Journal Article > Short ReportFull Text
BMC Proceedings. 6 March 2025; Volume 19 (Issue S4); 7.; DOI:10.1186/s12919-025-00320-w
Tornimbene B, Leiva Rioja ZB, Brownstein J, Dunn A, Faye S, et al.
BMC Proceedings. 6 March 2025; Volume 19 (Issue S4); 7.; DOI:10.1186/s12919-025-00320-w
The COVID-19 pandemic accelerated the development of AI-driven tools to improve public health surveillance and outbreak management. While AI programs have shown promise in disease surveillance, they also present issues such as data privacy, prejudice, and human-AI interactions. This sixth session of the of the WHO Pandemic and Epidemic Intelligence Innovation Forum examines the use of Artificial Intelligence (AI) in public health by collecting the experience of key global health organizations, such the Boston Children's Hospital, the Global South AI for Pandemic & Epidemic Preparedness & Response (AI4PEP) network, Medicines Sans Frontières (MSF), and the University of Sydney. AI's utility in clinical care, particularly in diagnostics, medication discovery, and data processing, has resulted in improvements that may also benefit public health surveillance. However, the use of AI in global health necessitates careful consideration of ethical issues, particularly those involving data use and algorithmic bias. As AI advances, particularly with large language models, public health officials must develop governance frameworks that stress openness, accountability, and fairness. These systems should address worldwide differences in data access and ensure that AI technologies are tailored to specific local needs. Ultimately, AI's ability to improve healthcare efficiency and equity is dependent on multidisciplinary collaboration, community involvement, and inclusive AI designs in ensuring equitable healthcare outcomes to fit the unique demands of global communities.
Journal Article > ReviewFull Text
JAC Antimicrob Resist. 26 December 2024; Volume 7 (Issue 1); DOI: 10.1093/jacamr/dlaf010
Mathu R, Diago-Navarro E, Lynch E, Degail MA, Ousley J, et al.
JAC Antimicrob Resist. 26 December 2024; Volume 7 (Issue 1); DOI: 10.1093/jacamr/dlaf010
INTRODUCTION
Despite global surveillance efforts, antibiotic resistance (ABR) is difficult to address in low- and middle-income countries (LMICs). In the absence of country-wide ABR surveillance data, peer-reviewed literature is the next most significant source of publicly available ABR data. Médecins Sans Frontières conducted this review in hopes of using the pooled findings to inform treatment choices in the studied countries where sufficient local ABR data are unavailable.
METHODS
A systematic literature review reporting ABR rates for six infection sites in nine countries in the Middle East and Southern Asia was conducted. PubMed was used to identify literature published between January 2012 and August 2022. A meta-analysis of the included studies (n = 694) was conducted, of which 224 are reviewed in this paper. The JBI critical appraisal tool was used to evaluate risk of bias for included studies.
RESULTS
This paper focuses on sepsis, burns and wound infections, specifically, with the largest number of papers describing data from Iran, Türkiye and Pakistan. High (>30%) resistance to recommended first-line antibiotics was found. Gram-negative resistance to ceftriaxone, aminoglycosides and carbapenems was high in burn-related infections; colistin resistance among Klebsiella pneumoniae isolates in Pakistan was alarmingly high (81%).
CONCLUSIONS
High-quality data on ABR in LMIC settings remain difficult to obtain. While peer-reviewed literature is a source of publicly available ABR data, it is of inconsistent quality; the field also lacks agreed reporting standards, limiting the capacity to pool findings. Nonetheless, high resistance to first-line antibiotics underscores the need for improved localized surveillance and stewardship.
Conference Material > Slide Presentation
Rapoud D, Cramer E, Al Asmar M, Sagara F, Ndiaye B, et al.
MSF Scientific Day International 2024. 16 May 2024; DOI:10.57740/2acXDPpuix
Conference Material > Abstract
Rapoud D, Cramer E, Al Asmar M, Sagara F, Ndiaye B, et al.
MSF Scientific Day International 2024. 16 May 2024; DOI:10.57740/rxwuURR8
INTRODUCTION
Antimicrobial resistance (AMR) is a major threat to public health and could cause 10 million deaths per year by 2050. Access to high-quality diagnostic tests is a key intervention to tackle AMR, leading to better patient care, provision of data for global surveillance, and more rational use of antibiotics. Despite technological advances, antimicrobial susceptibility testing (AST) interpretation is complex and requires expert clinical microbiologists, which are lacking in low- and middle-income countries (LMIC). To fill the gap, The Médecins Sans Frontières (MSF) Foundation developed Antibiogo, a smartphone-based application to support laboratory technicians with AST interpretation. We aimed to assess the clinical performance of Antibiogo in intended use settings as per European regulations for in-vitro diagnostic medical devices.
METHODS
Antibiogo combines image processing, machine learning, and expert system technologies for the provision of final results (S/I/R: Susceptible, Intermediate, or Resistant). In 2022, we assessed the clinical performance of Antibiogo according to European regulations in three microbiology laboratories in Jordan (MSF Reconstructive Surgery Hospital, Amman), Mali (MSF Paediatric Hospital, Koutiala), and Senegal (Pasteur Institute, Dakar). In each site, clinical AST performed for routine purposes was processed in parallel with Antibiogo. AST pictures and inhibition zone diameter values measured with Antibiogo were interpreted by an expert microbiologist who was masked to Antibiogo interpretation. We calculated S/I/R category agreement between the microbiologist and Antibiogo, as well as minor (mD), major (MD) and very major discrepancies (VMD).
RESULTS
We included 378 fresh isolates in the study, representing 11 different pathogens. The overall category agreement was 88.8% (95% CI 87.9–89.7), ranging per pathogen from 67.1% (63.2–70.8) (for Pseudomonas aeruginosa) to 98.1% (94.4–99.6) (for Haemophilus influenzae), with 10.2% (9.4–11.1) mD, 1.6% MD (1.2–2.3), and 0.25% VMD (0.08–0.59). From these results, Antibiogo was validated for 11 WHO priority pathogens. From an operational need identified, to proof of concept and evaluation, it became the first MSF CE-marked in-vitro diagnostic (IVD) test in May 2022. As of January 2024, it has been implemented in five MSF laboratories (in Central African Republic, Democratic Republic of the Congo, Jordan, Mali, and Yemen), and in public laboratories in Mali upon request from the Ministry of Health.
CONCLUSION
It will take 400 years to address the shortfall of microbiologists in LMIC at the present rate of training. In the meantime, technology can help fill the gap. In parallel to deployment of Antibiogo in additional countries and regions, developments are ongoing, and an improved version of the app will be released in 2024.
Antimicrobial resistance (AMR) is a major threat to public health and could cause 10 million deaths per year by 2050. Access to high-quality diagnostic tests is a key intervention to tackle AMR, leading to better patient care, provision of data for global surveillance, and more rational use of antibiotics. Despite technological advances, antimicrobial susceptibility testing (AST) interpretation is complex and requires expert clinical microbiologists, which are lacking in low- and middle-income countries (LMIC). To fill the gap, The Médecins Sans Frontières (MSF) Foundation developed Antibiogo, a smartphone-based application to support laboratory technicians with AST interpretation. We aimed to assess the clinical performance of Antibiogo in intended use settings as per European regulations for in-vitro diagnostic medical devices.
METHODS
Antibiogo combines image processing, machine learning, and expert system technologies for the provision of final results (S/I/R: Susceptible, Intermediate, or Resistant). In 2022, we assessed the clinical performance of Antibiogo according to European regulations in three microbiology laboratories in Jordan (MSF Reconstructive Surgery Hospital, Amman), Mali (MSF Paediatric Hospital, Koutiala), and Senegal (Pasteur Institute, Dakar). In each site, clinical AST performed for routine purposes was processed in parallel with Antibiogo. AST pictures and inhibition zone diameter values measured with Antibiogo were interpreted by an expert microbiologist who was masked to Antibiogo interpretation. We calculated S/I/R category agreement between the microbiologist and Antibiogo, as well as minor (mD), major (MD) and very major discrepancies (VMD).
RESULTS
We included 378 fresh isolates in the study, representing 11 different pathogens. The overall category agreement was 88.8% (95% CI 87.9–89.7), ranging per pathogen from 67.1% (63.2–70.8) (for Pseudomonas aeruginosa) to 98.1% (94.4–99.6) (for Haemophilus influenzae), with 10.2% (9.4–11.1) mD, 1.6% MD (1.2–2.3), and 0.25% VMD (0.08–0.59). From these results, Antibiogo was validated for 11 WHO priority pathogens. From an operational need identified, to proof of concept and evaluation, it became the first MSF CE-marked in-vitro diagnostic (IVD) test in May 2022. As of January 2024, it has been implemented in five MSF laboratories (in Central African Republic, Democratic Republic of the Congo, Jordan, Mali, and Yemen), and in public laboratories in Mali upon request from the Ministry of Health.
CONCLUSION
It will take 400 years to address the shortfall of microbiologists in LMIC at the present rate of training. In the meantime, technology can help fill the gap. In parallel to deployment of Antibiogo in additional countries and regions, developments are ongoing, and an improved version of the app will be released in 2024.
Conference Material > Video
Malou N
MSF Scientific Day International 2024. 16 May 2024; DOI:10.57740/FYVqmt4gsw
Journal Article > ResearchFull Text
PLOS Glob Public Health. 5 January 2023; Volume 3 (Issue 1); e0001316.; DOI:10.1371/journal.pgph.0001316
Temessadouno FW, Ndong JG, Gignoux EM, Coppieters Y, Ba A, et al.
PLOS Glob Public Health. 5 January 2023; Volume 3 (Issue 1); e0001316.; DOI:10.1371/journal.pgph.0001316
Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is the virus associated with coronavirus disease (COVID-19). At the time of the study, little data on the level of exposure of the population in Koutiala district in Mali to SARS-CoV-2 was available. Although blood donors are not representative of the general population, a COVID-19 seroprevalence estimate in this population was intended to assess the extent of community transmission, serve as a health alert system, and help guide the public health response. We measured seroprevalence of anti-SARS-CoV-2 antibodies using NG-Biotech SARS-Cov-2 RDT and ECLIA test between January and June 2020. This is a cross-sectional study of volunteer blood donors aged 18 to 60 years, independent of any previous COVID-19 disease. A stratified analysis of seroprevalence by month of sample collection and a comparison of the results of the NG-Biotech SARS-Cov-2 RDT with those of the ECLIA test was performed. The overall prevalence of antibodies to SARS-Cov-2 virus assessed by the NG-Biotech SARS-Cov-2 RDT was 24.6% (95% CI 21.8–27.4) and by the ECLIA test was 70.2 (95% CI 64.9–75.5). Both estimates remained relatively stable over the study period. We observed SARS-CoV-2 exposure much higher than indicated by case-based surveillance. The national surveillance system, as it was, was not able to detect variations in incidence, and as such, we do not recommend it as an alert system. However, the discrepancy between the results of the rapid test and the ECLIA test shows that further research is required to assess the validity of these test before a more solid conclusion can be drawn it their use in surveillance.
Journal Article > ResearchFull Text
PLOS Glob Public Health. 9 November 2022; Volume 2 (Issue 11); e0000767.; DOI:10.1371/journal.pgph.0000767
Malaeb R, Yousef N, Al-Nagdah O, Ali QH, Saeed MAS, et al.
PLOS Glob Public Health. 9 November 2022; Volume 2 (Issue 11); e0000767.; DOI:10.1371/journal.pgph.0000767
The true burden of COVID-19 in Yemen is underestimated. The healthcare system is dysfunctional and there is a high shortage of health care workers in the country. Testing for SARS-CoV-2 remains limited and official surveillance data is restricted to those who are severe or highly suspected. In this study, Médecins Sans Frontières (MSF) aimed to conduct serological screening using rapid tests for asymptomatic staff at the MSF Aden Trauma Center to determine the SARS-CoV-2 antibody seropositivity. Four months after the peak of the first wave, we offered all the staff at the MSF Aden Trauma Center PCR if symptomatic, and a baseline SARS-CoV-2 serology screening followed by follow-up screenings. A final round was scheduled four months after the baseline. A rapid serology lateral flow test, NG-Test IgM-IgG was used in all rounds and in the final round, an electrochemiluminescence immunoassay (ECLIA) (Elecsys Anti-SARS-CoV-2 assay). Univariate and multivariate analyses were used to identify risk factors for seropositivity. The level of agreement between the different serology assays used was investigated. Overall 69 out of 356 participants (19.4%, 95% CI 17.9–20.8) tested positive by NG-Test between September and November 2020. A sub-sample of 161 staff members were retested in January 2021. Of these, the NG-Test detected only 13 positive cases, whereas the ECLIA detected 109 positive cases. The adjusted seroprevalence by ECLIA was 59% (95%CI 52.2–65.9). The non-medical staff had significantly lower odds of seropositivity compared to the medical staff (AOR 0.43, 95% CI 0.15–0.7, p<0.001). The positive percent agreement between the two tests was very low (11%). Our results suggest a very high SARS-CoV-2 seroprevalence in healthcare workers in Yemen, highlighting the need for regular testing and rapid vaccination of all healthcare workers in the country.
Journal Article > ResearchFull Text
Nat Commun. 19 February 2021; Volume 12 (Issue 1); DOI:10.1038/s41467-021-21187-3
Pascucci M, Royer G, Adamek J, Al Asmar M, Aristizabal D, et al.
Nat Commun. 19 February 2021; Volume 12 (Issue 1); DOI:10.1038/s41467-021-21187-3
Antimicrobial resistance is a major global health threat and its development is promoted by antibiotic misuse. While disk diffusion antibiotic susceptibility testing (AST, also called antibiogram) is broadly used to test for antibiotic resistance in bacterial infections, it faces strong criticism because of inter-operator variability and the complexity of interpretative reading. Automatic reading systems address these issues, but are not always adapted or available to resource-limited settings. We present an artificial intelligence (AI)-based, offline smartphone application for antibiogram analysis. The application captures images with the phone's camera, and the user is guided throughout the analysis on the same device by a user-friendly graphical interface. An embedded expert system validates the coherence of the antibiogram data and provides interpreted results. The fully automatic measurement procedure of our application's reading system achieves an overall agreement of 90% on susceptibility categorization against a hospital-standard automatic system and 98% against manual measurement (gold standard), with reduced inter-operator variability. The application's performance showed that the automatic reading of antibiotic resistance testing is entirely feasible on a smartphone. Moreover our application is suited for resource-limited settings, and therefore has the potential to significantly increase patients' access to AST worldwide.
Journal Article > ResearchFull Text
Journal of the American Medical Association (JAMA). 2 August 2019; Volume 2 (Issue 8); DOI:10.1001/jamanetworkopen.2019.9118
Lenglet AD, van Deursen B, Viana R, Abubakar N, Hoare S, et al.
Journal of the American Medical Association (JAMA). 2 August 2019; Volume 2 (Issue 8); DOI:10.1001/jamanetworkopen.2019.9118
IMPORTANCE
Hand hygiene adherence monitoring and feedback can reduce health care-acquired infections in hospitals. Few low-cost hand hygiene adherence monitoring tools exist in low-resource settings.
OBJECTIVE
To pilot an open-source application for mobile devices and an interactive analytical dashboard for the collection and visualization of health care workers' hand hygiene adherence data.
DESIGN, SETTING, AND PARTICIPANTS
This prospective multicenter quality improvement study evaluated preintervention and postintervention adherence with the 5 Moments for Hand Hygiene, as suggested by the World Health Organization, among health care workers from April 23 to May 25, 2018. A novel data collection form, the Hand Hygiene Observation Tool, was developed in open-source software and used to measure adherence with hand hygiene guidelines among health care workers in the inpatient therapeutic feeding center and pediatric ward of Anka General Hospital, Anka, Nigeria, and the postoperative ward of Noma Children's Hospital, Sokoto, Nigeria. Qualitative data were analyzed throughout data collection and used for immediate feedback to staff. A more formal analysis of the data was conducted during October 2018.
EXPOSURES
Multimodal hand hygiene improvement strategy with increased availability and accessibility of alcohol-based hand sanitizer, staff training and education, and evaluation and feedback in near real-time.
MAIN OUTCOMES AND MEASURES
Hand hygiene adherence before and after the intervention in 3 hospital wards, stratified by health care worker role, ward, and moment of hand hygiene.
RESULTS
A total of 686 preintervention adherence observations and 673 postintervention adherence observations were conducted. After the intervention, overall hand hygiene adherence increased from 32.4% to 57.4%. Adherence increased in both wards in Anka General Hospital (inpatient therapeutic feeding center, 24.3% [54 of 222 moments] to 63.7% [163 of 256 moments]; P < .001; pediatric ward, 50.9% [132 of 259 moments] to 68.8% [135 of 196 moments]; P < .001). Adherence among nurses in Anka General Hospital also increased in both wards (inpatient therapeutic feeding center, 17.7% [28 of 158 moments] to 71.2% [79 of 111 moments]; P < .001; pediatric ward, 45.9% [68 of 148 moments] to 68.4% [78 of 114 moments]; P < .001). In Noma Children's Hospital, the overall adherence increased from 17.6% (36 of 205 moments) to 39.8% (88 of 221 moments) (P < .001). Adherence among nurses in Noma Children's Hospital increased from 11.5% (14 of 122 moments) to 61.4% (78 of 126 moments) (P < .001). Adherence among Noma Children's Hospital physicians decreased from 34.2% (13 of 38 moments) to 8.6% (7 of 81 moments). Lowest overall adherence after the intervention occurred before patient contact (53.1% [85 of 160 moments]), before aseptic procedure (58.3% [21 of 36 moments]), and after touching a patient's surroundings (47.1% [124 of 263 moments]).
CONCLUSIONS AND RELEVANCE
This study suggests that tools for the collection and rapid visualization of hand hygiene adherence data are feasible in low-resource settings. The novel tool used in this study may contribute to comprehensive infection prevention and control strategies and strengthening of hand hygiene behavior among all health care workers in health care facilities in humanitarian and low-resource settings.
Hand hygiene adherence monitoring and feedback can reduce health care-acquired infections in hospitals. Few low-cost hand hygiene adherence monitoring tools exist in low-resource settings.
OBJECTIVE
To pilot an open-source application for mobile devices and an interactive analytical dashboard for the collection and visualization of health care workers' hand hygiene adherence data.
DESIGN, SETTING, AND PARTICIPANTS
This prospective multicenter quality improvement study evaluated preintervention and postintervention adherence with the 5 Moments for Hand Hygiene, as suggested by the World Health Organization, among health care workers from April 23 to May 25, 2018. A novel data collection form, the Hand Hygiene Observation Tool, was developed in open-source software and used to measure adherence with hand hygiene guidelines among health care workers in the inpatient therapeutic feeding center and pediatric ward of Anka General Hospital, Anka, Nigeria, and the postoperative ward of Noma Children's Hospital, Sokoto, Nigeria. Qualitative data were analyzed throughout data collection and used for immediate feedback to staff. A more formal analysis of the data was conducted during October 2018.
EXPOSURES
Multimodal hand hygiene improvement strategy with increased availability and accessibility of alcohol-based hand sanitizer, staff training and education, and evaluation and feedback in near real-time.
MAIN OUTCOMES AND MEASURES
Hand hygiene adherence before and after the intervention in 3 hospital wards, stratified by health care worker role, ward, and moment of hand hygiene.
RESULTS
A total of 686 preintervention adherence observations and 673 postintervention adherence observations were conducted. After the intervention, overall hand hygiene adherence increased from 32.4% to 57.4%. Adherence increased in both wards in Anka General Hospital (inpatient therapeutic feeding center, 24.3% [54 of 222 moments] to 63.7% [163 of 256 moments]; P < .001; pediatric ward, 50.9% [132 of 259 moments] to 68.8% [135 of 196 moments]; P < .001). Adherence among nurses in Anka General Hospital also increased in both wards (inpatient therapeutic feeding center, 17.7% [28 of 158 moments] to 71.2% [79 of 111 moments]; P < .001; pediatric ward, 45.9% [68 of 148 moments] to 68.4% [78 of 114 moments]; P < .001). In Noma Children's Hospital, the overall adherence increased from 17.6% (36 of 205 moments) to 39.8% (88 of 221 moments) (P < .001). Adherence among nurses in Noma Children's Hospital increased from 11.5% (14 of 122 moments) to 61.4% (78 of 126 moments) (P < .001). Adherence among Noma Children's Hospital physicians decreased from 34.2% (13 of 38 moments) to 8.6% (7 of 81 moments). Lowest overall adherence after the intervention occurred before patient contact (53.1% [85 of 160 moments]), before aseptic procedure (58.3% [21 of 36 moments]), and after touching a patient's surroundings (47.1% [124 of 263 moments]).
CONCLUSIONS AND RELEVANCE
This study suggests that tools for the collection and rapid visualization of hand hygiene adherence data are feasible in low-resource settings. The novel tool used in this study may contribute to comprehensive infection prevention and control strategies and strengthening of hand hygiene behavior among all health care workers in health care facilities in humanitarian and low-resource settings.
Conference Material > Video
Malou N
MSF Scientific Days International 2021: Innovation. 20 May 2021