The effect of machine learning algorithms in the prediction, and diagnosis of meningitis: A systematic review

Background and Aims

This systematic review aimed to evaluating the effectiveness of machine learning (ML) algorithms for the prediction and diagnosis of meningitis.

Methods

On November 12, 2022, a systematic review was carried out using a keyword search in the reliable scientific databases PubMed, EMBASE, Scopus, and Web of Science. The recommendations of Preferred Reporting for Systematic Reviews and Meta-Analyses (PRISMA) were adhered to. Studies conducted in English that employed ML to predict and identify meningitis were deemed to match the inclusion criteria. The eligibility requirements were used to independently review the titles and abstracts. The whole text was then obtained and independently reviewed in accordance with the eligibility requirements.

Results

After all the research matched the inclusion criteria, a total of 16 studies were added to the systematic review. Studies on the application of ML algorithms in the three categories of disease diagnosis ability (8.16) and disease prediction ability (8.16) (including cases related to identifying patients (50%), risk of death in patients (25%), the consequences of the disease in childhood (12.5%), and its etiology [12.5%]) were placed. Among the ML algorithms used in this study, logistic regression (LR) (4.16, 25%) and multiple logistic regression (MLR) (4.16, 25%) were the most used. All the included studies indicated improvements in the processes of diagnosis, prediction, and disease outbreak with the help of ML algorithms.

Conclusion

The results of the study showed that in all included studies, ML algorithms were an effective approach to facilitate diagnosis, predict consequences for risk classification, and improve resource utilization by predicting the volume of patients or services as well as discovering risk factors. The role of ML algorithms in improving disease diagnosis was more significant than disease prediction and prevalence. Meanwhile, the use of combined methods can optimize differential diagnoses and facilitate the decision-making process for healthcare providers.

Convergence of Artificial Intelligence and Neuroscience towards the Diagnosis of Neurological Disorders-A Scoping Review

Artificial intelligence (AI) is a field of computer science that deals with the simulation of human intelligence using machines so that such machines gain problem-solving and decision-making capabilities similar to that of the human brain. Neuroscience is the scientific study of the struczture and cognitive functions of the brain. Neuroscience and AI are mutually interrelated. These two fields help each other in their advancements. The theory of neuroscience has brought many distinct improvisations into the AI field. The biological neural network has led to the realization of complex deep neural network architectures that are used to develop versatile applications, such as text processing, speech recognition, object detection, etc. Additionally, neuroscience helps to validate the existing AI-based models. Reinforcement learning in humans and animals has inspired computer scientists to develop algorithms for reinforcement learning in artificial systems, which enables those systems to learn complex strategies without explicit instruction. Such learning helps in building complex applications, like robot-based surgery, autonomous vehicles, gaming applications, etc. In turn, with its ability to intelligently analyze complex data and extract hidden patterns, AI fits as a perfect choice for analyzing neuroscience data that are very complex. Large-scale AI-based simulations help neuroscientists test their hypotheses. Through an interface with the brain, an AI-based system can extract the brain signals and commands that are generated according to the signals. These commands are fed into devices, such as a robotic arm, which helps in the movement of paralyzed muscles or other human parts. AI has several use cases in analyzing neuroimaging data and reducing the workload of radiologists. The study of neuroscience helps in the early detection and diagnosis of neurological disorders. In the same way, AI can effectively be applied to the prediction and detection of neurological disorders. Thus, in this paper, a scoping review has been carried out on the mutual relationship between AI and neuroscience, emphasizing the convergence between AI and neuroscience in order to detect and predict various neurological disorders.

Invasive meningococcal disease in older adults in North America and Europe: is this the time for action? A review of the literature

BACKGROUND

Neisseria meningitidis is an encapsulated Gram-negative diplococcus that asymptomatically colonises the upper respiratory tract in up to 25% of the population (mainly adolescents and young adults). Invasive meningococcal disease (IMD) caused by Neisseria meningitidis imposes a substantial public health burden,. The case fatality rate (CFR) of IMD remains high. IMD epidemiology varies markedly by region and over time, and there appears to be a shift in the epidemiology towards older adults. The objective of our review was to assess the published data on the epidemiology of IMD in older adults (those aged ≥ 55 years)in North America and Europe. Such information would assist decision-makers at national and international levels in developing future public health programmes for managing IMD.

METHODS

A comprehensive literature review was undertaken on 11 August 2020 across three databases: EMBASE, Medline and BIOSIS. Papers were included if they met the following criteria: full paper written in the English language; included patients aged ≥ 56 years; were published between 1/1/2009 11/9/2020 and included patients with either suspected or confirmed IMD or infection with N. meningitidis in North America or Europe. Case studies/reports/series were eligible for inclusion if they included persons in the age range of interest. Animal studies and letters to editors were excluded. In addition, the websites of international and national organisations and societies were also checked for relevant information.

RESULTS

There were 5,364 citations identified in total, of which 76 publications were included in this review. We identified that older adults with IMD were mainly affected by serogroups W and Y, which are generally not the predominant strains in circulation in most countries. Older adults had the highest CFRs, probably linked to underlying comorbidities and more atypical presentations hindering appropriate timely management. In addition, there was some evidence of a shift in the incidence of IMD from younger to older adults.

CONCLUSIONS

The use of meningococcal vaccines that include coverage against serogroups W and Y in immunization programs for older adults needs to be evaluated to inform health authorities' decisions of the relative benefits of vaccination and the utility of expanding national immunization programmes to this age group.

Systematic review of invasive meningococcal disease epidemiology in the Eastern Mediterranean and North Africa region

BACKGROUND

Invasive meningococcal disease (IMD) represents a global health burden. However, its epidemiology in the Eastern Mediterranean (EM) and North Africa (NA) regions is currently not well understood. This review had four key objectives: to describe asymptomatic meningococcal carriage, IMD epidemiology (e.g. serogroup prevalence, case-fatality rates [CFRs]), IMD presentation and management (e.g. clinical diagnosis, antibiotic treatments) and economic impact and evaluation (including health technology assessment [HTA] recommendations) in EM and NA.

METHODS

A systematic literature search (MEDLINE and EMBASE) was conducted (January 2000 to February 2021). Search strings included meningococcal disease and the regions/countries of interest. Identified publications were screened sequentially by title/abstract, followed by screening of the full-text article; articles were also assessed on methodological quality. Literature reviews, genetic sequencing or diagnostic accuracy studies, or other non-pertinent publication type were excluded. An additional grey literature search (non-peer-reviewed sources; start date January 2000) was conducted to the end of April 2019.

RESULTS

Of the 1745 publications identified, 79 were eligible for the final analysis (n = 61 for EM and n = 19 for NA; one study was relevant to both). Asymptomatic meningococcal carriage rates were 0-33% in risk groups (e.g. military personnel, pilgrims) in EM (no data in NA). In terms of epidemiology, serogroups A, B and W were most prevalent in EM compared with serogroups B and C in NA. IMD incidence was 0-20.5/100,000 in EM and 0.1-3.75/100,000 in NA (reported by 7/15 countries in EM and 3/5 countries in NA). CFRs were heterogenous across the EM, ranging from 0 to 57.9%, but were generally lower than 50%. Limited NA data showed a CFR of 0-50%. Data were also limited in terms of IMD presentation and management, particularly relating to clinical diagnosis/antibiotic treatment. No economic evaluation or HTA studies were found.

CONCLUSIONS

High-risk groups remain a significant reservoir of asymptomatic meningococcal carriage. It is probable that inadequacies in national surveillance systems have contributed to the gaps identified. There is consequently a pressing need to improve national surveillance systems in order to estimate the true burden of IMD and guide appropriate prevention and control programmes in these regions.

Global epidemiology and changing clinical presentations of invasive meningococcal disease: a narrative review

Neisseria meningitidis (the meningococcus) causes significant morbidity and mortality worldwide through an epidemic or sporadic invasive infections. The epidemiology of N. meningitidis is changing and unpredictable. Certain emerging meningococcal genotypes seem to be associated with increasing unusual clinical presentations. Indeed, early symptoms may vary and are frequently non-specific. However, atypical clinical forms including abdominal presentations, septic arthritis, and bacteremic pneumonia may lead to misdiagnosis and some are usually associated with higher case fatality rates due to delayed optimal management. Improving awareness of clinicians and public health specialists about these unusual but potentially severe presentations should help establish prompt diagnoses and provide appropriate management of cases. In this review, we described unusual panels of clinical presentations of invasive meningococcal disease linked to the recent changes in meningococcal epidemiology.

Artificial Intelligence in Differential Diagnostics of Meningitis: A Nationwide Study

Differential diagnosis between bacterial and viral meningitis is crucial. In our study, to differentiate bacterial vs. viral meningitis, three machine learning (ML) algorithms (multiple logistic regression (MLR), random forest (RF), and naïve-Bayes (NB)) were applied for the two age groups (0-14 and >14 years) of patients with meningitis by both conventional (culture) and molecular (PCR) methods. Cerebrospinal fluid (CSF) neutrophils, CSF lymphocytes, neutrophil-to-lymphocyte ratio (NLR), blood albumin, blood C-reactive protein (CRP), glucose, blood soluble urokinase-type plasminogen activator receptor (suPAR), and CSF lymphocytes-to-blood CRP ratio (LCR) were used as predictors for the ML algorithms. The performance of the ML algorithms was evaluated through a cross-validation procedure, and optimal predictions of the type of meningitis were above 95% for viral and 78% for bacterial meningitis. Overall, MLR and RF yielded the best performance when using CSF neutrophils, CSF lymphocytes, NLR, albumin, glucose, gender, and CRP. Also, our results reconfirm the high diagnostic accuracy of NLR in the differential diagnosis between bacterial and viral meningitis.

Economic evaluation of meningococcal serogroup B (MenB) vaccines: A systematic review

BACKGROUND

Meningococcal serogroup B (MenB) has emerged as the leading cause of invasive meningococcal disease (IMD) in several countries following the release of effective vaccines against serogroups A, C, W, and Y. In 2013, however, the first multicomponent MenB vaccine (Bexsero®) was licensed in Europe.

AIM

To review the evidence on the cost-effectiveness of vaccination against MenB.

METHODS

Searches were performed in MEDLINE, EMBASE, Web of Science, NHS EED, Econlit, Tufts CEA registry, and HTA. Three reviewers independently screened and selected studies. Using a narrative synthesis, studies were categorized by vaccination strategies. The quality of included studies was assessed using the Comparative Health Economics Evaluation Reporting Standards (CHEERS) checklist.

RESULTS

13 studies were included. Ten studies were conducted in the European region and three in the Americas. None of the vaccination strategies were considered cost-effective. Including herd effects improved value for money for MenB vaccines. Routine infant vaccination was the most effective short-term strategy, however, adolescent strategies offered the best value for money. Without herd immunity, routine infant vaccination had the lowest incremental cost-effectiveness ratio estimates.

CONCLUSION

Routine MenB vaccination does not offer substantial value for money, mainly due to high vaccine costs and low disease incidence.

Future Directions for Meningitis Surveillance and Vaccine Evaluation in the Meningitis Belt of Sub-Saharan Africa

In sub-Saharan Africa, bacterial meningitis remains a significant public health problem, especially in the countries of the meningitis belt, where Neisseria meningitidis serogroup A historically caused large-scale epidemics. In 2014, MenAfriNet was established as a consortium of partners supporting strategic implementation of case-based meningitis surveillance to monitor meningitis epidemiology and impact of meningococcal serogroup A conjugate vaccine (MACV). MenAfriNet improved data quality through use of standardized tools, procedures, and laboratory diagnostics. MenAfriNet surveillance and study data provided evidence of ongoing MACV impact, characterized the burden of non-serogroup A meningococcal disease (including the emergence of a new epidemic clone of serogroup C), and documented the impact of pneumococcal conjugate vaccine. New vaccines and schedules have been proposed for future implementation to address the remaining burden of meningitis. To support the goals of "Defeating Meningitis by 2030," MenAfriNet will continue to strengthen surveillance and support research and modeling to monitor the impact of these programs on meningitis burden in sub-Saharan Africa.

Bacterial Meningitis Epidemiology in Five Countries in the Meningitis Belt of Sub-Saharan Africa, 2015-2017

BACKGROUND

The MenAfriNet Consortium supports strategic implementation of case-based meningitis surveillance in key high-risk countries of the African meningitis belt: Burkina Faso, Chad, Mali, Niger, and Togo. We describe bacterial meningitis epidemiology in these 5 countries in 2015-2017.

METHODS

Case-based meningitis surveillance collects case-level demographic and clinical information and cerebrospinal fluid (CSF) laboratory results. Neisseria meningitidis, Streptococcus pneumoniae, or Haemophilus influenzae cases were confirmed and N. meningitidis/H. influenzae were serogrouped/serotyped by real-time polymerase chain reaction, culture, or latex agglutination. We calculated annual incidence in participating districts in each country in cases/100 000 population.

RESULTS

From 2015-2017, 18 262 suspected meningitis cases were reported; 92% had a CSF specimen available, of which 26% were confirmed as N. meningitidis (n = 2433; 56%), S. pneumoniae (n = 1758; 40%), or H. influenzae (n = 180; 4%). Average annual incidences for N. meningitidis, S. pneumoniae, and H. influenzae, respectively, were 7.5, 2.5, and 0.3. N. meningitidis incidence was 1.5 in Burkina Faso, 2.7 in Chad, 0.4 in Mali, 14.7 in Niger, and 12.5 in Togo. Several outbreaks occurred: NmC in Niger in 2015-2017, NmC in Mali in 2016, and NmW in Togo in 2016-2017. Of N. meningitidis cases, 53% were NmC, 30% NmW, and 13% NmX. Five NmA cases were reported (Burkina Faso, 2015). NmX increased from 0.6% of N. meningitidis cases in 2015 to 27% in 2017.

CONCLUSIONS

Although bacterial meningitis epidemiology varied widely by country, NmC and NmW caused several outbreaks, NmX increased although was not associated with outbreaks, and overall NmA incidence remained low. An effective low-cost multivalent meningococcal conjugate vaccine could help further control meningococcal meningitis in the region.