1
|
Han T, Xiong F, Sun B, Zhong L, Han Z, Lei M. Development and validation of an artificial intelligence mobile application for predicting 30-day mortality in critically ill patients with orthopaedic trauma. Int J Med Inform 2024; 184:105383. [PMID: 38387198 DOI: 10.1016/j.ijmedinf.2024.105383] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/21/2023] [Revised: 01/25/2024] [Accepted: 02/16/2024] [Indexed: 02/24/2024]
Abstract
BACKGROUND Given the intricate and grave nature of trauma-related injuries in ICU settings, it is imperative to develop and deploy reliable predictive tools that can aid in the early identification of high-risk patients who are at risk of early death. The objective of this study is to create and validate an artificial intelligence (AI) model that can accurately predict early mortality among critical fracture patients. METHODS A total of 2662 critically ill patients with orthopaedic trauma were included from the MIMIC III database. Early mortality was defined as death within 30 days in this study. The patients were randomly divided into a model training cohort and a model validation cohort. Various algorithms, including logistic regression (LR), extreme gradient boosting machine (eXGBM), decision tree (DT), support vector machine (SVM), random forest (RF), and neural network (NN), were employed. Evaluation metrics, including discrimination and calibration, were used to develop a comprehensive scoring system ranging from 0 to 60, with higher scores indicating better prediction performance. Furthermore, external validation was carried out using 131 patients. The optimal model was deployed as an internet-based AI tool. RESULTS Among all models, the eXGBM demonstrated the highest area under the curve (AUC) value (0.974, 95%CI: 0.959-0.983), followed by the RF model (0.951, 95%CI: 0.935-0.967) and the NN model (0.922, 95%CI: 0.905-0.941). Additionally, the eXGBM model outperformed other models in terms of accuracy (0.915), precision (0.906), recall (0.926), F1 score (0.916), Brier score (0.062), log loss (0.210), and discrimination slope (0.767). Based on the scoring system, the eXGBM model achieved the highest score (53), followed by RF (42) and NN (39). The LR, DT, and SVM models obtained scores of 28, 18, and 32, respectively. Decision curve analysis further confirmed the superior clinical net benefits of the eXGBM model. External validation of the model achieved an AUC value of 0.913 (95%CI: 0.878-0.948). Consequently, the model was deployed on the Internet at https://30-daymortalityincriticallyillpatients-fnfsynbpbp6rgineaspuim.streamlit.app/, allowing users to input patient features and obtain predicted risks of early mortality among critical fracture patients. Furthermore, the AI model successfully stratified patients into low or high risk of early mortality based on a predefined threshold and provided recommendations for appropriate therapeutic interventions. CONCLUSION This study successfully develops and validates an AI model, with the eXGBM algorithm demonstrating the highest predictive performance for early mortality in critical fracture patients. By deploying the model as a web-based AI application, healthcare professionals can easily access the tool, enabling them to predict 30-day mortality and aiding in the identification and management of high-risk patients among those critically ill with orthopedic trauma.
Collapse
Affiliation(s)
- Tao Han
- Department of Orthopedics, Hainan Hospital of PLA General Hospital, Hainan, China
| | - Fan Xiong
- Department of Orthopedic Surgery, People's Hospital of Macheng City, Huanggang, China
| | - Baisheng Sun
- Department of Critical Care Medicine, The First Medical Centre, PLA General Hospital, Beijing, China; Chinese PLA Medical School, Beijing, China
| | - Lixia Zhong
- Department of Intensive Care Medicine, Beijing Friendship Hospital, Capital Medical University, Beijing, China.
| | - Zhencan Han
- Xiangya School of Medicine, Center South University, Changsha, China.
| | - Mingxing Lei
- Department of Orthopedics, Hainan Hospital of PLA General Hospital, Hainan, China; Chinese PLA Medical School, Beijing, China; Department of Orthopedics, National Clinical Research Center for Orthopedics, Sports Medicine & Rehabilitation, PLA General Hospital, Beijing, China.
| |
Collapse
|
2
|
Taisne A, Aviat F, Essono Mintsa M, Belloncle C, Pailhoriès H. The survival of multi-drug resistant bacteria on raw Douglas fir material. Sci Rep 2024; 14:3546. [PMID: 38347026 PMCID: PMC10861437 DOI: 10.1038/s41598-024-53983-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/14/2023] [Accepted: 02/07/2024] [Indexed: 02/15/2024] Open
Abstract
In today's age of ecological transition, the use of materials such as renewable wood in construction is particularly relevant, but also a challenge in the healthcare sector where the hygiene dimension also comes into play. In this study we have investigated the survival of multi-resistant bacteria commonly responsible for healthcare-associated infections (HAIs) (ESBL-positive Klebsiella pneumoniae and glycopeptide-resistant Enterococcus faecalis) on two different types of wood (Douglas fir : Pseudotsuga menziesii and Maritime Pine : Pinus pinaster) compared to other materials (smooth: stainless steel and rough: pumice stone) and the effect of a disinfection protocol on the bacterial survival on Pseudotsuga menziesii. Approximately 108 bacteria were inoculated on each material and bacterial survival was observed over several days (D0, D1, D2, D3, D6, D7 and D15). Each analysis was performed in triplicate for each time and material. The results show an important reduction of the bacterial inoculum for Klebsiella pneumoniae and Enterococcus faecalis on Douglas fir, in contrast with the results obtained on maritime pine, stainless steel and pumice stone. No bacterial survival was detected on Douglas fir after application of a hospital disinfection protocol. These different results show that wood may have a place in the future of healthcare construction. Further studies would be interesting to better understand the different properties of wood.
Collapse
Affiliation(s)
- A Taisne
- Laboratoire de Bactériologie-Hygiène, Centre Hospitalier Universitaire, 4 rue Larrey, 49933, Angers cedex, France
| | - F Aviat
- Your ResearcH-Bio-Scientific, 307 la Gauterie, 44430, Le Landreau, France
| | - M Essono Mintsa
- Laboratoire Innovation Matériau Bois Habitat (LIMBHA), Ecole Supérieure du Bois, 7 rue Christian Pauc, 44000, Nantes, France
| | - C Belloncle
- Laboratoire Innovation Matériau Bois Habitat (LIMBHA), Ecole Supérieure du Bois, 7 rue Christian Pauc, 44000, Nantes, France
| | - H Pailhoriès
- Laboratoire de Bactériologie-Hygiène, Centre Hospitalier Universitaire, 4 rue Larrey, 49933, Angers cedex, France.
- Laboratoire HIFIH, UPRES EA3859, SFR 4208, Université d'Angers, Angers, France.
| |
Collapse
|
3
|
Frattari A, Polilli E, Rapacchiale G, Coladonato S, Ianniruberto S, Mazzotta E, Patarchi A, Battilana M, Ciulli R, Moretta A, Visocchi L, Savini V, Spacone A, Zocaro R, Carinci F, Parruti G. Predictors of bacteremia and death, including immune status, in a large single-center cohort of unvaccinated ICU patients with COVID-19 pneumonia. Eur J Med Res 2023; 28:219. [PMID: 37400898 DOI: 10.1186/s40001-023-01166-8] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/26/2022] [Accepted: 06/11/2023] [Indexed: 07/05/2023] Open
Abstract
BACKGROUND We investigated the possible role of the immune profile at ICU admission, among other well characterized clinical and laboratory predictors of unfavorable outcome in COVID-19 patients assisted in ICU. METHODS Retrospective analysis of clinical and laboratory data collected for all consecutive patients admitted to the ICUs of the General Hospital of Pescara (Abruzzo, Italy), between 1st March 2020 and 30th April 2021, with a confirmed diagnosis of COVID-19 respiratory failure. Logistic regressions were used to identify independent predictors of bacteremia and mortality. RESULTS Out of 431 patients included in the study, bacteremia was present in N = 191 (44.3%) and death occurred in N = 210 (48.7%). After multivariate analysis, increased risk of bacteremia was found for viral reactivation (OR = 3.28; 95% CI:1.83-6.08), pronation (3.36; 2.12-5.37) and orotracheal intubation (2.51; 1.58-4.02). Increased mortality was found for bacteremia (2.05; 1.31-3.22), viral reactivation (2.29; 1.29-4.19) and lymphocytes < 0.6 × 103c/µL (2.32; 1.49-3.64). CONCLUSIONS We found that viral reactivation, mostly due to Herpesviridae, was associated with increased risk of both bacteremia and mortality. In addition, pronation and intubation are strong predictors of bacteremia, which in turn together with severe lymphocytopenia due to SARS-CoV2 was associated with increased mortality. Most episodes of bacteremia, even due to Acinetobacter spp, were not predicted by microbiological evidence of colonization.
Collapse
Affiliation(s)
| | - Ennio Polilli
- Clinical Pathology Unit, Pescara General Hospital, Pescara, Italy
| | | | | | | | - Elena Mazzotta
- Infectious Diseases Unit, Pescara General Hospital, Pescara, Italy
| | | | | | - Raffaella Ciulli
- Unit of Intensive Care, Pescara General Hospital, Pescara, Italy
| | - Angelo Moretta
- Unit of Intensive Care, Pescara General Hospital, Pescara, Italy
| | - Lina Visocchi
- Unit of Intensive Care, Pescara General Hospital, Pescara, Italy
| | - Vincenzo Savini
- Microbiology and Virology Unit, Pescara General Hospital, Pescara, Italy
| | | | - Rosamaria Zocaro
- Unit of Intensive Care, Pescara General Hospital, Pescara, Italy
| | - Fabrizio Carinci
- Department of Statistical Sciences, Università Di Bologna, Bologna, Italy
| | - Giustino Parruti
- Infectious Diseases Unit, Pescara General Hospital, Pescara, Italy.
| |
Collapse
|
4
|
Rong R, Lin L, Yang Y, Zhao S, Guo R, Ye J, Zhu X, Wen Q, Liu D. Trending prevalence of healthcare-associated infections in a tertiary hospital in China during the COVID-19 pandemic. BMC Infect Dis 2023; 23:41. [PMID: 36670378 PMCID: PMC9857900 DOI: 10.1186/s12879-022-07952-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/21/2022] [Accepted: 12/19/2022] [Indexed: 01/22/2023] Open
Abstract
BACKGROUND The purpose of this study was to demonstrate both the four-year prevalence trend of healthcare-associated infections (HAIs) in a large tertiary hospital and the trend regarding the prevalence of HAIs following the outbreak of coronavirus disease 2019 (COVID-19) in order to provide evidence of hospital infection management during the COVID-19 pandemic. METHODS Based on the hospital's electronic nosocomial infection databases related to HAIs, we retrospectively identified the HAI cases to assess the epidemiological characteristics of HAIs from January 1, 2018, to December 31, 2021, in a large tertiary hospital in China. Similarly, the trends of HAIs after the COVID-19 outbreak and the seasonal variation of HAIs were further analyzed. RESULTS The HAI cases (n = 7833) were identified from the inpatients (n = 483,258) during the 4 years. The most frequently occurring underlying cause of HAIs was respiratory tract infections (44.47%), followed by bloodstream infections (11.59%), and urinary tract infections (8.69%). The annual prevalence of HAIs decreased from 2.39% in 2018 to 1.41% in 2021 (P = 0.032), with the overall prevalence of HAIs significantly decreasing since the outbreak of COVID-19 (2.20% in 2018-2019 vs. 1.44% in 2020-2021, P < 0.001). The prevalence of respiratory tract infections decreased most significantly; whereas, overall, the prevalence of HAIs was significantly greater during the winter compared with the rest of the year. CONCLUSIONS Not only did the annual prevalence of HAIs decrease from 2018 to 2021, but it also significantly decreased since the start of the COVID-19 pandemic, particularly respiratory tract infections. These results provide evidence for the need to prevent HAIs, especially during the winter season.
Collapse
Affiliation(s)
- Rong Rong
- grid.412615.50000 0004 1803 6239Department of Nosocomial Infection, The First Affiliated Hospital, Sun Yat-sen University, Zhong Shan 2nd Road, No. 58, Guangzhou, 510080 Guangdong China
| | - Lanxi Lin
- grid.412615.50000 0004 1803 6239Department of Nosocomial Infection, The First Affiliated Hospital, Sun Yat-sen University, Zhong Shan 2nd Road, No. 58, Guangzhou, 510080 Guangdong China
| | - Yongjie Yang
- grid.412615.50000 0004 1803 6239Department of Nosocomial Infection, The First Affiliated Hospital, Sun Yat-sen University, Zhong Shan 2nd Road, No. 58, Guangzhou, 510080 Guangdong China
| | - Shumin Zhao
- grid.412615.50000 0004 1803 6239Department of Nosocomial Infection, The First Affiliated Hospital, Sun Yat-sen University, Zhong Shan 2nd Road, No. 58, Guangzhou, 510080 Guangdong China
| | - Ruiling Guo
- grid.412615.50000 0004 1803 6239Department of Nosocomial Infection, The First Affiliated Hospital, Sun Yat-sen University, Zhong Shan 2nd Road, No. 58, Guangzhou, 510080 Guangdong China
| | - Junpeng Ye
- grid.412615.50000 0004 1803 6239Department of Nosocomial Infection, The First Affiliated Hospital, Sun Yat-sen University, Zhong Shan 2nd Road, No. 58, Guangzhou, 510080 Guangdong China
| | - Xinghua Zhu
- grid.412615.50000 0004 1803 6239Department of Nosocomial Infection, The First Affiliated Hospital, Sun Yat-sen University, Zhong Shan 2nd Road, No. 58, Guangzhou, 510080 Guangdong China
| | - Qiong Wen
- grid.412615.50000 0004 1803 6239Department of Nephrology, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, China ,grid.484195.5Key Laboratory of Guangdong Province, Key Laboratory of National Health Commission, Zhong Shan 2nd Road, No. 58, Guangzhou, 510080 Guangdong China
| | - Dayue Liu
- grid.412615.50000 0004 1803 6239Department of Nosocomial Infection, The First Affiliated Hospital, Sun Yat-sen University, Zhong Shan 2nd Road, No. 58, Guangzhou, 510080 Guangdong China
| |
Collapse
|
5
|
Thandar MM, Rahman MO, Haruyama R, Matsuoka S, Okawa S, Moriyama J, Yokobori Y, Matsubara C, Nagai M, Ota E, Baba T. Effectiveness of Infection Control Teams in Reducing Healthcare-Associated Infections: A Systematic Review and Meta-Analysis. INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH 2022; 19:17075. [PMID: 36554953 PMCID: PMC9779570 DOI: 10.3390/ijerph192417075] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 11/17/2022] [Revised: 12/11/2022] [Accepted: 12/15/2022] [Indexed: 06/17/2023]
Abstract
The infection control team (ICT) ensures the implementation of infection control guidelines in healthcare facilities. This systematic review aims to evaluate the effectiveness of ICT, with or without an infection control link nurse (ICLN) system, in reducing healthcare-associated infections (HCAIs). We searched four databases to identify randomised controlled trials (RCTs) in inpatient, outpatient and long-term care facilities. We judged the quality of the studies, conducted meta-analyses whenever interventions and outcome measures were comparable in at least two studies, and assessed the certainty of evidence. Nine RCTs were included; all were rated as being low quality. Overall, ICT, with or without an ICLN system, did not reduce the incidence rate of HCAIs [risk ratio (RR) = 0.65, 95% confidence interval (CI): 0.45-1.07], death due to HCAIs (RR = 0.32, 95% CI: 0.04-2.69) and length of hospital stay (42 days vs. 45 days, p = 0.52). However, ICT with an ICLN system improved nurses' compliance with infection control practices (RR = 1.17, 95% CI: 1.00-1.38). Due to the high level of bias, inconsistency and imprecision, these findings should be considered with caution. High-quality studies using similar outcome measures are needed to demonstrate the effectiveness and cost-effectiveness of ICT.
Collapse
Affiliation(s)
- Moe Moe Thandar
- Bureau of International Health Cooperation, National Center for Global Health and Medicine, Tokyo 162-8655, Japan
| | - Md. Obaidur Rahman
- Center for Surveillance, Immunization, and Epidemiologic Research, National Institute of Infectious Diseases, Tokyo 162-8640, Japan
- Center for Evidence-Based Medicine and Clinical Research, Dhaka 1230, Bangladesh
| | - Rei Haruyama
- Bureau of International Health Cooperation, National Center for Global Health and Medicine, Tokyo 162-8655, Japan
| | - Sadatoshi Matsuoka
- Bureau of International Health Cooperation, National Center for Global Health and Medicine, Tokyo 162-8655, Japan
| | - Sumiyo Okawa
- Bureau of International Health Cooperation, National Center for Global Health and Medicine, Tokyo 162-8655, Japan
| | - Jun Moriyama
- Bureau of International Health Cooperation, National Center for Global Health and Medicine, Tokyo 162-8655, Japan
| | - Yuta Yokobori
- Bureau of International Health Cooperation, National Center for Global Health and Medicine, Tokyo 162-8655, Japan
| | - Chieko Matsubara
- Bureau of International Health Cooperation, National Center for Global Health and Medicine, Tokyo 162-8655, Japan
| | - Mari Nagai
- Bureau of International Health Cooperation, National Center for Global Health and Medicine, Tokyo 162-8655, Japan
| | - Erika Ota
- Global Health Nursing, Graduate School of Nursing Sciences, St. Luke’s International University, Tokyo 104-0044, Japan
- Tokyo Foundation for Policy Research, Minato, Tokyo 106-0032, Japan
| | - Toshiaki Baba
- Bureau of International Health Cooperation, National Center for Global Health and Medicine, Tokyo 162-8655, Japan
| |
Collapse
|
6
|
Finazzi S, Luci G, Olivieri C, Langer M, Mandelli G, Corona A, Viaggi B, Di Paolo A. Tissue Penetration of Antimicrobials in Intensive Care Unit Patients: A Systematic Review—Part I. Antibiotics (Basel) 2022; 11:antibiotics11091164. [PMID: 36139944 PMCID: PMC9495190 DOI: 10.3390/antibiotics11091164] [Citation(s) in RCA: 11] [Impact Index Per Article: 5.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/23/2022] [Revised: 08/14/2022] [Accepted: 08/26/2022] [Indexed: 11/19/2022] Open
Abstract
The challenging severity of some infections, especially in critically ill patients, makes the diffusion of antimicrobial drugs within tissues one of the cornerstones of chemotherapy. The knowledge of how antibacterial agents penetrate tissues may come from different sources: preclinical studies in animal models, phase I–III clinical trials and post-registration studies. However, the particular physiopathology of critically ill patients may significantly alter drug pharmacokinetics. Indeed, changes in interstitial volumes (the third space) and/or in glomerular filtration ratio may influence the achievement of bactericidal concentrations in peripheral compartments, while inflammation can alter the systemic distribution of some drugs. On the contrary, other antibacterial agents may reach high and effective concentrations thanks to the increased tissue accumulation of macrophages and neutrophils. Therefore, the present review explores the tissue distribution of beta-lactams and other antimicrobials acting on the cell wall and cytoplasmic membrane of bacteria in critically ill patients. A systematic search of articles was performed according to PRISMA guidelines, and tissue/plasma penetration ratios were collected. Results showed a highly variable passage of drugs within tissues, while large interindividual variability may represent a hurdle which must be overcome to achieve therapeutic concentrations in some compartments. To solve that issue, off-label dosing regimens could represent an effective solution in particular conditions.
Collapse
Affiliation(s)
- Stefano Finazzi
- Istituto di Ricerche Farmacologiche Mario Negri IRCCS, 24020 Ranica, Italy
- Associazione GiViTI, c/o Istituto di Ricerche Farmacologiche Mario Negri IRCCS, 20156 Milan, Italy
| | - Giacomo Luci
- Department of Clinical and Experimental Medicine, University of Pisa, 56126 Pisa, Italy
| | - Carlo Olivieri
- Associazione GiViTI, c/o Istituto di Ricerche Farmacologiche Mario Negri IRCCS, 20156 Milan, Italy
- Anesthesia and Intensive Care, Sant’Andrea Hospital, ASL VC, 13100 Vercelli, Italy
| | - Martin Langer
- Associazione GiViTI, c/o Istituto di Ricerche Farmacologiche Mario Negri IRCCS, 20156 Milan, Italy
| | - Giulia Mandelli
- Istituto di Ricerche Farmacologiche Mario Negri IRCCS, 24020 Ranica, Italy
| | - Alberto Corona
- ICU and Accident & Emergency Department, ASST Valcamonica, 25043 Breno, Italy
| | - Bruno Viaggi
- Associazione GiViTI, c/o Istituto di Ricerche Farmacologiche Mario Negri IRCCS, 20156 Milan, Italy
- Department of Anesthesiology, Neuro-Intensive Care Unit, Florence Careggi University Hospital, 50139 Florence, Italy
| | - Antonello Di Paolo
- Department of Clinical and Experimental Medicine, University of Pisa, 56126 Pisa, Italy
- Correspondence:
| |
Collapse
|
7
|
Emerging Paradigms in the Prevention of Surgical Site Infection: The Patient Microbiome and Antimicrobial Resistance. Anesthesiology 2022; 137:252-262. [PMID: 35666980 PMCID: PMC9558427 DOI: 10.1097/aln.0000000000004267] [Citation(s) in RCA: 16] [Impact Index Per Article: 8.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/18/2022]
Abstract
This article summarizes new scientific evidence on the pathogenesis of surgical site infection, including the roles of the patient microbiome and antimicrobial resistance, and reviews changes in guidelines and clinical practices for prevention.
Collapse
|