Empirical antibiotic therapy (ABT) of lower respiratory tract infections (LRTI) in the elderly: application of artificial neural network (ANN). Preliminary results

An AI-based auxiliary empirical antibiotic therapy model for children with bacterial pneumonia using low-dose chest CT images

Purpose

To construct an auxiliary empirical antibiotic therapy (EAT) multi-class classification model for children with bacterial pneumonia using radiomics features based on artificial intelligence and low-dose chest CT images.

Materials and methods

Data were retrospectively collected from children with pathogen-confirmed bacterial pneumonia including Gram-positive bacterial pneumonia (122/389, 31%), Gram-negative bacterial pneumonia (159/389, 41%) and atypical bacterial pneumonia (108/389, 28%) from January 1 to June 30, 2019. Nine machine-learning models were separately evaluated based on radiomics features extracted from CT images; three optimal submodels were constructed and integrated to form a multi-class classification model.

Results

We selected five features to develop three radiomics submodels: a Gram-positive model, a Gram-negative model and an atypical model. The comprehensive radiomics model using support vector machine method yielded an average area under the curve (AUC) of 0.75 [95% confidence interval (CI), 0.65–0.83] and accuracy (ACC) of 0.58 [sensitivity (SEN), 0.57; specificity (SPE), 0.78] in the training set, and an average AUC of 0.73 (95% CI 0.61–0.79) and ACC of 0.54 (SEN, 0.52; SPE, 0.75) in the test set.

Conclusion

This auxiliary EAT radiomics multi-class classification model was deserved to be researched in differential diagnosing bacterial pneumonias in children.

Can Artificial Intelligence Improve the Management of Pneumonia

The use of artificial intelligence (AI) to support clinical medical decisions is a rather promising concept. There are two important factors that have driven these advances: the availability of data from electronic health records (EHR) and progress made in computational performance. These two concepts are interrelated with respect to complex mathematical functions such as machine learning (ML) or neural networks (NN). Indeed, some published articles have already demonstrated the potential of these approaches in medicine. When considering the diagnosis and management of pneumonia, the use of AI and chest X-ray (CXR) images primarily have been indicative of early diagnosis, prompt antimicrobial therapy, and ultimately, better prognosis. Coupled with this is the growing research involving empirical therapy and mortality prediction, too. Maximizing the power of NN, the majority of studies have reported high accuracy rates in their predictions. As AI can handle large amounts of data and execute mathematical functions such as machine learning and neural networks, AI can be revolutionary in supporting the clinical decision-making processes. In this review, we describe and discuss the most relevant studies of AI in pneumonia.

A new tool for the evaluation of the rehabilitation outcomes in older persons: a machine learning model to predict functional status 1 year ahead

PURPOSE

To date, the assessment of disability in older people is obtained utilizing a Comprehensive Geriatric Assessment (CGA). However, it is often difficult to understand which areas of CGA are most predictive of the disability. The aim of this study is to evaluate the possibility to early predict-1 year ahead-the disability level of a patient using machine leaning models.

METHODS

Community-dwelling older people were enrolled in this study. CGA was made at baseline and at 1 year follow-up. After collecting input/independent variables (i.e., age, gender, schooling followed, body mass index, information on smoking, polypharmacy, functional status, cognitive performance, depression, nutritional status), we performed two distinct Support Vector Machine models (SVMs) able to predict functional status 1 year ahead. To validate the choice of the model, the results achieved with the SVMs were compared with the output produced by simple linear regression models.

RESULTS

218 patients (mean age = 78.01; SD = 7.85; male = 39%) were recruited. The combination of the two SVMs is able to achieve a higher prediction accuracy (exceeding 80% instances correctly classified vs 67% instances correctly classified by the combination of the two linear regression models). Furthermore, SVMs are able to classify both the three categories, self sufficiently, disability risk and disability, while linear regression model separates the population only in two groups (self-sufficiency and disability) without identifying the intermediate category (disability risk) which turns out to be the most critical one.

CONCLUSIONS

The development of such a model can contribute to the early detection of patients at risk of self-sufficiency loss.

Pneumococcus and the Elderly in Italy: A Summary of Available Evidence Regarding Carriage, Clinical Burden of Lower Respiratory Tract Infections and On-Field Effectiveness of PCV13 Vaccination

Streptococcus pneumoniae is currently the leading cause of community-acquired pneumonia (CAP) and lower respiratory tract infections (LRTI) in adults, elderly and high-risk subjects worldwide. The clear benefits of pneumococcal conjugate vaccination in childhood have been accompanied by a decrease of vaccine-serotype invasive diseases among adults in several countries, mainly due to the herd effect mediated by the reduction of vaccine-serotype nasopharyngeal colonization in both age groups, but this reduction in the incidence of pneumonia has not been observed. The "Community Acquired Pneumonia Immunization Trial in Adults" (CAPITA) study provided conclusive evidence about 13-valent pneumococcal conjugate vaccine (PCV13) efficacy in preventing CAP in adults and led Western countries to issue new recommendations for pneumococcal immunization targeting subjects >50 years and high-risk groups, with marked differences with respect to age and/or risk groups immunized, eligibility for reimbursement and national, regional or local implementation. Several Italian regions implemented PCV13 immunization programs in adults and interesting data have been come available in the last years, especially from Liguria, a Northern region with a high and long-lasting pneumococcal vaccine immunological pressure in infants. In this review, currently available evidence from Italy and Liguria regarding pneumococcal carriage, burden of CAP and LRTI, and on-field effectiveness of PCV13 immunization in adults and elderly will be summarized.

Aid decision algorithms to estimate the risk in congenital heart surgery

BACKGROUND AND OBJECTIVE

In this paper, we have tested the suitability of using different artificial intelligence-based algorithms for decision support when classifying the risk of congenital heart surgery. In this sense, classification of those surgical risks provides enormous benefits as the a priori estimation of surgical outcomes depending on either the type of disease or the type of repair, and other elements that influence the final result. This preventive estimation may help to avoid future complications, or even death.

METHODS

We have evaluated four machine learning algorithms to achieve our objective: multilayer perceptron, self-organizing map, radial basis function networks and decision trees. The architectures implemented have the aim of classifying among three types of surgical risk: low complexity, medium complexity and high complexity.

RESULTS

Accuracy outcomes achieved range between 80% and 99%, being the multilayer perceptron method the one that offered a higher hit ratio.

CONCLUSIONS

According to the results, it is feasible to develop a clinical decision support system using the evaluated algorithms. Such system would help cardiology specialists, paediatricians and surgeons to forecast the level of risk related to a congenital heart disease surgery.

Potential effect of PCV13 introduction on Emergency Department accesses for lower respiratory tract infections in elderly and at risk adults

Liguria, an administrative region in northern Italy characterized by a decade of high PCV coverage in paediatric age group, has issued new PCV13 recommendations for free active immunization in adults with risk factors and subjects aged ≥ 70 years old. Main aims of this study are: (1) a descriptive epidemiology of the clinical burden of lower respiratory tract infections (LRTI) in adults ≥18 years of age; and (2) a crossover evaluation of the effect of introduction of PCV13 vaccination in adults aged ≥70 years old, in terms of ED accesses for LRTI, obtained by a Syndrome Surveillance System (SSS). The ED access, chief complaint based SSS will allow an active surveillance of a population cohort of >430 000 individuals resident in Genoa metropolitan area, aged ≥18 years old, for a period of 60 months. During pre-PCV period, annual cumulative incidence of ED accesses for LRTI was equal to 7/1000 and 2% in ≥65 and ≥85 year adults, respectively. In ≥65 years adults, more than 70% of subjects identified by the SSS has at least one risk condition, with a peak of 87% in ≥85 year cohort. New Ligurian PCV13 recommendations can potentially reach more than 75% of ED accesses for LRTI. Data highlights the heavy impact of LRTI in terms of ED accesses, especially in the elderly and subjects with chronic conditions and the usefulness of SSS tool for monitoring PCV vaccination effect.

Three-question dementia screening. Development of the Salzburg Dementia Test Prediction (SDTP)

BACKGROUND

To date, short dementia screenings are often limited by poor specificity or still take too much time with respect to the restricted resources of primary care physicians and the increasing number of dementia disorders. As a new instrument, the three-question dementia screening (SDTP, Salzburg Dementia Test Prediction) should be compared with the eight-item screening of Chen et al. and the CERAD battery (Consortium to Establish a Registry for Alzheimer's Disease), focusing on specificity and economy of time.

MATERIALS AND METHODS

We tested 404 patients (243 women). The mean age of the subjects was 80.1 years (SD = 6.8) for men and 83.2 years (SD = 6.0) for women. The mean Mini-Mental State Examination (MMSE) score was 21.9 (SD =  5.8) for men and 21.1 (SD =  6.3) for women. Artificial neural networks (ANNs) were used to find a mathematical model that allows the total MMSE to be predicted with only three questions of the MMSE. This is achieved by multiplying the outcome of the three best predictor questions with a weighting coefficient, which was delineated by using ANNs.

RESULTS

The Salzburg Dementia Test Prediction (SDTP) had a sensitivity of 94% (95% CI: 87-97%) for screening of possible dementia, when the MMSE (MMSE < 25/30) was used as the reference test method and 96% when the CERAD was used. The specificity was 68% (95% CI: 57-77%) if the MMSE was used and 70% if the whole test battery (CERAD) was used, which is as sensitive as and more specific than the eight-item screening.

CONCLUSION

The SDTP is a time-saving instrument for screening of dementia, which is as sensitive as and more specific than the eight-item screening of Chen et al. and provides a prediction of the MMSE with high accuracy.