Three artificial intelligence data challenges based on CT and MRI.

PURPOSE: The second edition of the artificial intelligence (AI) data challenge was organized by the French Society of Radiology with the aim to: (i), work on relevant public health issues; (ii), build large, multicentre, high quality databases; and (iii), include three-dimensional (3D) information and prognostic questions. MATERIALS AND METHODS: Relevant clinical questions were proposed by French subspecialty colleges of radiology. Their feasibility was assessed by experts in the field of AI. A dedicated platform was set up for inclusion centers to safely upload their anonymized examinations in compliance with general data protection regulation. The quality of the database was checked by experts weekly with annotations performed by radiologists. Multidisciplinary teams competed between September 11th and October 13th 2019. RESULTS: Three questions were selected using different imaging and evaluation modalities, including: pulmonary nodule detection and classification from 3D computed tomography (CT), prediction of expanded disability status scale in multiple sclerosis using 3D magnetic resonance imaging (MRI) and segmentation of muscular surface for sarcopenia estimation from two-dimensional CT. A total of 4347 examinations were gathered of which only 6% were excluded. Three independent databases from 24 individual centers were created. A total of 143 participants were split into 20 multidisciplinary teams. CONCLUSION: Three data challenges with over 1200 general data protection regulation compliant CT or MRI examinations each were organized. Future challenges should be made with more complex situations combining histopathological or genetic information to resemble real life situations faced by radiologists in routine practice.

Affordability, cost-effectiveness and efficiency of primary health care: the Bamako Initiative experience in Benin and Guinea.

Since 1986 two West African countries, Benin and Guinea, have been actively reorganizing their peripheral health systems according to strategies subsequently called the "Bamako Initiative". Two preceding articles described the strategies implemented and the increased effectiveness of primary health care (PHC) witnessed over a period of six years. This article presents an analysis of cost and coverage data from biannual monitoring sessions between 1988 and 1993 in approximately 200 health centres in Benin and 214 in Guinea. In order to assess affordability, the total and per capita recurrent costs for operational health centres are analysed and then compared. The cost analysis reveals a mean total cost per health centre per year of slightly over US+11,000 in Benin and nearly US+9,000 in Guinea. The median cost per capita per year is approximately US+1.0 in Benin and between US+0.60 and US+0.80 in Guinea. Comparisons of these costs between regions, health centres and over time (as coverage levels evolved) show very little variation in either country. Cost-effectiveness is estimated by allocating these costs to immunization, antenatal and curative care and comparing them to the coverage achieved with these interventions. First, the cost-effectiveness of the Bamako Initiative (BI) system as a whole is analysed. The cost per fully vaccinated child is calculated at US+10.9 in Benin and US+8.8 in Guinea. The cost per woman receiving at least three antenatal visits is US+7 in Benin and US+4.7 in Guinea. For curative care, cost per full treatment is US+1.6 in Benin and half this amount in Guinea. Cost-effectiveness is variable between regions, health centres reveals that these differences in cost-effectiveness are mainly caused by the coverage levels achieved, since total costs are relatively stable. Finally the efficiency of drug management and prescriptions as well as of outreach for the expanded programme of immunizations (EPI) is estimated by relating specific drug and outreach activities costs to the number of beneficiaries. The average cost of drugs per treatment is around US+0.5 in Benin and around US+0.3 in Guinea. Cost analysis of outreach activities undertaken for EPI in Guinea revealed a similar average cost per child completely vaccinated for health centres with different intensities of outreach (approximately US+10) and an additional cost per child vaccinated attributable to outreach of US+1-2.

Local cost sharing in Bamako Initiative systems in Benin and Guinea: assuring the financial viability of primary health care.

The fourth in a series of five, this article presents and analyses data on cost recovery and community cost-sharing, two key aspects of the Bamako Initiative which have been implemented in Benin and Guinea since 1986. The data come from approximately 400 health centres and result from the six-monthly monitoring sessions conducted from 1989 to 1993. Community involvement in the financing of local operating costs in the two national scale programmes is also described. In Benin and Guinea, a user fee system generates the community financed revenue with the aim of covering local operating costs including drugs. Health worker salaries remain the responsibility of the government and donor funding covers vaccine and investment costs. Village health committees manage and control resources and revenue. The community is also involved in decision making, strategy definition and quality control. In Benin in 1993, community financing revenue amounted to about US$0.6 per capita per year and generally covered all local recurrent non salary costs except vaccines and left a surplus. Although total costs and revenues were slightly lower in Guinea for the same period, over-all user fee revenue (around US$0.3 per capita per year) covered local recurrent costs (not including salaries or vaccines). A comparison of costs and revenue between regions and individual health centres revealed important differences in cost recovery ratios. In Benin, some centres recovered more than twice the local costs targeted for community financing. Twenty-five per cent of centres in Guinea did not manage to cover their designated local recurrent costs. The longitudinal analysis showed that the level of cost recovery remained stable over time even as preventive care (and especially EPI) coverage rose significantly. To better understand the most important characteristics affecting cost recovery levels, best performing health centres in terms of cost-recovery levels in 1993 were compared to worst performing centres. This analysis showed that the size of the target population of the health centre is a key determinant of cost-recovery in both countries. In addition, in Guinea the utilization of curative care linked to geographical access and in Benin the average revenue per case linked to the number of deliveries proved to be additional factors of importance. In best performing centres, financial viability improved over time in both countries between 1990 and 1993. Finally, the implications of these conclusions for the planning of health centre revitalization in West Africa are discussed.

[Integration of the Expanded Program on Immunization into primary health care: examples of Benin and Guinea]. / Intégration du PEV aux soins de santé primaires: l'exemple du Bénin et de la Guinée.

Since 1986, two West African countries have been delivering immunizations within the framework of reorganized peripheral health systems. This revitalization is based on strategies which are implemented by an increasing number of African countries under the name "Bamako Initiative". It aims at providing universal access to a minimum package of maternal and child health priority interventions starting with immunizations, pre and perinatal care, oral rehydration for diarrhoea, treatment of malaria and acute lower respiratory infections. Within this package, immunization has been given high priority. Several strategies aimed at improving immunization coverage have been implemented: services have been reorganized so that any child or woman making contact with the health system receives immunization if needed. Health information systems have been revised so as to allow for active individual follow up and better management of health centre resources. Health staff have been given training in management and a biannual monitoring/microplanning process at health centre level has been introduced. The goal of monitoring is to enable health personnel to identify the obstacles to attaining optimum coverages with the priority interventions and to select locally appropriate corrective strategies. Health centres have also been provided with a motorcycle allowing for regular outreach activities. To cover the running costs of the services (mainly restocking of drugs, running and maintenance of the cold chain and the motorbike, and staff incentives), financial contribution from local communities have been sought through a fee-for-treatment system. Prices have been set at an affordable level by limiting the number of drugs to a minimal list purchased under generic names by international tendering procedures.(ABSTRACT TRUNCATED AT 250 WORDS)