1
|
Wang Y, Wang G, Zhao Y, Wang C, Chen C, Ding Y, Lin J, You J, Gao S, Pang X. A deep learning model for predicting multidrug-resistant organism infection in critically ill patients. J Intensive Care 2023; 11:49. [PMID: 37941079 PMCID: PMC10633993 DOI: 10.1186/s40560-023-00695-y] [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: 08/31/2023] [Accepted: 10/12/2023] [Indexed: 11/10/2023] Open
Abstract
BACKGROUND This study aimed to apply the backpropagation neural network (BPNN) to develop a model for predicting multidrug-resistant organism (MDRO) infection in critically ill patients. METHODS This study collected patient information admitted to the intensive care unit (ICU) of the Affiliated Hospital of Qingdao University from August 2021 to January 2022. All patients enrolled were divided randomly into a training set (80%) and a test set (20%). The least absolute shrinkage and selection operator and stepwise regression analysis were used to determine the independent risk factors for MDRO infection. A BPNN model was constructed based on these factors. Then, we externally validated this model in patients from May 2022 to July 2022 over the same center. The model performance was evaluated by the calibration curve, the area under the curve (AUC), sensitivity, specificity, and accuracy. RESULTS In the primary cohort, 688 patients were enrolled, including 109 (15.84%) MDRO infection patients. Risk factors for MDRO infection, as determined by the primary cohort, included length of hospitalization, length of ICU stay, long-term bed rest, antibiotics use before ICU, acute physiology and chronic health evaluation II, invasive operation before ICU, quantity of antibiotics, chronic lung disease, and hypoproteinemia. There were 238 patients in the validation set, including 31 (13.03%) MDRO infection patients. This BPNN model yielded good calibration. The AUC of the training set, the test set and the validation set were 0.889 (95% CI 0.852-0.925), 0.919 (95% CI 0.856-0.983), and 0.811 (95% CI 0.731-0.891), respectively. CONCLUSIONS This study confirmed nine independent risk factors for MDRO infection. The BPNN model performed well and was potentially used to predict MDRO infection in ICU patients.
Collapse
Affiliation(s)
- Yaxi Wang
- Department of Critical Care Medicine, The Affiliated Hospital of Qingdao University, No. 16 Jiangsu Road, Qingdao, 266000, China
| | - Gang Wang
- Department of Critical Care Medicine, The Affiliated Hospital of Qingdao University, No. 16 Jiangsu Road, Qingdao, 266000, China
| | - Yuxiao Zhao
- Department of Critical Care Medicine, The Affiliated Hospital of Qingdao University, No. 16 Jiangsu Road, Qingdao, 266000, China
| | - Cheng Wang
- Department of Critical Care Medicine, The Affiliated Hospital of Qingdao University, No. 16 Jiangsu Road, Qingdao, 266000, China
| | - Chen Chen
- School of Nursing, Qingdao University, No. 38 Dengzhou Road, Qingdao, 266021, China
| | - Yaoyao Ding
- Department of Critical Care Medicine, The Affiliated Hospital of Qingdao University, No. 16 Jiangsu Road, Qingdao, 266000, China
| | - Jing Lin
- Department of Critical Care Medicine, The Affiliated Hospital of Qingdao University, No. 16 Jiangsu Road, Qingdao, 266000, China
| | - Jingjing You
- Department of Critical Care Medicine, The Affiliated Hospital of Qingdao University, No. 16 Jiangsu Road, Qingdao, 266000, China
| | - Silong Gao
- Department of Critical Care Medicine, The Affiliated Hospital of Qingdao University, No. 16 Jiangsu Road, Qingdao, 266000, China.
| | - Xufeng Pang
- Department of Hospital-Acquired Infection Control, The Affiliated Hospital of Qingdao University, No. 16 Jiangsu Road, Qingdao, 266000, China.
| |
Collapse
|
2
|
Jung M, Park HY, Park GY, Lee JI, Kim Y, Kim YH, Lim SH, Yoo YJ, Im S. Post-Stroke Infections: Insights from Big Data Using Clinical Data Warehouse (CDW). Antibiotics (Basel) 2023; 12:antibiotics12040740. [PMID: 37107102 PMCID: PMC10134983 DOI: 10.3390/antibiotics12040740] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/01/2023] [Revised: 04/04/2023] [Accepted: 04/08/2023] [Indexed: 04/29/2023] Open
Abstract
This study analyzed a digitized database of electronic medical records (EMRs) to identify risk factors for post-stroke infections. The sample included 41,236 patients hospitalized with a first stroke diagnosis (ICD-10 codes I60, I61, I63, and I64) between January 2011 and December 2020. Logistic regression analysis was performed to examine the effect of clinical variables on post-stroke infection. Multivariable analysis revealed that post-stroke infection was associated with the male sex (odds ratio [OR]: 1.79; 95% confidence interval [CI]: 1.49-2.15), brain surgery (OR: 7.89; 95% CI: 6.27-9.92), mechanical ventilation (OR: 18.26; 95% CI: 8.49-44.32), enteral tube feeding (OR: 3.65; 95% CI: 2.98-4.47), and functional activity level (modified Barthel index: OR: 0.98; 95% CI: 0.98-0.98). In addition, exposure to steroids (OR: 2.22; 95% CI: 1.60-3.06) and acid-suppressant drugs (OR: 1.44; 95% CI: 1.15-1.81) increased the risk of infection. On the basis of the findings from this multicenter study, it is crucial to carefully evaluate the balance between the potential benefits of acid-suppressant drugs or corticosteroids and the increased risk of infection in patients at high risk for post-stroke infection.
Collapse
Affiliation(s)
- Moa Jung
- Department of Rehabilitation Medicine, Bucheon St. Mary's Hospital, College of Medicine, The Catholic University of Korea, Seoul 06591, Republic of Korea
| | - Hae-Yeon Park
- Department of Rehabilitation Medicine, Bucheon St. Mary's Hospital, College of Medicine, The Catholic University of Korea, Seoul 06591, Republic of Korea
| | - Geun-Young Park
- Department of Rehabilitation Medicine, Bucheon St. Mary's Hospital, College of Medicine, The Catholic University of Korea, Seoul 06591, Republic of Korea
| | - Jong In Lee
- Department of Rehabilitation Medicine, Seoul St. Mary's Hospital, College of Medicine, The Catholic University of Korea, Seoul 06591, Republic of Korea
| | - Youngkook Kim
- Department of Rehabilitation Medicine, Yeouido St. Mary's Hospital, College of Medicine, The Catholic University of Korea, Seoul 06591, Republic of Korea
| | - Yeo Hyung Kim
- Department of Rehabilitation Medicine, Uijeongbu St. Mary's Hospital, College of Medicine, The Catholic University of Korea, Seoul 06591, Republic of Korea
| | - Seong Hoon Lim
- Department of Rehabilitation Medicine, St. Vincent's Hospital, College of Medicine, The Catholic University of Korea, Seoul 06591, Republic of Korea
| | - Yeun Jie Yoo
- Department of Rehabilitation Medicine, St. Vincent's Hospital, College of Medicine, The Catholic University of Korea, Seoul 06591, Republic of Korea
| | - Sun Im
- Department of Rehabilitation Medicine, Bucheon St. Mary's Hospital, College of Medicine, The Catholic University of Korea, Seoul 06591, Republic of Korea
| |
Collapse
|
3
|
Lenglet A, Contigiani O, Ariti C, Evens E, Charles K, Casimir CF, Senat Delva R, Badjo C, Roggeveen H, Pawulska B, Clezy K, McRae M, Wertheim H, Hopman J. Early warning for healthcare acquired infections in neonatal care units in a low-resource setting using routinely collected hospital data: The experience from Haiti, 2014-2018. PLoS One 2022; 17:e0269385. [PMID: 35737713 PMCID: PMC9223318 DOI: 10.1371/journal.pone.0269385] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/26/2021] [Accepted: 05/19/2022] [Indexed: 11/19/2022] Open
Abstract
In low-resource settings, detection of healthcare-acquired outbreaks in neonatal units relies on astute clinical staff to observe unusual morbidity or mortality from sepsis as microbiological diagnostics are often absent. We aimed to generate reliable (and automated) early warnings for potential clusters of neonatal late onset sepsis using retrospective data that could signal the start of an outbreak in an NCU in Port au Prince, Haiti, using routinely collected data on neonatal admissions. We constructed smoothed time series for late onset sepsis cases, late onset sepsis rates, neonatal care unit (NCU) mortality, maternal admissions, neonatal admissions and neonatal antibiotic consumption. An outbreak was defined as a statistical increase in any of these time series indicators. We created three outbreak alarm classes: 1) thresholds: weeks in which the late onset sepsis cases exceeded four, the late onset sepsis rates exceeded 10% of total NCU admissions and the NCU mortality exceeded 15%; 2) differential: late onset sepsis rates and NCU mortality were double the previous week; and 3) aberration: using the improved Farrington model for late onset sepsis rates and NCU mortality. We validated pairs of alarms by calculating the sensitivity and specificity of the weeks in which each alarm was launched and comparing each alarm to the weeks in which a single GNB positive blood culture was reported from a neonate. The threshold and aberration alarms were the strongest predictors for current and future NCU mortality and current LOS rates (p<0.0002). The aberration alarms were also those with the highest sensitivity, specificity, negative predictive value, and positive predictive value. Without microbiological diagnostics in NCUs in low-resource settings, applying these simple algorithms to routinely collected data show great potential to facilitate early warning for possible healthcare-acquired outbreaks of LOS in neonates. The methods used in this study require validation across other low-resource settings.
Collapse
Affiliation(s)
- Annick Lenglet
- Médecins Sans Frontières, Amsterdam, The Netherlands
- Department of Medical Microbiology, Radboud Institute for Health Sciences, Radboudumc, Nijmegen, The Netherlands
| | - Omar Contigiani
- Médecins Sans Frontières, Amsterdam, The Netherlands
- Leiden Observatory, Leiden University, Leiden, The Netherlands
- Lorentz Institute for Theoretical Physics, Leiden University, Leiden, The Netherlands
| | - Cono Ariti
- School of Medicine, Cardiff University, Cardiff, United Kingdom
| | | | | | | | | | | | | | | | - Kate Clezy
- Médecins Sans Frontières, Amsterdam, The Netherlands
| | - Melissa McRae
- Médecins Sans Frontières, Amsterdam, The Netherlands
| | - Heiman Wertheim
- Department of Medical Microbiology, Radboud Institute for Health Sciences, Radboudumc, Nijmegen, The Netherlands
| | - Joost Hopman
- Médecins Sans Frontières, Amsterdam, The Netherlands
- Department of Medical Microbiology, Radboud Institute for Health Sciences, Radboudumc, Nijmegen, The Netherlands
- Department of Patient Safety and Quality, Radboudumc, Nijmegen, The Netherlands
| |
Collapse
|
4
|
Fan Y, Wu Y, Cao X, Zou J, Zhu M, Dai D, Lu L, Yin X, Xiong L. Automated Cluster Detection of Health Care-Associated Infection Based on the Multisource Surveillance of Process Data in the Area Network: Retrospective Study of Algorithm Development and Validation. JMIR Med Inform 2020; 8:e16901. [PMID: 32965228 PMCID: PMC7647819 DOI: 10.2196/16901] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/05/2019] [Revised: 07/13/2020] [Accepted: 08/02/2020] [Indexed: 11/13/2022] Open
Abstract
BACKGROUND The cluster detection of health care-associated infections (HAIs) is crucial for identifying HAI outbreaks in the early stages. OBJECTIVE We aimed to verify whether multisource surveillance based on the process data in an area network can be effective in detecting HAI clusters. METHODS We retrospectively analyzed the incidence of HAIs and 3 indicators of process data relative to infection, namely, antibiotic utilization rate in combination, inspection rate of bacterial specimens, and positive rate of bacterial specimens, from 4 independent high-risk units in a tertiary hospital in China. We utilized the Shewhart warning model to detect the peaks of the time-series data. Subsequently, we designed 5 surveillance strategies based on the process data for the HAI cluster detection: (1) antibiotic utilization rate in combination only, (2) inspection rate of bacterial specimens only, (3) positive rate of bacterial specimens only, (4) antibiotic utilization rate in combination + inspection rate of bacterial specimens + positive rate of bacterial specimens in parallel, and (5) antibiotic utilization rate in combination + inspection rate of bacterial specimens + positive rate of bacterial specimens in series. We used the receiver operating characteristic (ROC) curve and Youden index to evaluate the warning performance of these surveillance strategies for the detection of HAI clusters. RESULTS The ROC curves of the 5 surveillance strategies were located above the standard line, and the area under the curve of the ROC was larger in the parallel strategy than in the series strategy and the single-indicator strategies. The optimal Youden indexes were 0.48 (95% CI 0.29-0.67) at a threshold of 1.5 in the antibiotic utilization rate in combination-only strategy, 0.49 (95% CI 0.45-0.53) at a threshold of 0.5 in the inspection rate of bacterial specimens-only strategy, 0.50 (95% CI 0.28-0.71) at a threshold of 1.1 in the positive rate of bacterial specimens-only strategy, 0.63 (95% CI 0.49-0.77) at a threshold of 2.6 in the parallel strategy, and 0.32 (95% CI 0.00-0.65) at a threshold of 0.0 in the series strategy. The warning performance of the parallel strategy was greater than that of the single-indicator strategies when the threshold exceeded 1.5. CONCLUSIONS The multisource surveillance of process data in the area network is an effective method for the early detection of HAI clusters. The combination of multisource data and the threshold of the warning model are 2 important factors that influence the performance of the model.
Collapse
Affiliation(s)
- Yunzhou Fan
- Department of Nosocomial Infection Management, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Yanyan Wu
- Department of Nosocomial Infection Management, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Xiongjing Cao
- Department of Nosocomial Infection Management, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Junning Zou
- Department of Nosocomial Infection Management, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Ming Zhu
- Department of Nosocomial Infection Management, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Di Dai
- Department of Nosocomial Infection Management, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Lin Lu
- Department of Nosocomial Infection Management, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Xiaoxv Yin
- School of Public Health, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Lijuan Xiong
- Department of Nosocomial Infection Management, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| |
Collapse
|
5
|
Zhang M, Ma XY, Feng ZQ, Gao L. Survey of antibiotic use among hospitalised children in a hospital in Northeast China over a 4-year period. J SPEC PEDIATR NURS 2020; 25:e12282. [PMID: 31825166 DOI: 10.1111/jspn.12282] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 04/10/2019] [Revised: 10/08/2019] [Accepted: 11/06/2019] [Indexed: 12/23/2022]
Abstract
PURPOSE We investigated the usage of antibiotic utilisation rate (AUR) among Chinese hospitalised children over a 4-year period to determine clinical characteristics. DESIGN AND METHODS AUR, antibiotic type and antibiotic use in combination were analysed among hospitalised children of the affiliated hospital of Beihua University in Northeast China from January 2015 to December 2018. The linear prediction was used to investigate the trends of antibiotics use in combination and AUR, and autoregressive integrated moving average model was used to predict AUR in 2019. RESULTS A total of 2,981 inpatients were admitted to the hospital during the study period. The AUR from 2015 to 2018 was 91.51%, 92.67%, 91.30%, and 93.00%, respectively. AUR was associated with season (p < .01), the peak period was found to be from November to January in 2019 (R2 = 0.802). The etiological delivery rate had increased (p < .01). Pneumonia was the main disease in children for which they received antibiotics. The combination of multidrug (≥3 agents used) had increased (p < .01) over the study period. PRACTICE IMPLICATIONS AUR was stable among hospitalised children in a hospital. Cephalosporin and macrolide antibiotics were the main antibiotic types, and the combination of multidrug had increased, more attention should be paid to the use of antibiotics in hospitalised children.
Collapse
Affiliation(s)
- Min Zhang
- School of Nursing, Beihua University, Jilin, China
| | - Xin Yu Ma
- School of Nursing, Beihua University, Jilin, China
| | - Zhi Qiang Feng
- School of GeoSciences, The University of Edinburgh, Edinburgh, UK
| | - Ling Gao
- School of Nursing, Beihua University, Jilin, China
| |
Collapse
|
6
|
The Minimum Data Set and Quality Indicators for National Healthcare-Associated Infection Surveillance in Mainland China: Towards Precision Management. BIOMED RESEARCH INTERNATIONAL 2019; 2019:2936264. [PMID: 31360709 PMCID: PMC6642767 DOI: 10.1155/2019/2936264] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 04/25/2019] [Accepted: 06/26/2019] [Indexed: 12/13/2022]
Abstract
The magnitude and scope of the healthcare-associated infections (HCAIs) burden are underestimated worldwide, and have raised public concerns for their adverse effect on patient safety. In China, HCAIs still present an unneglected challenge and economic burden in recent decades. With the purpose of reducing the HCAI prevalence and enhancing precision management, China's National Nosocomial Infection Management and Quality Control Center (NNIMQCC) had developed a Minimum Data Set (MDS) and corresponding Quality Indicators (QIs) for establishing national HCAI surveillance system, the data elements of which were repeatedly discussed, investigated, and confirmed by consensus of the expert team. The total number of data elements in MDS and QIs were 70 and 64, and they were both classified into seven categorical items. The NNIMQCC also had started two pilot projects to inspect the applicability, feasibility, and reliability of MDS. After years of hard work, more than 400 health facilities in 14 provinces have realized the importance of HCAI surveillance and contributed to developing an ability of exporting automatically standardized data to meet the requirement of MDS and participate in the regional surveillance system. Generally, the emergence of MDS and QIs in China indicates the beginning of the national HCAI surveillance based on information technology and computerized process data. The establishment of MDS aimed to use electronic health process data to ensure the data accuracy and comparability and to provide instructive and ongoing QIs to estimate and monitor the burden of HCAIs, and to evaluate the effects of interventions and direct health policy decision-making.
Collapse
|