; Retrospective Studies ; Intensive Care Units ; Ultrasonography
    Language English
    Publishing date 2023-07-01
    Publishing country England
    Document type Journal Article
    ZDB-ID 2041406-7
    ISSN 1466-609X ; 1364-8535
    ISSN (online) 1466-609X
    ISSN 1364-8535
    DOI 10.1186/s13054-023-04548-w
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

To top