Boosting backpropagation algorithm by stimulus-sampling: Application in computer-aided medical diagnosis

Artificial Neural Network and Remote Sensing combined to predict the Aboveground Biomass in the Cerrado biome

Cerrado is the second largest biome in Brazil, and it is responsible for providing us several ecosystem services, including the functions of storing Carbon and biodiversity conservation. In this study, we developed a modeling approach to predict the Aboveground biomass (AGB) in Cerrado vegetation using Artificial Neural Networks (ANNs), vegetation indices retrieved from RapidEye satellite imagery, and field data acquired within the Federal District territory, Brazil. Correlation testing was performed to identify potential vegetation index candidates to be used as input in the AGB modeling. Several ANNs were trained to predict the AGB in the study area using vegetation indices and field data. The optimum ANN was selected according to criteria of mean error of the estimate, correlation coefficient, and graphical analysis. The best performing ANN showed a predictive power of 90% and RMSE less than 17%. The validation tests showed no significant difference between the observed and ANN-predicted values. We estimated an average AGB of 16.55± 8.6 Mg.ha-1 in shrublands in the study area. Our study results indicate that vegetation indices and ANNs combined could accurately estimate the AGB in the Cerrado vegetation in the study area, showing to be a promising methodological approach to be broadly applied throughout the Cerrado biome.

Application of Artificial Neural Network Models to Differentiate Between Complicated and Uncomplicated Acute Appendicitis

Preoperative prediction of complicated appendicitis is challenging, and many clinical tools are developed to predict complicated appendicitis. This study evaluated whether a supervised learning method can recognize complicated appendicitis in emergency department (ED). Consecutive patients with acute appendicitis presenting to the ED were enrolled and included into training and testing datasets at a ratio of 70:30. The multilayer perceptron artificial neural network (ANN) models were trained to perform binary outcome classification between uncomplicated and complicated acute appendicitis. Measures of sensitivity, specificity, positive and negative likelihood ratio (LR + and LR-), and a c statistic of a receiver of operating characteristic curve were used to evaluate an ANN model. The simplest ANN model by Bröker et al. including the C-reactive protein (CRP) and symptom duration as variables achieved a c statistic value of 0.894. The ANN models developed by Avanesov et al. including symptom duration, appendiceal diameter, periappendiceal fluid, extraluminal air, and abscess as variables attained a high diagnostic performance (a c statistic value of 0.949) and good efficiency (sensitivity of 78.6%, specificity of 94.5%, LR + of 14.29, LR- of 0.23 in the testing dataset); and our own model by H.A. Lin et al. including the CRP level, neutrophil-to-lymphocyte ratio, fat-stranding sign, appendicolith, and ascites exhibited high accuracy (c statistic of 0.950) and outstanding efficiency (sensitivity of 85.7%, specificity of 91.7%, LR + of 10.36, LR- of 0.16 in the testing dataset). The ANN models developed by Avanesov et al. and H.A. Lin et al. developed model exhibited a high diagnostic performance.

Artificial Intelligence Techniques That May Be Applied to Primary Care Data to Facilitate Earlier Diagnosis of Cancer: Systematic Review

BACKGROUND

More than 17 million people worldwide, including 360,000 people in the United Kingdom, were diagnosed with cancer in 2018. Cancer prognosis and disease burden are highly dependent on the disease stage at diagnosis. Most people diagnosed with cancer first present in primary care settings, where improved assessment of the (often vague) presenting symptoms of cancer could lead to earlier detection and improved outcomes for patients. There is accumulating evidence that artificial intelligence (AI) can assist clinicians in making better clinical decisions in some areas of health care.

OBJECTIVE

This study aimed to systematically review AI techniques that may facilitate earlier diagnosis of cancer and could be applied to primary care electronic health record (EHR) data. The quality of the evidence, the phase of development the AI techniques have reached, the gaps that exist in the evidence, and the potential for use in primary care were evaluated.

METHODS

We searched MEDLINE, Embase, SCOPUS, and Web of Science databases from January 01, 2000, to June 11, 2019, and included all studies providing evidence for the accuracy or effectiveness of applying AI techniques for the early detection of cancer, which may be applicable to primary care EHRs. We included all study designs in all settings and languages. These searches were extended through a scoping review of AI-based commercial technologies. The main outcomes assessed were measures of diagnostic accuracy for cancer.

RESULTS

We identified 10,456 studies; 16 studies met the inclusion criteria, representing the data of 3,862,910 patients. A total of 13 studies described the initial development and testing of AI algorithms, and 3 studies described the validation of an AI algorithm in independent data sets. One study was based on prospectively collected data; only 3 studies were based on primary care data. We found no data on implementation barriers or cost-effectiveness. Risk of bias assessment highlighted a wide range of study quality. The additional scoping review of commercial AI technologies identified 21 technologies, only 1 meeting our inclusion criteria. Meta-analysis was not undertaken because of the heterogeneity of AI modalities, data set characteristics, and outcome measures.

CONCLUSIONS

AI techniques have been applied to EHR-type data to facilitate early diagnosis of cancer, but their use in primary care settings is still at an early stage of maturity. Further evidence is needed on their performance using primary care data, implementation barriers, and cost-effectiveness before widespread adoption into routine primary care clinical practice can be recommended.

Deep Learning in the Biomedical Applications: Recent and Future Status

Deep neural networks represent, nowadays, the most effective machine learning technology in biomedical domain. In this domain, the different areas of interest concern the Omics (study of the genome—genomics—and proteins—transcriptomics, proteomics, and metabolomics), bioimaging (study of biological cell and tissue), medical imaging (study of the human organs by creating visual representations), BBMI (study of the brain and body machine interface) and public and medical health management (PmHM). This paper reviews the major deep learning concepts pertinent to such biomedical applications. Concise overviews are provided for the Omics and the BBMI. We end our analysis with a critical discussion, interpretation and relevant open challenges.

Early experience with Watson for oncology in Korean patients with colorectal cancer

BACKGROUND

Watson for oncology (WFO) is a cognitive computing system providing decision support. We evaluated the concordance rates between the treatment options determined by WFO and those determined by a multidisciplinary team (MDT).

METHODS

We reviewed the medical charts of patients diagnosed with colorectal cancer who visited the MDT at a single tertiary medical center from November 2016 to April 2017. WFO classified the treatment options for specific patients into three categories: 'Recommended', 'For consideration', and 'Not recommended'. Concordance rates between the WFO- and MDT-determined chemotherapy options, and the factors that potentially influence the concordance rate, were analyzed.

RESULTS

Sixty-nine patients with colorectal cancer met with the MDT from Nov. 2016 to Feb. 2017. The mean age of the patients was 62 years (range: 34-86 years), and more patients were male (47/69) than female. Of the 69 patients, 51 (73.9%) were diagnosed with colon cancer, of whom 46.4% received the same regimen recommendation from WFO ('Recommended') as they did from the MDT. After inclusion of the 'For consideration' category from WFO, the concordance rate increased to 87.0%. The concordance rate between MDT and NCCN guidelines was 97.1%, and that between the WFO and NCCN guidelines was 88.4%. The concordance rates between WFO and MDT were significantly lower in patients with stage II, IIIC, or IV disease (P<0.001), and the colorectal cancer stage was the only statistically significant factor discriminating between WFO and MDT.

CONCLUSIONS

The concordance rate between chemotherapy regimens for colorectal cancer determined by MDT versus WFO recommendations was 46.4%. After including the 'For consideration' category from WFO, the concordance rate increased to 88.4%. Further modification and improvement of the WFO prioritizing algorithm used to recommend treatment may increase the usefulness of WFO in the clinic.