Development of two artificial neural network models to support the diagnosis of pulmonary tuberculosis in hospitalized patients in Rio de Janeiro, Brazil

Identification of spinal tuberculosis subphenotypes using routine clinical data: a study based on unsupervised machine learning

OBJECTIVE

The identification of spinal tuberculosis subphenotypes is an integral component of precision medicine. However, we lack proper study models to identify subphenotypes in patients with spinal tuberculosis. Here we identified possible subphenotypes of spinal tuberculosis and compared their clinical results.

METHODS

A total of 422 patients with spinal tuberculosis who received surgical treatment were enrolled. Clustering analysis was performed using the K-means clustering algorithm and the routinely available clinical data collected from patients within 24 h after admission. Finally, the differences in clinical characteristics, surgical efficacy, and postoperative complications among the subphenotypes were compared.

RESULTS

Two subphenotypes of spinal tuberculosis were identified. Laboratory examination results revealed that the levels of more than one inflammatory index in cluster 2 were higher than those in cluster 1. In terms of disease severity, Cluster 2 showed a higher Oswestry Disability Index (ODI), a higher visual analysis scale (VAS) score, and a lower Japanese Orthopedic Association (JOA) score. In addition, in terms of postoperative outcomes, cluster 2 patients were more prone to complications, especially wound infections, and had a longer hospital stay.

CONCLUSION

K-means clustering analysis based on conventional available clinical data can rapidly identify two subtypes of spinal tuberculosis with different clinical results. We believe this finding will help clinicians to rapidly and easily identify the subtypes of spinal tuberculosis at the bedside and become the cornerstone of individualized treatment strategies.

Diagnostic Accuracy of the Artificial Intelligence Methods in Medical Imaging for Pulmonary Tuberculosis: A Systematic Review and Meta-Analysis

Tuberculosis (TB) remains one of the leading causes of death among infectious diseases worldwide. Early screening and diagnosis of pulmonary tuberculosis (PTB) is crucial in TB control, and tend to benefit from artificial intelligence. Here, we aimed to evaluate the diagnostic efficacy of a variety of artificial intelligence methods in medical imaging for PTB. We searched MEDLINE and Embase with the OVID platform to identify trials published update to November 2022 that evaluated the effectiveness of artificial-intelligence-based software in medical imaging of patients with PTB. After data extraction, the quality of studies was assessed using quality assessment of diagnostic accuracy studies 2 (QUADAS-2). Pooled sensitivity and specificity were estimated using a bivariate random-effects model. In total, 3987 references were initially identified and 61 studies were finally included, covering a wide range of 124,959 individuals. The pooled sensitivity and the specificity were 91% (95% confidence interval (CI), 89-93%) and 65% (54-75%), respectively, in clinical trials, and 94% (89-96%) and 95% (91-97%), respectively, in model-development studies. These findings have demonstrated that artificial-intelligence-based software could serve as an accurate tool to diagnose PTB in medical imaging. However, standardized reporting guidance regarding AI-specific trials and multicenter clinical trials is urgently needed to truly transform this cutting-edge technology into clinical practice.

Review and Updates on the Diagnosis of Tuberculosis

Diagnosis of tuberculosis, and especially the diagnosis of extrapulmonary tuberculosis, still faces challenges in clinical practice. There are several reasons for this. Methods based on the detection of Mycobacterium tuberculosis (Mtb) are insufficiently sensitive, methods based on the detection of Mtb-specific immune responses cannot always differentiate active disease from latent infection, and some of the serological markers of infection with Mtb are insufficiently specific to differentiate tuberculosis from other inflammatory diseases. New tools based on technologies such as flow cytometry, mass spectrometry, high-throughput sequencing, and artificial intelligence have the potential to solve this dilemma. The aim of this review was to provide an updated overview of current efforts to optimize classical diagnostic methods, as well as new molecular and other methodologies, for accurate diagnosis of patients with Mtb infection.

Machine learning in the loop for tuberculosis diagnosis support

The use of machine learning (ML) for diagnosis support has advanced in the field of health. In the present paper, the results of studying ML techniques in a tuberculosis diagnosis loop in a scenario of limited resources are presented. Data are analyzed using a tuberculosis (TB) therapy program at a health institution in a main city of a developing country using five ML models. Logistic regression, classification trees, random forest, support vector machines, and artificial neural networks are trained under physician supervision following physicians' typical daily work. The models are trained on seven main variables collected when patients arrive at the facility. Additionally, the variables applied to train the models are analyzed, and the models' advantages and limitations are discussed in the context of the automated ML techniques. The results show that artificial neural networks obtain the best results in terms of accuracy, sensitivity, and area under the receiver operating curve. These results represent an improvement over smear microscopy, which is commonly used techniques to detect TB for special cases. Findings demonstrate that ML in the TB diagnosis loop can be reinforced with available data to serve as an alternative diagnosis tool based on data processing in places where the health infrastructure is limited.

Optimizing human-centered AI for healthcare in the Global South

Over the past 60 years, artificial intelligence (AI) has made significant progress, but most of its benefits have failed to make a significant impact within the Global South. Current practices that have led to biased systems will prevent AI from being actualized unless significant efforts are made to change them. As technical advances in AI and an interest in solving new problems lead researchers and tech companies to develop AI applications that target the health of marginalized communities, it is crucially important to study how AI can be used to empower those on the front lines in the Global South and how these tools can be optimally designed for marginalized communities. This perspective examines the landscape of AI for healthcare in the Global South and the evaluations of such systems and provides tangible recommendations for AI practitioners and human-centered researchers to incorporate in the development of AI systems for use with marginalized populations.

Despite growing enthusiasm to address societal problems using AI, there is a scarce amount of research studying the implications and challenges associated with integrating AI-enabled technologies into low-resource communities throughout the Global South. Neglecting to analyze the unique needs and requirements of the frontline workers expected to operate AI systems, especially those used for healthcare, stands to exacerbate existing issues in algorithmic bias and impose additional work burdens, deteriorating the level of care provided to vulnerable communities.

The Promise of Clinical Decision Support Systems Targetting Low-Resource Settings

Low-resource clinical settings are plagued by low physician-to-patient ratios and a shortage of high-quality medical expertise and infrastructure. Together, these phenomena lead to over-burdened healthcare systems that under-serve the needs of the community. Alleviating this burden can be undertaken by the introduction of clinical decision support systems (CDSSs); systems that support stakeholders (ranging from physicians to patients) within the clinical setting in their day-to-day activities. Such systems, which have proven to be effective in the developed world, remain to be under-explored in low-resource settings. This review attempts to summarize the research focused on clinical decision support systems that either target stakeholders within low-resource clinical settings or diseases commonly found in such environments. When categorizing our findings according to disease applications, we find that CDSSs are predominantly focused on dealing with bacterial infections and maternal care, do not leverage deep learning, and have not been evaluated prospectively. Together, these highlight the need for increased research in this domain in order to impact a diverse set of medical conditions and ultimately improve patient outcomes.

Artificial intelligence and the future of global health

Concurrent advances in information technology infrastructure and mobile computing power in many low and middle-income countries (LMICs) have raised hopes that artificial intelligence (AI) might help to address challenges unique to the field of global health and accelerate achievement of the health-related sustainable development goals. A series of fundamental questions have been raised about AI-driven health interventions, and whether the tools, methods, and protections traditionally used to make ethical and evidence-based decisions about new technologies can be applied to AI. Deployment of AI has already begun for a broad range of health issues common to LMICs, with interventions focused primarily on communicable diseases, including tuberculosis and malaria. Types of AI vary, but most use some form of machine learning or signal processing. Several types of machine learning methods are frequently used together, as is machine learning with other approaches, most often signal processing. AI-driven health interventions fit into four categories relevant to global health researchers: (1) diagnosis, (2) patient morbidity or mortality risk assessment, (3) disease outbreak prediction and surveillance, and (4) health policy and planning. However, much of the AI-driven intervention research in global health does not describe ethical, regulatory, or practical considerations required for widespread use or deployment at scale. Despite the field remaining nascent, AI-driven health interventions could lead to improved health outcomes in LMICs. Although some challenges of developing and deploying these interventions might not be unique to these settings, the global health community will need to work quickly to establish guidelines for development, testing, and use, and develop a user-driven research agenda to facilitate equitable and ethical use.

Stillbirth risk prediction using machine learning for a large cohort of births from Western Australia, 1980-2015

Quantification of stillbirth risk has potential to support clinical decision-making. Studies that have attempted to quantify stillbirth risk have been hampered by small event rates, a limited range of predictors that typically exclude obstetric history, lack of validation, and restriction to a single classifier (logistic regression). Consequently, predictive performance remains low, and risk quantification has not been adopted into antenatal practice. The study population consisted of all births to women in Western Australia from 1980 to 2015, excluding terminations. After all exclusions there were 947,025 livebirths and 5,788 stillbirths. Predictive models for stillbirth were developed using multiple machine learning classifiers: regularised logistic regression, decision trees based on classification and regression trees, random forest, extreme gradient boosting (XGBoost), and a multilayer perceptron neural network. We applied 10-fold cross-validation using independent data not used to develop the models. Predictors included maternal socio-demographic characteristics, chronic medical conditions, obstetric complications and family history in both the current and previous pregnancy. In this cohort, 66% of stillbirths were observed for multiparous women. The best performing classifier (XGBoost) predicted 45% (95% CI: 43%, 46%) of stillbirths for all women and 45% (95% CI: 43%, 47%) of stillbirths after the inclusion of previous pregnancy history. Almost half of stillbirths could be potentially identified antenatally based on a combination of current pregnancy complications, congenital anomalies, maternal characteristics, and medical history. Greatest sensitivity is achieved with addition of current pregnancy complications. Ensemble classifiers offered marginal improvement for prediction compared to logistic regression.

Applications of artificial neural networks in health care organizational decision-making: A scoping review

Health care organizations are leveraging machine-learning techniques, such as artificial neural networks (ANN), to improve delivery of care at a reduced cost. Applications of ANN to diagnosis are well-known; however, ANN are increasingly used to inform health care management decisions. We provide a seminal review of the applications of ANN to health care organizational decision-making. We screened 3,397 articles from six databases with coverage of Health Administration, Computer Science and Business Administration. We extracted study characteristics, aim, methodology and context (including level of analysis) from 80 articles meeting inclusion criteria. Articles were published from 1997–2018 and originated from 24 countries, with a plurality of papers (26 articles) published by authors from the United States. Types of ANN used included ANN (36 articles), feed-forward networks (25 articles), or hybrid models (23 articles); reported accuracy varied from 50% to 100%. The majority of ANN informed decision-making at the micro level (61 articles), between patients and health care providers. Fewer ANN were deployed for intra-organizational (meso- level, 29 articles) and system, policy or inter-organizational (macro- level, 10 articles) decision-making. Our review identifies key characteristics and drivers for market uptake of ANN for health care organizational decision-making to guide further adoption of this technique.

Modelling the impact of chest X-ray and alternative triage approaches prior to seeking a tuberculosis diagnosis

Background

Tuberculosis is a major challenge to health in the developing world. Triage prior to diagnostic testing could potentially reduce the volume of tests and costs associated with using the more accurate, but costly, Xpert MTB/RIF assay. An effective methodology to predict the impact of introducing triage prior to tuberculosis diagnostic testing could be useful in helping to guide policy.

Methods

The development and use of operational modelling to project the impact on case detection and health system costs of alternative triage approaches for tuberculosis, with or without X-ray, based on data from Porto Alegre City, Brazil.

Results

Most of the triage approaches modelled without X-ray were predicted to provide no significant benefit. One approach based on an artificial neural network applied to patient and symptom characteristics was projected to increase case detection (82% vs. 75%) compared to microscopy, and reduce costs compared to Xpert without triage. In addition, use of X-ray before diagnostic testing for HIV-negative patients could maintain diagnostic yield of using Xpert without triage, and reduce costs.

Conclusion

A model for the impact assessment of alternative triage approaches has been tested. The results from using the approach demonstrate its usefulness in informing policy in a typical high burden setting for tuberculosis.

Electronic supplementary material

The online version of this article (10.1186/s12879-019-3684-1) contains supplementary material, which is available to authorized users.

Evaluation of the effect of CaD on the bone structure and bone metabolic changes in senile osteoporosis rats based on MLP–ANN methods

Senile osteoporosis (SOP) is a related disease of systematic degenerative changes in bones during natural aging.

Early detection of colorectal adenocarcinoma: a clinical decision support tool based on plasma porphyrin accumulation and risk factors

BACKGROUND

An increase in naturally-occurring porphyrins has been described in the blood of subjects bearing different kinds of tumors, including colorectal, and this is probably related to a systemic alteration of heme metabolism induced by tumor cells. The aim of our study was to develop an artificial neural network (ANN) classifier for early detection of colorectal adenocarcinoma based on plasma porphyrin accumulation and risk factors.

METHODS

We measured the endogenous fluorescence of blood plasma in 100 colorectal adenocarcinoma patients and 112 controls using a conventional spectrofluorometer. Height, weight, personal and family medical history, use of alcohol, red meat, vegetables and tobacco were all recorded. An ANN model was built up from demographic data and from the integral of the fluorescence emission peak in the range 610-650 nm. We used the Receiver Operating Characteristic (ROC) curve to assess performance in distinguishing colorectal adenocarcinoma patients and controls. A liquid chromatography-high resolution mass spectrometry (LC-HRMS) analytical method was employed to identify the agents responsible for native fluorescence.

RESULTS

The fluorescence analysis indicated that the integral of the fluorescence emission peak in the range 610-650 nm was significantly higher in colorectal adenocarcinoma patients than controls (p < 0.0001) and was weakly correlated with the TNM staging (Spearman's rho = 0.224, p = 0.011). LC-HRMS measurements showed that the agents responsible for the fluorescence emission were mainly protoporphyrin-IX (PpIX) and coproporphyrin-I (CpI). The overall accuracy of our ANN model was 88% (87% sensitivity and 90% specificity) with an area under the ROC curve of 0.83.

CONCLUSIONS

These results confirm that tumor cells accumulate a diagnostic level of endogenous porphyrin compounds and suggest that plasma porphyrin concentrations, indirectly measured through fluorescence analysis, may be useful, together with risk factors, as a clinical decision support tool for the early detection of colorectal adenocarcinoma. Our future efforts will be aimed at examining how plasma porphyrin accumulation correlates with survival and response to therapy.

Tuberculosis diagnosis support analysis for precarious health information systems

BACKGROUND AND OBJECTIVE

Pulmonary tuberculosis is a world emergency for the World Health Organization. Techniques and new diagnosis tools are important to battle this bacterial infection. There have been many advances in all those fields, but in developing countries such as Colombia, where the resources and infrastructure are limited, new fast and less expensive strategies are increasingly needed. Artificial neural networks are computational intelligence techniques that can be used in this kind of problems and offer additional support in the tuberculosis diagnosis process, providing a tool to medical staff to make decisions about management of subjects under suspicious of tuberculosis.

MATERIALS AND METHODS

A database extracted from 105 subjects with precarious information of people under suspect of pulmonary tuberculosis was used in this study. Data extracted from sex, age, diabetes, homeless, AIDS status and a variable with clinical knowledge from the medical personnel were used. Models based on artificial neural networks were used, exploring supervised learning to detect the disease. Unsupervised learning was used to create three risk groups based on available information.

RESULTS

Obtained results are comparable with traditional techniques for detection of tuberculosis, showing advantages such as fast and low implementation costs. Sensitivity of 97% and specificity of 71% where achieved.

CONCLUSIONS

Used techniques allowed to obtain valuable information that can be useful for physicians who treat the disease in decision making processes, especially under limited infrastructure and data.

Applying an artificial neural network model for developing a severity score for patients with hereditary amyloid polyneuropathy

Hereditary (familial) amyloid polyneuropathy (FAP) is a systemic disease that includes a sensorimotor polyneuropathy related to transthyretin (TTR) mutations. So far, a scale designed to classify the severity of this disease has not yet been validated. This work proposes the implementation of an artificial neural network (ANN) in order to develop a severity scale for monitoring the disease progression in FAP patients. In order to achieve this goal, relevant symptoms and laboratory findings were collected from 98 Brazilian patients included in THAOS - the Transthyretin Amyloidosis Outcomes Survey. Ninety-three percent of them bore Val30Met, the most prevalent variant of TTR worldwide; 63 were symptomatic and 35 were asymptomatic. These data were numerically codified for the purpose of constructing a Self-Organizing Map (SOM), which maps data onto a grid of artificial neurons. Mapped data could be clustered by similarity into five groups, based on increasing FAP severity (from Groups 1 to 5). Most symptoms were virtually absent from patients who mapped to Group 1, which also includes the asymptomatic patients. Group 2 encompasses the patients bearing symptoms considered to be initial markers of FAP, such as first signs of walking disabilities and lack of sensitivity to temperature and pain. Interestingly, the patients with cardiac symptoms, which also carry cardiac-associated mutations of the TTR gene (such as Val112Ile and Ala19Asp), were concentrated in Group 3. Symptoms such as urinary and fecal incontinence and diarrhea characterized particularly Groups 4 and 5. Renal impairment was found almost exclusively in Group 5. Model validation was accomplished by considering the symptoms from a sample with 48 additional Brazilian patients. The severity scores proposed here not only identify the current stage of a patient's disease but also offer to the physician an easy-to-read, 2D map that makes it possible to track disease progression.

Application of artificial neural network model combined with four biomarkers in auxiliary diagnosis of lung cancer

The purpose of the study was to explore the application of artificial neural network model in the auxiliary diagnosis of lung cancer and compare the effects of back-propagation (BP) neural network with Fisher discrimination model for lung cancer screening by the combined detections of four biomarkers of p16, RASSF1A and FHIT gene promoter methylation levels and the relative telomere length. Real-time quantitative methylation-specific PCR was used to detect the levels of three-gene promoter methylation, and real-time PCR method was applied to determine the relative telomere length. BP neural network and Fisher discrimination analysis were used to establish the discrimination diagnosis model. The levels of three-gene promoter methylation in patients with lung cancer were significantly higher than those of the normal controls. The values of Z(P) in two groups were 2.641 (0.008), 2.075 (0.038) and 3.044 (0.002), respectively. The relative telomere lengths of patients with lung cancer (0.93 ± 0.32) were significantly lower than those of the normal controls (1.16 ± 0.57), t = 4.072, P < 0.001. The areas under the ROC curve (AUC) and 95 % CI of prediction set from Fisher discrimination analysis and BP neural network were 0.670 (0.569-0.761) and 0.760 (0.664-0.840). The AUC of BP neural network was higher than that of Fisher discrimination analysis, and Z(P) was 0.76. Four biomarkers are associated with lung cancer. BP neural network model for the prediction of lung cancer is better than Fisher discrimination analysis, and it can provide an excellent and intelligent diagnosis tool for lung cancer.