BackgroundDespite the availability of free routine immunizations in low- and middle-income countries, many children are not completely vaccinated, vaccinated late for age, or drop out from the course of the immunization schedule. Without the technology to model and visualize risk of large datasets, vaccinators and policy makers are unable to identify target groups and individuals at high risk of dropping out; thus default rates remain high, preventing universal immunization coverage. Predictive analytics algorithm leverages artificial intelligence and uses statistical modeling, machine learning, and multidimensional data mining to accurately identify children who are most likely to delay or miss their follow-up immunization visits.ObjectiveThis study aimed to conduct feasibility testing and validation of a predictive analytics algorithm to identify the children who are likely to default on subsequent immunization visits for any vaccine included in the routine immunization schedule.MethodsThe algorithm was developed using 47,554 longitudinal immunization records, which were classified into the training and validation cohorts. Four machine learning models (random forest; recursive partitioning; support vector machines, SVMs; and C-forest) were used to generate the algorithm that predicts the likelihood of each child defaulting from the follow-up immunization visit. The following variables were used in the models as predictors of defaulting: gender of the child, language spoken at the child’s house, place of residence of the child (town or city), enrollment vaccine, timeliness of vaccination, enrolling staff (vaccinator or others), date of birth (accurate or estimated), and age group of the child. The models were encapsulated in the predictive engine, which identified the most appropriate method to use in a given case. Each of the models was assessed in terms of accuracy, precision (positive predictive value), sensitivity, specificity and negative predictive value, and area under the curve (AUC).ResultsOut of 11,889 cases in the validation dataset, the random forest model correctly predicted 8994 cases, yielding 94.9% sensitivity and 54.9% specificity. The C-forest model, SVMs, and recursive partitioning models improved prediction by achieving 352, 376, and 389 correctly predicted cases, respectively, above the predictions made by the random forest model. All models had a C-statistic of 0.750 or above, whereas the highest statistic (AUC 0.791, 95% CI 0.784-0.798) was observed in the recursive partitioning algorithm.ConclusionsThis feasibility study demonstrates that predictive analytics can accurately identify children who are at a higher risk for defaulting on follow-up immunization visits. Correct identification of potential defaulters opens a window for evidence-based targeted interventions in resource limited settings to achieve optimal immunization coverage and timeliness.
Background: Despite free access to vaccines through the Expanded Program on Immunization (EPI) in Pakistan, only 54% of children receive all basic vaccinations. The global success of mobile health (mHealth) technologies, particularly, Digital immunization registries (DIRs), offers immense potential for comprehensive improvement in immunization programs. In 2012, we developed and piloted Zindagi Mehfooz (Safe Life; ZM) Digital Immunization Registry, an Android phone-based platform that enables vaccinators to digitally enroll and track the immunization status of their catchment population while allowing real-time access to data and easy generation of monitoring reports. Leveraging cutting edge mHealth technology, ZM includes features such as identification through quick response barcodes, interactive SMS reminders, decision support systems for routine/catch-up immunizations, real-time workforce tracking, predictive analytics for identifying high-risk children and customized report generation for monitoring. In 2017, ZM was scaled up, in collaboration with EPI, across the entire Sindh province and is currently being used by 1589 government vaccinators in 1296 basic health facilities. Objective: We evaluated the ZM Registry in terms of improvement in immunization coverage and timeliness. The primary outcome of interest was fully immunized child (FIC) coverage in children under 2 years of age, ie, a child who has received one dose of Bacillus-Calmette-Guérin (BCG), three doses each of OPV and Pentavalent immunizations, and one dose of Measles vaccine. The secondary outcomes of interest included the Pentavalent-3 coverage rate and dropout rate between BCG and Measles-1 vaccine. Methods: The provincial scale-up commenced in October 2017, and as of July 2018, over 700,000 children between 0-2 years have been enrolled in the Registry. At enrollment, the caretaker's information, child's bio-data, and immunization history are recorded and a unique Quick Response (QR)-code sticker is provided for identification. For the follow-up immunization visits, 3 SMS reminders are sent to parents for each vaccination. At the follow-up immunization, the child's history is retrieved on the phone by scanning the QR-code, and the vaccination record is updated accordingly. Data exported from the ZM DIR records was used to calculate the coverage rate for children enrolled in the Registry and the outcomes were compared with the coverage estimates from the most recent demographic survey (MICS 2014) to determine the impact of the Registry. Results: Full immunization coverage of children (12-23 months) increased significantly from 35% as reported in MICS 2014 to 45% for children enrolled in ZM. Pentavalent-3 coverage of children enrolled in the Registry showed a 7% increase (from 53% reported in MICS 2014 data to 60% for children enrolled in the Registry). The dropout rate from BCG to Measles 1 vaccine was 24% as per the MICS 2014 figures and only 4% for children enrolled in the Registry.
Commentary 306Human Vaccines & Immunotherapeutics Volume 10 Issue 2 Commentary V accination is recommended throughout life to prevent vaccinepreventable diseases and their sequel. The primary focus of vaccination programs has historically been directed to childhood immunizations. For adults, chronic diseases have been the primary focus of preventive and medical health care, though there has been increased emphasis on preventing infectious diseases. Adult vaccination coverage, however, remains low for most of the routinely recommended vaccines. Though adults are less susceptible to fall prey to traditional infectious agents, the probability of exposure to infectious agents has increased manifold owing to globalization and increasing travel opportunities both within and across the countries. Thus, there is an urgent need to address the problem of adult immunization. The adult immunization enterprise is more complex, encompassing a wide variety of vaccines and a very diverse target population. There is no coordinated public health infrastructure to support an adult immunization program as there is for children. Moreover, there is little coordination among adult healthcare providers in terms of vaccine provision. Substantial improvement in adult vaccination is needed to reduce the health consequences of vaccine-preventable diseases among adults. Routine assessment of adult patient vaccination needs, recommendation, and offer of needed vaccines for adults should be incorporated into routine clinical care of adults.
BACKGROUND Despite free access to vaccines through the Expanded Program on Immunization (EPI) in Pakistan, only 54% of children receive all basic vaccinations. The global success of mobile health (mHealth) technologies, particularly, Digital immunization registries (DIRs), offers immense potential for comprehensive improvement in immunization programs. In 2012, we developed and piloted Zindagi Mehfooz (Safe Life; ZM) Digital Immunization Registry, an Android phone-based platform that enables vaccinators to digitally enroll and track the immunization status of their catchment population while allowing real-time access to data and easy generation of monitoring reports. Leveraging cutting edge mHealth technology, ZM includes features such as identification through quick response barcodes, interactive SMS reminders, decision support systems for routine/catch-up immunizations, real-time workforce tracking, predictive analytics for identifying high-risk children and customized report generation for monitoring. In 2017, ZM was scaled up, in collaboration with EPI, across the entire Sindh province and is currently being used by 1589 government vaccinators in 1296 basic health facilities. OBJECTIVE We evaluated the ZM Registry in terms of improvement in immunization coverage and timeliness. The primary outcome of interest was fully immunized child (FIC) coverage in children under 2 years of age, ie, a child who has received one dose of Bacillus-Calmette-Guérin (BCG), three doses each of OPV and Pentavalent immunizations, and one dose of Measles vaccine. The secondary outcomes of interest included the Pentavalent-3 coverage rate and dropout rate between BCG and Measles-1 vaccine. METHODS The provincial scale-up commenced in October 2017, and as of July 2018, over 700,000 children between 0-2 years have been enrolled in the Registry. At enrollment, the caretaker’s information, child’s bio-data, and immunization history are recorded and a unique Quick Response (QR)-code sticker is provided for identification. For the follow-up immunization visits, 3 SMS reminders are sent to parents for each vaccination. At the follow-up immunization, the child’s history is retrieved on the phone by scanning the QR-code, and the vaccination record is updated accordingly. Data exported from the ZM DIR records was used to calculate the coverage rate for children enrolled in the Registry and the outcomes were compared with the coverage estimates from the most recent demographic survey (MICS 2014) to determine the impact of the Registry. RESULTS Full immunization coverage of children (12-23 months) increased significantly from 35% as reported in MICS 2014 to 45% for children enrolled in ZM. Pentavalent-3 coverage of children enrolled in the Registry showed a 7% increase (from 53% reported in MICS 2014 data to 60% for children enrolled in the Registry). The dropout rate from BCG to Measles 1 vaccine was 24% as per the MICS 2014 figures and only 4% for children enrolled in the Registry. CONCLUSIONS ZM demonstrates the potential of DIRs to improve immunization outcomes within low-resource settings by enabling better child tracking, efficient data monitoring and most importantly a higher retention rate for completing all the recommended immunizations. The evidence base generated through the evolution of ZM over the years has also facilitated global replication and can be leveraged to achieve universal immunization coverage in underserved regions.
Hepatitis C Virus (HCV) infection is a major cause of chronic hepatitis, cirrhosis, and hepatocellular carcinoma. Following acute infection, 20% of people eliminate the virus over weeks or months and are often asymptomatic. The remaining 80% of people will develop chronic disease, of which approximately 20% will eventually develop liver cirrhosis and 1-5% will develop liver cancer. About 150 million people are chronically infected with HCV, and more than 350,000 people die every year from hepatitis C related liver diseases. The economic cost of hepatitis C is significant both to the individual and to the society. In the United States the average lifetime cost of the disease was estimated at $33,407 USD with the cost of a liver transplant approximately $200,000 USD. PEG-IFN and ribavirin treatment is also expensive and, at an average cost of approximately GB £7000 in the UK for a treatment course, is unaffordable in developing countries. Hepatitis C, not only brings down the quality of the life of individuals but also affect progress of the nation by adding financial burden. If we prevent the disease from occurring or find a perfect cure of the disease, in form of a prophylactic or therapeutic vaccine, it will be a boon to not only to the individual but to the nation as a whole.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.