1
|
Lukasewicz Ferreira SA, Franco Meneses AC, Vaz TA, da Fontoura Carvalho OL, Hubner Dalmora C, Pressotto Vanni D, Ribeiro Berti I, Pires Dos Santos R. Hospital-acquired infections surveillance: The machine-learning algorithm mirrors National Healthcare Safety Network definitions. Infect Control Hosp Epidemiol 2024; 45:604-608. [PMID: 38204340 DOI: 10.1017/ice.2023.224] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/12/2024]
Abstract
BACKGROUND Surveillance of hospital-acquired infections (HAIs) is the foundation of infection control. Machine learning (ML) has been demonstrated to be a valuable tool for HAI surveillance. We compared manual surveillance with a supervised, semiautomated, ML method, and we explored the types of infection and features of importance depicted by the model. METHODS From July 2021 to December 2021, a semiautomated surveillance method based on the ML random forest algorithm, was implemented in a Brazilian hospital. Inpatient records were independently manually searched by the local team, and a panel of independent experts reviewed the ML semiautomated results for confirmation of HAI. RESULTS Among 6,296 patients, manual surveillance classified 183 HAI cases (2.9%), and a semiautomated method found 299 HAI cases (4.7%). The semiautomated method added 77 respiratory infections, which comprised 93.9% of the additional HAIs. The ML model considered 447 features for HAI classification. Among them, 148 features (33.1%) were related to infection signs and symptoms; 101 (22.6%) were related to patient severity status, 51 features (11.4%) were related to bacterial laboratory results; 40 features (8.9%) were related to invasive procedures; 34 (7.6%) were related to antibiotic use; and 31 features (6.9%) were related to patient comorbidities. Among these 447 features, 229 (51.2%) were similar to those proposed by NHSN as criteria for HAI classification. CONCLUSION The ML algorithm, which included most NHSN criteria and >200 features, augmented the human capacity for HAI classification. Well-documented algorithm performances may facilitate the incorporation of AI tools in clinical or epidemiological practice and overcome the drawbacks of traditional HAI surveillance.
Collapse
|
2
|
Knighton SC, Engle J, Berkson J, Bartles R. A narrative review of how infection preventionist (IP) staffing and outcome metrics are assessed by health care organizations and factors to consider. Am J Infect Control 2024; 52:91-106. [PMID: 37978984 DOI: 10.1016/j.ajic.2023.06.017] [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: 02/18/2023] [Revised: 06/22/2023] [Accepted: 06/22/2023] [Indexed: 11/19/2023]
Abstract
BACKGROUND Infection Preventionist to date are experiencing staffing shortages, the purpose of this narrative review is to understand how heath care organizations track staffing and outcome metrics in relation to Infection Preventionists. METHODS Databases utilized included MEDLINE, PubMed, EMBASE, Web of Science, and Google Scholar. RESULTS The initial search included 668 studies. After excluding duplicates, the title and abstract review yielded 50 articles. After screening full texts, 37 studies met the inclusion criteria. Significant variability exists within infection prevention staffing metrics. Common metrics to account for IP staffing levels include the ratio of IPs per facility and IPs per inpatient bed. Frequently tracked outcomes in relation to infection preventionists include Catheter-associated urinary tract infections and central line bloodstream infection incidence rates and standardized infection ratios, as well as Clostridioides difficile incidence rates. Metrics and outcomes from included studies are available in our supporting tables. CONCLUSIONS This review highlights the need for a new IP staffing model that focuses on a granular assessment of each program and care setting. Additional studies can then be conducted to examine how ideal staffing impacts outcome metrics.
Collapse
Affiliation(s)
- Shanina C Knighton
- Case Western Reserve University, Frances Payne Bolton School of Nursing, Cleveland, OH.
| | - Joshua Engle
- Beth Israel Deaconess Medical Center, School of Medicine, Boston, MA
| | - Julia Berkson
- Association for Professions in Infection Control and Epidemiology, Center for Research, Practice and Innovation, Arlington, VA
| | - Rebecca Bartles
- Providence Saint Joseph Health, System Infectious Disease Management & Prevention, Seattle, WA; University of Providence, Infection Prevention and Epidemiology, Great Falls, MT
| |
Collapse
|
3
|
Robinson J, Price L, Otter J, Burnett E. Designing an optimal infection prevention service: Part 2. J Infect Prev 2023; 24:11-22. [PMID: 36644523 PMCID: PMC9834426 DOI: 10.1177/17571774221127573] [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: 04/14/2022] [Accepted: 09/04/2022] [Indexed: 01/18/2023] Open
Abstract
Background The importance of infection prevention and control (IPC) services to prevent threats from healthcare-associated infections and improve the quality of healthcare delivery is undeniable. However, IPC services across the UK and Ireland have substantial variability in terms of team structures and delivery models. Aim The aim of this study was to define an optimal IPC service in different contexts and settings within the United Kingdom and Ireland. Methods This mixed methods study adopted discussion huddles with IPC teams to explore various components of IPC programmes and services. A Nominal Group technique was then undertaken to achieve a group consensus of what an optimal infection prevention service should look like. Results Five discussion huddles were conducted which included 53 participants in total. Key themes arising were IPC Service Priorities, IPC Service Enablers for Success, and Necessary Skills and Expertise Required for Delivering an Effective IPC Service. For the nominal technique, 45 responses were identified which were determining the key priorities for an effective IPC service and 69 responses for establishing key enablers for success. Discussion These findings supported the development of a conceptual model for designing an optimal infection prevention service, which can be used to develop IPC services at an international, national, regional and local level. A focus is required around implementation of these highlighted enablers, so are effectively embedded into infection prevention and control services, and wider healthcare settings.
Collapse
Affiliation(s)
- Jude Robinson
- Infection Prevention and control, NHS England and Improvement, Midlands, UK
| | - Lesley Price
- School of Health and life sciences, Glasgow Caledonian University, Glasgow, UK
| | - Jon Otter
- Infection Prevention and control, Guy’s and St Thomas NHS, London, UK
| | - Emma Burnett
- Fatima College of Health Sciences, Al Ain, United Arab Emirates
| |
Collapse
|
4
|
Crnich CJ. Reimagining Infection Control in U.S. Nursing Homes in the Era of COVID-19. J Am Med Dir Assoc 2022; 23:1909-1915. [PMID: 36423677 PMCID: PMC9666375 DOI: 10.1016/j.jamda.2022.10.022] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/09/2022] [Revised: 10/24/2022] [Accepted: 10/24/2022] [Indexed: 11/18/2022]
Abstract
Residents of nursing homes (NHs) are susceptible to infection, and these facilities, particularly those that provide post-acute care services, are high-risk settings for the rapid spread of communicable respiratory and gastrointestinal illnesses, as well as antibiotic-resistant bacteria. The complexity of medical care delivered in most NHs has increased dramatically over the past 2 decades; however, the structure and resources supporting the practice of infection prevention and control in these facilities has failed to keep pace. Rising numbers of infections caused by Clostridioides difficile and multidrug-resistant organisms, as well as the catastrophic effects of COVID-19 have pushed NH infection control resources to a breaking point. Recent changes to federal regulations require NHs to devote greater resources to the facility infection control program. However, additional changes are needed if sustained improvements in the prevention and control of infections and antibiotic resistance in NHs are to be achieved.
Collapse
Affiliation(s)
- Christopher J Crnich
- School of Medicine & Public Health, University of Wisconsin-Madison, Madison, WI, USA; William S. Middleton Veterans Hospital Geriatric Research Education and Clinical Center, Madison, WI, USA.
| |
Collapse
|
5
|
Nair A, Jawale Y, Dubey SR, Dharmadhikari S, Zadey S. Workforce problems at rural public health-centres in India: a WISN retrospective analysis and national-level modelling study. HUMAN RESOURCES FOR HEALTH 2022; 19:147. [PMID: 35090494 PMCID: PMC8796332 DOI: 10.1186/s12960-021-00687-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/04/2021] [Accepted: 11/05/2021] [Indexed: 05/09/2023]
Abstract
BACKGROUND Rural India has a severe shortage of human resources for health (HRH). The National Rural Health Mission (NRHM) deploys HRH in the rural public health system to tackle shortages. Sanctioning under NRHM does not account for workload resulting in inadequate and inequitable HRH allocation. The Workforce Indicators of Staffing Needs (WISN) approach can identify shortages and inform appropriate sanctioning norms. India currently lacks nationally relevant WISN estimates. We used existing data and modelling techniques to synthesize such estimates. METHODS We conducted a retrospective analysis of existing survey data for 93 facilities from 5 states over 8 years to create WISN calculations for HRH cadres at primary and community health centres (PHCs and CHCs) in rural areas. We modelled nationally representative average WISN-based requirements for specialist doctors at CHCs, general doctors and nurses at PHCs and CHCs. For 2019, we calculated national and state-level overall and per-centre WISN differences and ratios to depict shortage and workload pressure. We checked correlations between WISN ratios for cadres at a given centre-type to assess joint workload pressure. We evaluated the gaps between WISN-based requirements and sanctioned posts to investigate suboptimal sanctioning through concordance analysis and difference comparisons. RESULTS In 2019, at the national-level, WISN differences depicted workforce shortages for all considered HRH cadres. WISN ratios showed that nurses at PHCs and CHCs, and all specialist doctors at CHCs had very high workload pressure. States with more workload on PHC-doctors also had more workload on PHC-nurses depicting an augmenting or compounding effect on workload pressure across cadres. A similar result was seen for CHC-specialist pairs-physicians and surgeons, physicians and paediatricians, and paediatricians and obstetricians-gynaecologists. We found poor concordance between current sanctioning norms and WISN-based requirements with all cadres facing under-sanctioning. We also present across-state variations in workforce problems, workload pressure and sanctioning problems. CONCLUSION We demonstrate the use of WISN calculations based on available data and modelling techniques for national-level estimation. Our findings suggest prioritising nurses and specialists in the rural public health system and updating the existing sanctioning norms based on workload assessments. Workload-based rural HRH deployment can ensure adequate availability and optimal distribution.
Collapse
Affiliation(s)
- Aatmika Nair
- Association for Socially Applicable Research (ASAR), Pune, 411007, Maharashtra, India
- Rajarshi Chhatrapati Shahu Maharaj Government Medical College and CPR Hospital, Kolhapur, 416002, Maharashtra, India
| | - Yash Jawale
- Association for Socially Applicable Research (ASAR), Pune, 411007, Maharashtra, India
- Department of Bionanoscience, Kavli Institute of Nanoscience, Delft University of Technology, Delft, The Netherlands
| | - Sweta R Dubey
- Association for Socially Applicable Research (ASAR), Pune, 411007, Maharashtra, India
| | - Surabhi Dharmadhikari
- Association for Socially Applicable Research (ASAR), Pune, 411007, Maharashtra, India
| | - Siddhesh Zadey
- Association for Socially Applicable Research (ASAR), Pune, 411007, Maharashtra, India.
- Duke Global Health Institute, Duke University, Durham, NC, 27710, USA.
- Department of Surgery, Duke University School of Medicine, Durham, NC, 27710, USA.
| |
Collapse
|
6
|
Lessons Learnt during the Implementation of WISN for Comprehensive Primary Health Care in India, South Africa and Peru. INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH 2021; 18:ijerph182312541. [PMID: 34886270 PMCID: PMC8656745 DOI: 10.3390/ijerph182312541] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Subscribe] [Scholar Register] [Received: 10/29/2021] [Revised: 11/25/2021] [Accepted: 11/27/2021] [Indexed: 11/20/2022]
Abstract
Introduction: The World Health Organization introduced the workload indicators of staffing needs (WISN) in 1998 to improve country-level health workforce planning. This study presents the primary care health workforce planning experiences of India, South Africa and Peru. Methods: A case study approach was used to explore the lessons learnt in the implementation of WISN in India and South Africa. It also describes the methods developed and implemented to estimate health workforce in Peru. We identify the barriers and facilitators faced by countries during the implementation phase through the triangulation of literature, government reports and accounts of involved health planners in the three countries. Results: India implemented WISN in a referral pathway of three district health facilities, including a primary health centre, community health centre and district hospital. Implementation was impeded by limited technical support, poor stakeholder consultation and information systems challenges. South Africa implemented WISN for health workforce planning in primary care and found the skills mix and staff determinations to be unaffordable. The Peruvian Ministry of Health considered using WISN but decided to develop a context-specific tool to estimate the health workforce needed using its available resources such as the National Register of Health Personnel. The main challenge in using WISN was the insufficient information on its inputs. Conclusion: While India and South Africa had unique experiences with the integration of WISN in their health system, none of the countries has yet benefited from the implementation of WISN due to financial, infrastructure and technical challenges. Since the methodology developed by the Peruvian Ministry of Health is context-specific, its implementation has been promising for health workforce planning. The learnings from these countries’ experiences will prove useful in bringing future changes for the health workforce.
Collapse
|
7
|
Improving surgical site infection prevention in Asia-Pacific through appropriate surveillance programs: Challenges and recommendation. Infect Dis Health 2021; 26:198-207. [PMID: 33931363 DOI: 10.1016/j.idh.2021.03.003] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/03/2021] [Revised: 03/23/2021] [Accepted: 03/25/2021] [Indexed: 01/26/2023]
Abstract
BACKGROUND Surgical site infections (SSIs) represent a substantial clinical and economic burden on patients and the healthcare system. The prevention of SSIs entails surveillance activities which lead to effective mitigation strategies, which are lacking across Asia Pacific (APAC). This manuscript aims to document gaps and challenges across APAC that affect the undertaking of a successful SSI surveillance activities and to provide recommendations on overcoming such challenges. METHODS A targeted literature review with relevance to APAC identified a series of salient points pertaining to SSI prevention guidelines, implementation, surveillance and outcomes, which was discussed in July 2019 at the APAC Surgical Site Infection Prevention Symposium. An expert panel, comprising eight multidisciplinary experts from APAC and the USA, subsequently amalgamated the key discussion points from the Symposium and their clinical experiences in developing this article. RESULTS The barriers to implementing a successful and effective APAC SSI surveillance program were identified as: (a) lack of standardized definitions, reporting methodology and accountability, (b) lack of fiscal resources, (c) reporting variability and under-reporting, and (d) lack of safety culture. Implementing an effective surveillance program in APAC will require countries to develop a well-designed and robust surveillance plan and ensure adequate training for staffs involved. CONCLUSION To improve SSI prevention in the region, it is imperative to encourage implementation of national programs with standardized methodologies and accountabilities. An ongoing APAC information exchange, including data and methodologies, will enable continuous learning within the APAC region.
Collapse
|