1
|
Imdad A, Rogner J, Sherwani RN, Sidhu J, Regan A, Haykal MR, Tsistinas O, Smith A, Chan XHS, Mayo-Wilson E, Bhutta ZA. Zinc supplementation for preventing mortality, morbidity, and growth failure in children aged 6 months to 12 years. Cochrane Database Syst Rev 2023; 3:CD009384. [PMID: 36994923 PMCID: PMC10061962 DOI: 10.1002/14651858.cd009384.pub3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 03/31/2023]
Abstract
BACKGROUND Zinc deficiency is prevalent in low- and middle-income countries, and is considered a significant risk factor for morbidity, mortality, and linear growth failure. The effectiveness of preventive zinc supplementation in reducing prevalence of zinc deficiency needs to be assessed. OBJECTIVES To assess the effects of zinc supplementation for preventing mortality and morbidity, and for promoting growth, in children aged 6 months to 12 years. SEARCH METHODS A previous version of this review was published in 2014. In this update, we searched CENTRAL, MEDLINE, Embase, five other databases, and one trials register up to February 2022, together with reference checking and contact with study authors to identify additional studies. SELECTION CRITERIA Randomized controlled trials (RCTs) of preventive zinc supplementation in children aged 6 months to 12 years compared with no intervention, a placebo, or a waiting list control. We excluded hospitalized children and children with chronic diseases or conditions. We excluded food fortification or intake, sprinkles, and therapeutic interventions. DATA COLLECTION AND ANALYSIS Two review authors screened studies, extracted data, and assessed the risk of bias. We contacted study authors for missing information and used GRADE to assess the certainty of evidence. The primary outcomes of this review were all-cause mortality; and cause-specific mortality, due to all-cause diarrhea, lower respiratory tract infection (LRTI, including pneumonia), and malaria. We also collected information on a number of secondary outcomes, such as those related to diarrhea and LRTI morbidity, growth outcomes and serum levels of micronutrients, and adverse events. MAIN RESULTS We included 16 new studies in this review, resulting in a total of 96 RCTs with 219,584 eligible participants. The included studies were conducted in 34 countries; 87 of them in low- or middle-income countries. Most of the children included in this review were under five years of age. The intervention was delivered most commonly in the form of syrup as zinc sulfate, and the most common dose was between 10 mg and 15 mg daily. The median duration of follow-up was 26 weeks. We did not consider that the evidence for the key analyses of morbidity and mortality outcomes was affected by risk of bias. High-certainty evidence showed little to no difference in all-cause mortality with preventive zinc supplementation compared to no zinc (risk ratio (RR) 0.93, 95% confidence interval (CI) 0.84 to 1.03; 16 studies, 17 comparisons, 143,474 participants). Moderate-certainty evidence showed that preventive zinc supplementation compared to no zinc likely results in little to no difference in mortality due to all-cause diarrhea (RR 0.95, 95% CI 0.69 to 1.31; 4 studies, 132,321 participants); but probably reduces mortality due to LRTI (RR 0.86, 95% CI 0.64 to 1.15; 3 studies, 132,063 participants) and mortality due to malaria (RR 0.90, 95% CI 0.77 to 1.06; 2 studies, 42,818 participants); however, the confidence intervals around the summary estimates for these outcomes were wide, and we could not rule out a possibility of increased risk of mortality. Preventive zinc supplementation likely reduces the incidence of all-cause diarrhea (RR 0.91, 95% CI 0.90 to 0.93; 39 studies, 19,468 participants; moderate-certainty evidence) but results in little to no difference in morbidity due to LRTI (RR 1.01, 95% CI 0.95 to 1.08; 19 studies, 10,555 participants; high-certainty evidence) compared to no zinc. There was moderate-certainty evidence that preventive zinc supplementation likely leads to a slight increase in height (standardized mean difference (SMD) 0.12, 95% CI 0.09 to 0.14; 74 studies, 20,720 participants). Zinc supplementation was associated with an increase in the number of participants with at least one vomiting episode (RR 1.29, 95% CI 1.14 to 1.46; 5 studies, 35,192 participants; high-certainty evidence). We report a number of other outcomes, including the effect of zinc supplementation on weight and serum markers such as zinc, hemoglobin, iron, copper, etc. We also performed a number of subgroup analyses and there was a consistent finding for a number of outcomes that co-supplementation of zinc with iron decreased the beneficial effect of zinc. AUTHORS' CONCLUSIONS Even though we included 16 new studies in this update, the overall conclusions of the review remain unchanged. Zinc supplementation might help prevent episodes of diarrhea and improve growth slightly, particularly in children aged 6 months to 12 years of age. The benefits of preventive zinc supplementation may outweigh the harms in regions where the risk of zinc deficiency is relatively high.
Collapse
Affiliation(s)
- Aamer Imdad
- Department of Pediatrics, SUNY Upstate Medical University, Syracuse, NY, USA
| | - Jaimie Rogner
- Departments of Medicine and Pediatrics, University of Rochester Medical Center, Rochester, NY, USA
| | - Rida N Sherwani
- Department of Pediatrics, SUNY Upstate Medical University, Syracuse, NY, USA
| | - Jasleen Sidhu
- Norton College of Medicine, SUNY Upstate Medical University, Syracuse, NY, USA
| | - Allison Regan
- Norton College of Medicine, SUNY Upstate Medical University, Syracuse, NY, USA
| | - Maya R Haykal
- Norton College of Medicine, SUNY Upstate Medical University, Syracuse, NY, USA
| | - Olivia Tsistinas
- Health Sciences Library, SUNY Upstate Medical University, Syracuse, NY, USA
| | - Abigail Smith
- Health Sciences Library, SUNY Upstate Medical University, Syracuse, NY, USA
| | - Xin Hui S Chan
- Pandemic Sciences Institute, University of Oxford, Oxford, UK
| | - Evan Mayo-Wilson
- Department of Epidemiology, UNC Gillings School of Global Public HealthMcGavran-Greenberg Hall, Chapel Hill, NC, USA
| | - Zulfiqar A Bhutta
- Centre for Global Child Health, The Hospital for SickKids, Toronto, Canada
- Center of Excellence for Women and Child Health, Aga Khan University, Karachi, Pakistan
| |
Collapse
|
2
|
Saha P, Mell B, Golonka RM, Bovilla VR, Abokor AA, Mei X, Yeoh BS, Doris PA, Gewirtz AT, Joe B, Vijay-Kumar M. Selective IgA Deficiency in Spontaneously Hypertensive Rats With Gut Dysbiosis. Hypertension 2022; 79:2239-2249. [PMID: 35950503 PMCID: PMC9458624 DOI: 10.1161/hypertensionaha.122.19307] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/08/2022] [Accepted: 07/07/2022] [Indexed: 12/11/2022]
Abstract
BACKGROUND The spontaneously hypertensive rat (SHR) is extensively used to study hypertension. Gut microbiota dysbiosis is a notable feature in SHR for reasons unknown. Immunoglobulin A (IgA) is a major host factor required for gut microbiota homeostasis. We hypothesized that inadequate IgA contributes to gut microbiota dysbiosis in SHR. METHODS IgA was measured in feces, cecum, serum, liver, gut-associated lymphoid tissue, and milk from SHR and Wistar Kyoto rats. IgA regulatory factors like IgM, IgG, and pIgR (polymeric immunoglobulin receptor) were analyzed. IgA and IgG antibodies and blood pressure (BP) were measured before and after administrating a bacterial antigen (ie, flagellin). RESULTS Compared with Wistar Kyoto rats, SHR displayed remarkably near-deficient IgA levels accompanied by compensatory increases in serum IgM and IgG and gut-liver pIgR expression. Inadequate milk IgA in SHR emphasized this immune defect stemmed from the neonatal stage. Reduced IgA+ B cells in circulation and Peyer patches indicated a possible reason for the lower IgA in SHR. Noteworthy, a genetic insufficiency was unlikely because administering flagellin to SHR induced anti-flagellin IgA antibodies. This immune response surprisingly accelerated hypertension development in SHR, suggesting IgA quiescence may help maintain lower BP. CONCLUSIONS This study is the first to reveal IgA deficiency in SHR as one host factor associated with gut microbiota dysbiosis and invigorates future research to determine the pathophysiological role of IgA in hypertension.
Collapse
Affiliation(s)
- Piu Saha
- UT Microbiome Consortium, Center for Hypertension and Precision Medicine, Department of Physiology & Pharmacology, University of Toledo College of Medicine and Life Sciences, Toledo, OH 43614, USA
| | - Blair Mell
- UT Microbiome Consortium, Center for Hypertension and Precision Medicine, Department of Physiology & Pharmacology, University of Toledo College of Medicine and Life Sciences, Toledo, OH 43614, USA
| | - Rachel M. Golonka
- UT Microbiome Consortium, Center for Hypertension and Precision Medicine, Department of Physiology & Pharmacology, University of Toledo College of Medicine and Life Sciences, Toledo, OH 43614, USA
| | - Venugopal R. Bovilla
- UT Microbiome Consortium, Center for Hypertension and Precision Medicine, Department of Physiology & Pharmacology, University of Toledo College of Medicine and Life Sciences, Toledo, OH 43614, USA
| | - Ahmed A. Abokor
- UT Microbiome Consortium, Center for Hypertension and Precision Medicine, Department of Physiology & Pharmacology, University of Toledo College of Medicine and Life Sciences, Toledo, OH 43614, USA
| | - Xue Mei
- UT Microbiome Consortium, Center for Hypertension and Precision Medicine, Department of Physiology & Pharmacology, University of Toledo College of Medicine and Life Sciences, Toledo, OH 43614, USA
| | - Beng San Yeoh
- UT Microbiome Consortium, Center for Hypertension and Precision Medicine, Department of Physiology & Pharmacology, University of Toledo College of Medicine and Life Sciences, Toledo, OH 43614, USA
| | - Peter A. Doris
- Brown Foundation Institute of Molecular Medicine, University of Texas McGovern Medical School, Houston, TX 77030, USA
| | - Andrew T. Gewirtz
- Center for Inflammation, Immunity and Infection, Institute for Biomedical Sciences, Georgia State University, Atlanta, GA 30303, USA
| | - Bina Joe
- UT Microbiome Consortium, Center for Hypertension and Precision Medicine, Department of Physiology & Pharmacology, University of Toledo College of Medicine and Life Sciences, Toledo, OH 43614, USA
| | - Matam Vijay-Kumar
- UT Microbiome Consortium, Center for Hypertension and Precision Medicine, Department of Physiology & Pharmacology, University of Toledo College of Medicine and Life Sciences, Toledo, OH 43614, USA
| |
Collapse
|
3
|
Danquah FI, Ansu-Mensah M, Bawontuo V, Yeboah M, Kuupiel D. Prevalence, incidence, and trends of childhood overweight/obesity in Sub-Saharan Africa: a systematic scoping review. Arch Public Health 2020; 78:109. [PMID: 33292679 PMCID: PMC7599109 DOI: 10.1186/s13690-020-00491-2] [Citation(s) in RCA: 20] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/12/2020] [Accepted: 10/20/2020] [Indexed: 02/08/2023] Open
Abstract
BACKGROUND The growing burden of non-communicable diseases (NDC), particularly in low-and middle-income countries, poses a significant threat to global health. Obesity and overweight constitute major risk factors of NCDs such as heart diseases, diabetes, and kidney disease, and as a result, contribute significantly to the development of chronic morbidities, reduced quality of life, and increased risk of premature death. This study described evidence on the prevalence, incidence, and trends of childhood overweight and obesity in sub-Sahara Africa (SSA). METHODS We conducted a systematic scoping review employing the Arksey and O'Malley framework, Levac et al. recommendations, and the Joanna Briggs Institute guidelines. To obtain relevant published articles for this review, we performed a comprehensive keywords search in PubMed, Google Scholar, Web of Science, and CINAHL via EBSCOhost platform for studies published between 2009 and June 2019. Guided by the eligibility criteria, title and abstracts, as well as the full-text articles were independently screened in parallel by two investigators. All relevant data were independently extracted by two investigators using a piloted form designed in Microsoft and thematic analysis conducted. RESULTS Of the 81 included studies obtained from 250,148 potentially eligible articles, the majority (25) conducted in South Africa followed by 18 in Nigeria. Six studies were conducted in Ethiopia (6), Tanzania (5), Kenya (4), Cameroon (4), Ghana (3), Uganda (2), Mozambique (2), and Sudan (2). One study each was conducted in Botswana, Gambia, Lesotho, Mauritius, Seychelles, Togo, and Zimbabwe. The remaining three articles were multi-country studies. Most (81.5%) of the included studies were cross-sectional surveys and the majority (79) focused on both male and female participants. The majority (80/81) of the included studies reported on the prevalence of childhood overweight/obesity, 8 on the trends of childhood overweight/obesity, and one presented evidence on the incidence of childhood overweight and obesity in SSA. CONCLUSION This review demonstrates limited studies on childhood overweight/obesity in most SSA countries although the included studies suggest an increasing burden. Considering the consequences of childhood obesity, there is a need for more primary researches to inform policies decision and implementation to halt the rise of childhood obesity/overweight in SSA.
Collapse
Affiliation(s)
- Frederick Inkum Danquah
- Department of Public Health, Faculty of Health and Allied Sciences, Catholic University College of Ghana, Fiapre, Sunyani, Ghana
| | - Monica Ansu-Mensah
- Department of Public Health, Faculty of Health and Allied Sciences, Catholic University College of Ghana, Fiapre, Sunyani, Ghana
| | - Vitalis Bawontuo
- Department of Public Health, Faculty of Health and Allied Sciences, Catholic University College of Ghana, Fiapre, Sunyani, Ghana
- Research for Sustainable Development Consult, Sunyani, Ghana
| | - Matilda Yeboah
- Department of Public Health, Faculty of Health and Allied Sciences, Catholic University College of Ghana, Fiapre, Sunyani, Ghana
| | - Desmond Kuupiel
- Department of Public Health, Faculty of Health and Allied Sciences, Catholic University College of Ghana, Fiapre, Sunyani, Ghana
- Research for Sustainable Development Consult, Sunyani, Ghana
- Department of Public Health Medicine, School of Nursing and Public Health, University of KwaZulu-Natal, Durban, 4001 South Africa
| |
Collapse
|
4
|
Lauer JM, McDonald CM, Kisenge R, Aboud S, Fawzi WW, Liu E, Tran HQ, Gewirtz AT, Manji KP, Duggan CP. Markers of Systemic Inflammation and Environmental Enteric Dysfunction Are Not Reduced by Zinc or Multivitamins in Tanzanian Infants: A Randomized, Placebo-Controlled Trial. J Pediatr 2019; 210:34-40.e1. [PMID: 30952509 PMCID: PMC6590867 DOI: 10.1016/j.jpeds.2019.02.016] [Citation(s) in RCA: 11] [Impact Index Per Article: 2.2] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 11/21/2018] [Revised: 01/30/2019] [Accepted: 02/13/2019] [Indexed: 12/30/2022]
Abstract
OBJECTIVE To examine whether daily zinc and/or multivitamin supplementation reduce biomarkers of environmental enteric dysfunction (EED), systemic inflammation, or markers of growth in a sample of infants from Dar es Salaam, Tanzania. STUDY DESIGN Subgroup analysis of infants participating in a randomized, double-blind, placebo-controlled trial received daily oral supplementation of zinc, multivitamins, zinc + multivitamins, or placebo for 18 months starting at 6 weeks of age. EED (anti-flagellin and anti-lipopolysaccharide immunoglobulins), systemic inflammation (C-reactive protein and alpha-1-acid glycoprotein), and growth biomarkers (insulin-like growth factor-1 and insulin-like growth factor binding protein-3) were measured via enzyme-linked immunosorbent assay in a subsample of 590 infants at 6 weeks and 6 months of age. EED biomarkers also were measured in 162 infants at 12 months of age. RESULTS With the exception of anti-lipopolysaccharide IgG concentrations, which were significantly greater in infants who received multivitamins compared with those who did not (1.41 ± 0.61 vs 1.26 ± 0.65, P = .006), and insulin-like growth factor binding protein-3 concentrations, which were significantly lower in children who received zinc compared with those who did not (981.13 ± 297.59 vs 1019.10 ± 333.01, P = .03), at 6 months of age, we did not observe any significant treatment effects of zinc or multivitamins on EED, systemic inflammation, or growth biomarkers. CONCLUSIONS Neither zinc nor multivitamin supplementation ameliorated markers of EED or systemic inflammation during infancy. Other interventions should be prioritized for future trials. TRIAL REGISTRATION Clinicaltrials.gov: NCT00421668.
Collapse
Affiliation(s)
- Jacqueline M Lauer
- Division of Gastroenterology, Hepatology and Nutrition, Boston Children's Hospital, Boston, MA.
| | | | - Rodrick Kisenge
- Department of Pediatrics and Child Health, Muhimbili University of Health and Allied Sciences, Dar es Salaam, Tanzania
| | - Said Aboud
- Department of Microbiology and Immunology, Muhimbili University of Health and Allied Sciences, Dar es Salaam, Tanzania
| | - Wafaie W Fawzi
- Department of Global Health and Population, Harvard T.H. Chan School of Public Health, Boston, MA; Department of Epidemiology, Harvard T.H. Chan School of Public Health, Boston, MA; Department of Nutrition, Harvard T.H. Chan School of Public Health, Boston, MA
| | - Enju Liu
- Division of Gastroenterology, Hepatology and Nutrition, Boston Children's Hospital, Boston, MA; Institutional Centers of Clinical and Translational Research, Boston Children's Hospital, Boston, MA
| | - Hao Q Tran
- Institute for Biomedical Sciences, Georgia State University, Atlanta, GA
| | - Andrew T Gewirtz
- Institute for Biomedical Sciences, Georgia State University, Atlanta, GA
| | - Karim P Manji
- Department of Pediatrics and Child Health, Muhimbili University of Health and Allied Sciences, Dar es Salaam, Tanzania
| | - Christopher P Duggan
- Division of Gastroenterology, Hepatology and Nutrition, Boston Children's Hospital, Boston, MA; Department of Pediatrics and Child Health, Muhimbili University of Health and Allied Sciences, Dar es Salaam, Tanzania; Department of Global Health and Population, Harvard T.H. Chan School of Public Health, Boston, MA; Department of Nutrition, Harvard T.H. Chan School of Public Health, Boston, MA
| |
Collapse
|
5
|
Richard SA, McCormick BJJ, Murray-Kolb LE, Lee GO, Seidman JC, Mahfuz M, Ahmed T, Guerrant RL, Petri WA, Rogawski ET, Houpt E, Kang G, Mduma E, Kosek MN, Lima AAM, Shrestha SK, Chandyo RK, Bhutta Z, Bessong P, Caulfield LE. Enteric dysfunction and other factors associated with attained size at 5 years: MAL-ED birth cohort study findings. Am J Clin Nutr 2019; 110:131-138. [PMID: 31127812 PMCID: PMC6599740 DOI: 10.1093/ajcn/nqz004] [Citation(s) in RCA: 24] [Impact Index Per Article: 4.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/20/2018] [Accepted: 01/07/2019] [Indexed: 01/06/2023] Open
Abstract
BACKGROUND Poor growth in early childhood has been associated with increased risk of mortality and morbidity, as well as long-term deficits in cognitive development and economic productivity. OBJECTIVES Data from the MAL-ED cohort study were used to identify factors in the first 2 y of life that are associated with height-for-age, weight-for-age, and body mass index z-scores (HAZ, WAZ, BMIZ) at 5 y of age. METHODS A total of 1017 children were followed from near birth until 5 y of age at sites in Bangladesh, Brazil, India, Nepal, Peru, South Africa, and Tanzania. Data were collected on their growth, environmental enteric dysfunction (EED), micronutrient status, enteric pathogen burden, illness prevalence, dietary intake, and various other socio-economic and environmental factors. RESULTS EED biomarkers were related to size at 5 y. Mean lactulose:mannitol z-scores during the first 2 y of life were negatively associated with all of the growth measures (HAZ: -0.11 [95% CI: -0.19, -0.03]; WAZ: -0.16 [95% CI: -0.26, -0.06]; BMIZ: -0.11 [95% CI: -0.23, 0.0]). Myeloperoxidase was negatively associated with weight (WAZ: -0.52 [95% CI: -0.78, -0.26] and BMIZ: -0.56 [95% CI: -0.86, -0.26]); whereas α-1-antitrypsin had a negative association with HAZ (-0.28 [95% CI: -0.52, -0.04]). Transferrin receptor was positively related to HAZ (0.18 [95% CI: 0.06, 0.30]) and WAZ (0.21 [95% CI: 0.07, 0.35]). Hemoglobin was positively related to HAZ (0.06 [95% CI: 0.00, 0.12]), and ferritin was negatively related to HAZ (-0.08 [95% CI: -0.12, -0.04]). Bacterial density in stool was negatively associated with HAZ (-0.04 [95% CI: -0.08, 0.00]), but illness symptoms did not have any effect on size at 5 y. CONCLUSIONS EED markers, bacterial density, and iron markers are associated with growth at 5 y of age. Interventions to reduce bacterial burden and EED may improve long-term growth in low-income settings.
Collapse
Affiliation(s)
| | | | | | - Gwyneth O Lee
- The Johns Hopkins University, Baltimore, MD,Present address for GOL: University of Michigan, Ann Arbor, MI
| | | | - Mustafa Mahfuz
- International Centre for Diarrhoeal Disease Research, Bangladesh (icddr,b), Dhaka, Bangladesh
| | - Tahmeed Ahmed
- International Centre for Diarrhoeal Disease Research, Bangladesh (icddr,b), Dhaka, Bangladesh
| | | | - William A Petri
- University of Virginia, School of Medicine, Charlottesville, VA
| | | | - Eric Houpt
- University of Virginia, School of Medicine, Charlottesville, VA
| | - Gagandeep Kang
- Christian Medical College, Division of Gastrointestinal Sciences, Vellore, Tamil Nadu, India
| | | | | | - Aldo A M Lima
- Universidade Federal do Ceará, INCT—Instituto de Biomedicina do Semiárido Brasileiro, Fortaleza, Brazil
| | - Sanjaya K Shrestha
- Walter Reed Armed Forces Research Institute of Medical Sciences (AFRIMS) Research Unit (WARUN), Kathmandu, Nepal
| | - Ram K Chandyo
- Institute of Medicine, Tribhuvan University, Kathmandu, Nepal,Present address for RKC: Kathmandu Medical College, Kathmandu, Nepal
| | - Zulfiqar Bhutta
- Aga Khan University, Centre of Excellence in Women and Child Health, Karachi, Pakistan,Present address for ZB: University of Toronto, Toronto, Canada
| | | | - Laura E Caulfield
- The Johns Hopkins University, Baltimore, MD,Address correspondence to LEC (e-mail: )
| | | |
Collapse
|
6
|
Syed S, Al-Boni M, Khan MN, Sadiq K, Iqbal NT, Moskaluk CA, Kelly P, Amadi B, Ali SA, Moore SR, Brown DE. Assessment of Machine Learning Detection of Environmental Enteropathy and Celiac Disease in Children. JAMA Netw Open 2019; 2:e195822. [PMID: 31199451 PMCID: PMC6575155 DOI: 10.1001/jamanetworkopen.2019.5822] [Citation(s) in RCA: 22] [Impact Index Per Article: 4.4] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/17/2019] [Accepted: 04/30/2019] [Indexed: 12/16/2022] Open
Abstract
Importance Duodenal biopsies from children with enteropathies associated with undernutrition, such as environmental enteropathy (EE) and celiac disease (CD), display significant histopathological overlap. Objective To develop a convolutional neural network (CNN) to enhance the detection of pathologic morphological features in diseased vs healthy duodenal tissue. Design, Setting, and Participants In this prospective diagnostic study, a CNN consisting of 4 convolutions, 1 fully connected layer, and 1 softmax layer was trained on duodenal biopsy images. Data were provided by 3 sites: Aga Khan University Hospital, Karachi, Pakistan; University Teaching Hospital, Lusaka, Zambia; and University of Virginia, Charlottesville. Duodenal biopsy slides from 102 children (10 with EE from Aga Khan University Hospital, 16 with EE from University Teaching Hospital, 34 with CD from University of Virginia, and 42 with no disease from University of Virginia) were converted into 3118 images. The CNN was designed and analyzed at the University of Virginia. The data were collected, prepared, and analyzed between November 2017 and February 2018. Main Outcomes and Measures Classification accuracy of the CNN per image and per case and incorrect classification rate identified by aggregated 10-fold cross-validation confusion/error matrices of CNN models. Results Overall, 102 children participated in this study, with a median (interquartile range) age of 31.0 (20.3-75.5) months and a roughly equal sex distribution, with 53 boys (51.9%). The model demonstrated 93.4% case-detection accuracy and had a false-negative rate of 2.4%. Confusion metrics indicated most incorrect classifications were between patients with CD and healthy patients. Feature map activations were visualized and learned distinctive patterns, including microlevel features in duodenal tissues, such as alterations in secretory cell populations. Conclusions and Relevance A machine learning-based histopathological analysis model demonstrating 93.4% classification accuracy was developed for identifying and differentiating between duodenal biopsies from children with EE and CD. The combination of the CNN with a deconvolutional network enabled feature recognition and highlighted secretory cells' role in the model's ability to differentiate between these histologically similar diseases.
Collapse
Affiliation(s)
- Sana Syed
- Division of Pediatric Gastroenterology and Hepatology, Department of Pediatrics, University of Virginia, Charlottesville
- Department of Pediatrics and Child Health, Aga Khan University, Karachi, Pakistan
| | - Mohammad Al-Boni
- Systems and Information Engineering, University of Virginia, Charlottesville
| | - Marium N. Khan
- Division of Pediatric Gastroenterology and Hepatology, Department of Pediatrics, University of Virginia, Charlottesville
| | - Kamran Sadiq
- Department of Pediatrics and Child Health, Aga Khan University, Karachi, Pakistan
| | - Najeeha T. Iqbal
- Department of Pediatrics and Child Health, Aga Khan University, Karachi, Pakistan
| | | | - Paul Kelly
- Blizard Institute, Barts and The London School of Medicine, Queen Mary University of London, London, United Kingdom
- Tropical Gastroenterology and Nutrition Group, University of Zambia School of Medicine, Lusaka, Zambia
| | - Beatrice Amadi
- Tropical Gastroenterology and Nutrition Group, University of Zambia School of Medicine, Lusaka, Zambia
| | - S. Asad Ali
- Department of Pediatrics and Child Health, Aga Khan University, Karachi, Pakistan
| | - Sean R. Moore
- Division of Pediatric Gastroenterology and Hepatology, Department of Pediatrics, University of Virginia, Charlottesville
| | - Donald E. Brown
- Data Science Institute, University of Virginia, Charlottesville
| |
Collapse
|