Artificial Intelligence-based Tools Research Articles

Artificial Intelligence-Based Tools for Process Optimization: Case Study—Bromocresol Green Decolorization with Active Carbon

This study highlights the benefits of optimizing the decolorization of bromocresol green (a colorant/pH indicator widely used in the industry, whose degradation produces toxic byproducts) by adsorption on active carbon. A set of experiments were planned and performed based on the design of experiments methodology for the following parameters: the colorant concentration (0.009-0.045 g/L), the amount of adsorbent (0.5-3 g/L), and the contact time (60-240 min). Modeling and optimization strategies were employed to determine the working conditions leading to efficiency maximization. Using the response surface methodology, the optimum values of the primary process parameters were established. In addition, a modified bacterial foraging optimization algorithm was applied as an alternative optimizer in combination with artificial neural networks in order to determine multiple combinations of parameters that can lead to maximum process efficiency. Different solutions were obtained with the considered strategies, and the maximum efficiency obtained was >99%. The study emphasizes that adsorption on active carbon is an effective method for bromocresol green decolorization in wastewater that can be further improved using advanced optimization methods.

The pharmacogenomics of vincristine-induced peripheral neuropathy in pediatric acute lymphoblastic leukemia patients in Serbia - a single center experience

Introduction/Objective. Vincristine (VCR) is one of the key drugs in current treatment protocols for pediatric acute lymphoblastic leukemia (ALL). By destabilizing microtubules, VCR arrests cells in metaphase, inducing apoptosis of malignant cells. VCR also causes axonal degradation and impairment of axonal transport, which leads to VCR-induced peripheral neuropathy (VIPN). This study aimed to investigate the association of five variants in pharmacogenes involved in VCR metabolism with VIPN in Serbian ALL children. We also wanted to discover candidate pharmacogenomic markers of VIPN in Serbian population. Methods. PCR and sequencing-based methodology was used to detect variants in CYP3?5, CEP72, ACTG1, MIR3117, and MIR4481 genes. Statistical analyses were performed for investigating their association with VIPN in 56 pediatric ALL patients. Population VCR pharmacogenomics analysis of 17 pharmacogenes from in-house next-generation sequencing data was also done. Data on allele frequency distribution for the European population were extracted from public databases. Results. During the treatment, 17.86% of patients developed VIPN. Association analyses have shown that none of the genetic variants contributed to the occurrence of VIPN in our study. Population pharmacogenomics study did not reveal valid candidate pharmacovariants for VIPN. Our results suggested that pre-emptive pharmacogenetic testing for VCR is not applicable presently. Conclusion. More comprehensive approaches are needed to identify the panel of genes that could explain the VIPN development after VCR administration in ALL patients. Utilizing better designed genome-wide association studies and more robust artificial intelligence-based tools would provide a panel of pharmacogenes for pre-emptive tests of VIPN to individualize therapy for ALL in children.

Precision Detection of Real-Time Conditions of Dairy Cows Using an Advanced Artificial Intelligence Hub

One of the main challenges in the adoption of artificial intelligence-based tools, such as integrated decision support systems, is the complexities of their application. This study aimed to define the relevant parameters that can be used as indicators for real-time detection of heat stress and subclinical mastitis in dairy cows. Moreover, this study aimed to demonstrate the use of a developed data-mining hub as an artificial intelligence-based tool that integrates the defined relevant information (parameters or traits) in accurately identifying the condition of the cow. A comprehensive theoretical framework of the data-mining hub is demonstrated, the selection of the parameters that were used for the data-mining hub is listed, and the relevance of the traits is discussed. The practical application of the data-mining hub has shown that using 21 parameters instead of 13 and 8 parameters resulted in a high overall accuracy of detecting heat stress and subclinical mastitis in dairy cows with a high precision effect reflecting a low percentage of misclassifying the conditions of the dairy cows. This study has developed an innovative approach in which combined information from different independent data was used to accurately detect the health and wellness status of the dairy cows. It can also be implied that an artificial intelligence-based tool such as the proposed theoretical data-mining hub of dairy cows could maximize the use of continuously generated and underutilized data in farms, thus ultimately simplifying repetitive and difficult decision-making tasks in dairy farming.

Prognostic role of computed tomography-based, artificial intelligence-driven waist skeletal muscle volume in uterine endometrial carcinoma

ObjectivesTo investigate the impact of computed tomography (CT)-based, artificial intelligence-driven waist skeletal muscle volume on survival outcomes in patients with endometrial cancer.MethodsWe retrospectively identified endometrial cancer patients who received primary surgical treatment between 2014 and 2018 and whose pre-treatment CT scans were available (n = 385). Using an artificial intelligence-based tool, the skeletal muscle area (cm2) at the third lumbar vertebra (L3) and the skeletal muscle volume (cm3) at the waist level were measured. These values were converted to the L3 skeletal muscle index (SMI) and volumetric SMI by normalisation with body height. The relationships between L3, volumetric SMIs, and survival outcomes were evaluated.ResultsSetting 39.0 cm2/m2 of L3 SMI as cut-off value for sarcopenia, sarcopenia (< 39.0 cm2/m2, n = 177) and non-sarcopenia (≥ 39.0 cm2/m2, n = 208) groups showed similar progression-free survival (PFS; p = 0.335) and overall survival (OS; p = 0.241). Using the median value, the low-volumetric SMI group (< 206.0 cm3/m3, n = 192) showed significantly worse PFS (3-year survival rate, 77.3% vs. 88.8%; p = 0.004) and OS (3-year survival rate, 92.8% vs. 99.4%; p = 0.003) than the high-volumetric SMI group (≥ 206.0 cm3/m3, n = 193). In multivariate analyses adjusted for baseline body mass index and other factors, low-volumetric SMI was identified as an independent poor prognostic factor for PFS (adjusted HR, 1.762; 95% CI, 1.051–2.953; p = 0.032) and OS (adjusted HR, 5.964; 95% CI, 1.296–27.448; p = 0.022).ConclusionsWaist skeletal muscle volume might be a novel prognostic biomarker in patients with endometrial cancer. Assessing body composition before treatment can provide important prognostic information for such patients.

ENVISION – Improve intensive care of COVID-19 patients with artificial intelligence

The Envision project aims at developing artificial intelligence-based tools for supporting the treatment of critically ill COVID-19 patients in the intensive care unit. Twelve European hospitals participate in the collection of patient data for the development and validation of the artificial intelligence tools. Ten potential use cases have been identified as development targets. Data analysis and results from expert interviews are applied to define the clinically most relevant parameters and functional use cases to be used in providing decision support for the clinicians in the intensive care units for this patient group. The resulting artificial intelligence-based tool may be beneficial in the management of the next similar epidemics, as well.

Artificial intelligence strategy integrating morphologic and architectural biomarkers provides robust diagnostic accuracy for disease progression in chronic lymphocytic leukemia

Artificial intelligence-based tools designed to assist in the diagnosis of lymphoid neoplasms remain limited. The development of such tools can add value as a diagnostic aid in the evaluation of tissue samples involved by lymphoma. A common diagnostic question is the determination of chronic lymphocytic leukemia (CLL) progression to accelerated CLL (aCLL) or transformation to diffuse large B-cell lymphoma (Richter transformation; RT) in patients who develop progressive disease. The morphologic assessment of CLL, aCLL, and RT can be diagnostically challenging. Using established diagnostic criteria of CLL progression/transformation, we designed four artificial intelligence-constructed biomarkers based on cytologic (nuclear size and nuclear intensity) and architectural (cellular density and cell to nearest-neighbor distance) features. We analyzed the predictive value of implementing these biomarkers individually and then in an iterative sequential manner to distinguish tissue samples with CLL, aCLL, and RT. Our model, based on these four morphologic biomarker attributes, achieved a robust analytic accuracy. This study suggests that biomarkers identified using artificial intelligence-based tools can be used to assist in the diagnostic evaluation of tissue samples from patients with CLL who develop aggressive disease features. © 2021 The Pathological Society of Great Britain and Ireland. Published by John Wiley & Sons, Ltd.

ARTIFICIAL INTELLIGENCE AS A PREDICTIVE TOOL TO IDENTIFY PATIENTS AT HIGH-RISK FOR NON ST ELEVATION MYOCARDIAL INFARCTION READMISSION: A RETROSPECTIVE STUDY

TOPIC: Education, Research, and Quality Improvement TYPE: Original Investigations PURPOSE: Cardiovascular death is the number one cause of death in the US. Over half of these deaths are due to myocardial infarction. While high costs and hospital admissions due to myocardial infarction are common, there is additional stress to the healthcare system with regards to readmission. In an effort to curb the cost of readmission and to improve patient outcomes, the Centers for Medicare and Medicaid Services have used 30-day hospital readmission rates as a metric to evaluate quality of care provided by hospitals across the country and to determine reimbursement. A commercially available AI machine learning tool was deployed through the electronic health record (EHR) at our institution to predict risk of readmission. The aim of our work was to assess the accuracy of an artificial intelligence-based tool in predicting which patients are at high-risk for readmission at 30 days and comparing it with a validated prediction tool, the LACE index for patients admitted with non ST elevation myocardial infarction (NSTEMI). Prospectively identifying patients hospitalized with NSTEMI who are at high risk for readmission could help prevent readmissions. METHODS: Data was collected retrospectively on patients 18 years or older with a primary diagnosis of NSTEMI and discharged from a tertiary care center from 11/26/2018 to 02/01/2020. We evaluated the effectiveness and accuracy of the proprietary AI product to identify patients at high risk for hospital readmission. This was compared with the risk predictions made by the LACE Index. The primary evaluated outcome was all-cause readmissions for HF within 30-days from the index hospitalization. The statistical method for comparison was logistic regression with LACE score as a single predictor. Sensitivities were compared after choosing a threshold that most closely matched the proprietary AI product specificity. RESULTS: A logistic regression with LACE Index score as a single predictor was used. Sensitivities were compared after choosing a threshold which resulted in the specificity most closely matching AI product specificity. After matching for specificity, the proprietary AI product had a greater sensitivity (4.7%) as compared to LACE Index score (2.7%) in detecting all-cause readmissions for NSTEMI. CONCLUSIONS: This study concludes that a proprietary AI product was a more useful predictor of readmission rates for NSTEMI as compared to prior conventional prediction tools, specifically the LACE index score. Models using AI should be implicated in clinical settings to predict readmission rates for all medical conditions to reduce readmission and overall improve patient care. We recommend that future studies should be performed to include AI models in everyday practice. CLINICAL IMPLICATIONS: Artificial intelligence can be an important asset in the future of medicine. It can be used to improve overall patient care and clinical outcomes. DISCLOSURES: No relevant relationships by Asad Cheema, source=Web Response No relevant relationships by radhika deshpande, source=Web Response No relevant relationships by Michael Gleason, source=Web Response No relevant relationships by Daniel Holtz, source=Web Response No relevant relationships by Cameron Koester, source=Web Response No relevant relationships by Abhishek Kalidas Kulkarni, source=Web Response No relevant relationships by Zurain Niaz, source=Web Response No relevant relationships by vivek prakash, source=Web Response No relevant relationships by Prashanth Singanallur, source=Web Response

ARTIFICIAL INTELLIGENCE AS A PREDICTIVE TOOL TO IDENTIFY PATIENTS WITH PULMONARY EMBOLISM AT HIGH RISK FOR 30-DAY READMISSION

TOPIC: Education, Research, and Quality Improvement TYPE: Original Investigations PURPOSE: Pulmonary Embolism (PE) is the third leading cause of cardiovascular death in the United States [1]. Venous thromboembolism (VTE) has an annual incidence of 1-2 people per 1000. The 1-year mortality can be as high as 21.6% [2]. The greatest risk factor for VTE, is a prior episode of VTE. Bikdeli et al (2019), found that though hospitalization rates for PE increased from the years 1999 to 2015, the 30-day readmission rates decreased.30-day hospital readmission rates have been used as a metric to evaluate the quality of care provided by hospitals and to determine reimbursement[5]. Risk prediction models have been developed to help identify patients at high risk of readmission with goals to reduce hospital readmissions and healthcare costs. Results with these various models have varied. Machine learning models using artificial intelligence (AI) have been developed to predict hospital readmissions. A commercially available AI/ machine learning tool was deployed through the electronic health record to predict risk of readmission. The aim of this study was to assess the accuracy of artificial intelligence-based tool in predicting which patients are at high-risk for readmission at 30 days by comparing it with a validated prediction tool, the LACE index for patients admitted with PE. METHODS: Data was collected retrospectively on patients 18 years or older with a primary diagnosis of PE and discharged from a tertiary care center from 11/26/2018 to 02/01/2020. We evaluated the effectiveness and accuracy of a proprietary AI product, to identify patients at high risk for hospital readmission and compared the effectiveness with the LACE Index. The statistical method for comparison was logistic regression with LACE score as a single predictor. Sensitivities were compared after choosing a threshold that most closely matched the proprietary AI product specificity. The primary evaluated outcome was readmissions for PE within 30-days from the index hospitalization. RESULTS: Logistic regression with LACE Index score as a single predictor was used. Sensitivities were compared after choosing a threshold which resulted in the specificity most closely matching AI product specificity. At specificity of 96.3% the AI product model had sensitivity of 19.4%. The LACE model had either 2.8 point higher (22.2%) or 5.5 point lower (13.9%) sensitivity depending on the chosen specificities of 94.7% and 97.9% respectively. We conclude that the LACE model performs roughly on par with proprietary AI tool in detecting all-cause readmission for PE. CONCLUSIONS: The LACE model performs roughly on par with proprietary AI tool in detecting 30-day readmission for PE. Proprietary AI tools may be helpful for predicting readmission rates for other diseases, in the case of PE, it did not provide a greater advantage. CLINICAL IMPLICATIONS: The LACE model performs roughly on par with proprietary AI tool in detecting all-cause readmission for PE. DISCLOSURES: No relevant relationships by Asad Cheema, source=Web Response No relevant relationships by radhika deshpande, source=Web Response No relevant relationships by Michael Gleason, source=Web Response No relevant relationships by Daniel Holtz, source=Web Response No relevant relationships by Cameron Koester, source=Web Response No relevant relationships by Abhishek Kalidas Kulkarni, source=Web Response No relevant relationships by Zurain Niaz, source=Web Response No relevant relationships by vivek prakash, source=Web Response No relevant relationships by Prashanth Singanallur, source=Web Response

Impact of Computed Tomography-Based, Artificial Intelligence-Driven Volumetric Sarcopenia on Survival Outcomes in Early Cervical Cancer.

The purpose of this study was to investigate the impact of sarcopenia and body composition change during primary treatment on survival outcomes in patients with early cervical cancer. We retrospectively identified patients diagnosed with 2009 International Federation of Gynecology and Obstetrics stage IB1-IIA2 cervical cancer who underwent primary radical hysterectomy between 2007 and 2019. From pre-treatment CT scans (n = 306), the skeletal muscle area at the third lumbar vertebra (L3) and the waist skeletal muscle volume were measured using an artificial intelligence-based tool. These values were converted to the L3 and volumetric skeletal muscle indices by normalization. We defined L3 and volumetric sarcopenia using 39.0 cm2/m2 and the first quartile (Q1) value, respectively. From pre- and post-treatment CT scan images (n = 192), changes (%) in waist skeletal muscle and fat volumes were assessed. With the use of Cox regression models, factors associated with progression-free survival (PFS) and overall survival (OS) were analyzed. Between the L3 sarcopenia and non-sarcopenia groups, no differences in PFS and OS were observed. In contrast, volumetric sarcopenia was identified as a poor prognostic factor for PFS (adjusted hazard ratio [aHR], 1.874; 95% confidence interval [CI], 1.028–3.416; p = 0.040) and OS (aHR, 3.001; 95% CI, 1.016–8.869; p = 0.047). During primary treatment, significant decreases in waist skeletal muscle (median, −3.9%; p < 0.001) and total fat (median, −5.3%; p < 0.001) were observed. Of the two components, multivariate analysis revealed that the waist fat gain was associated with worse PFS (aHR, 2.007; 95% CI, 1.009–3.993; p = 0.047). The coexistence of baseline volumetric sarcopenia and waist fat gain further deteriorated PFS (aHR, 2.853; 95% CI, 1.257–6.474; p = 0.012). In conclusion, baseline volumetric sarcopenia might be associated with poor survival outcomes in patients with early cervical cancer undergoing primary RH. Furthermore, sarcopenia patients who gained waist fat during primary treatment were at a high risk of disease recurrence.

Chatbot as a Tool for Knowledge Sharing in the Maintenance and Repair Processes

Abstract In the era of digitization and general access to Internet resources, it seems natural to expect fast, direct, and tailored access to the knowledge of interest. The research shows that the use of modern technologies is not reserved only for industrial solutions, but can be applied in common use. Solutions based on artificial intelligence can provide solutions to many problems of the modern world. This is particularly visible in the era of challenges related to ecology (e.g. minimization of paper consumption) and expectations of fast access to information regardless of place and time. Treating chatbots as a tool supporting the customer in current activities, quick problem-solving shows the potential and care for the image of the producers. Developing the functionality of virtual assistants used for marketing activities with the functionality of technical support can bring tangible benefits both in the economic and social spheres. It should be noted that electronic versions of documents, knowledge transferred in an interactive form can be easily updated and presented in different forms. This increases the attractiveness of transmitted knowledge, users can choose the appropriate form, and access to these resources becomes easier. Artificial intelligence-based tools in the form of chatbots (also called virtual assistants) seem to be a solution worthy of interest. This paper presents the process of developing a virtual assistant to support the maintenance and repair activities of small household appliances. A chatbot aims at gathering in one place and then providing dedicated knowledge resources to an individual user on a just-in-time basis.

Role of artificial intelligence in multidisciplinary imaging diagnosis of gastrointestinal diseases.

The use of artificial intelligence-based tools is regarded as a promising approach to increase clinical efficiency in diagnostic imaging, improve the interpretability of results, and support decision-making for the detection and prevention of diseases. Radiology, endoscopy and pathology images are suitable for deep-learning analysis, potentially changing the way care is delivered in gastroenterology. The aim of this review is to examine the key aspects of different neural network architectures used for the evaluation of gastrointestinal conditions, by discussing how different models behave in critical tasks, such as lesion detection or characterization (i.e. the distinction between benign and malignant lesions of the esophagus, the stomach and the colon). To this end, we provide an overview on recent achievements and future prospects in deep learning methods applied to the analysis of radiology, endoscopy and histologic whole-slide images of the gastrointestinal tract.

Artificial intelligence-based predictions in neovascular age-related macular degeneration.

Purpose of reviewPredicting treatment response and optimizing treatment regimen in patients with neovascular age-related macular degeneration (nAMD) remains challenging. Artificial intelligence-based tools have the potential to increase confidence in clinical development of new therapeutics, facilitate individual prognostic predictions, and ultimately inform treatment decisions in clinical practice.Recent findingsTo date, most advances in applying artificial intelligence to nAMD have focused on facilitating image analysis, particularly for automated segmentation, extraction, and quantification of imaging-based features from optical coherence tomography (OCT) images. No studies in our literature search evaluated whether artificial intelligence could predict the treatment regimen required for an optimal visual response for an individual patient. Challenges identified for developing artificial intelligence-based models for nAMD include the limited number of large datasets with high-quality OCT data, limiting the patient populations included in model development; lack of counterfactual data to inform how individual patients may have fared with an alternative treatment strategy; and absence of OCT data standards, impairing the development of models usable across devices.SummaryArtificial intelligence has the potential to enable powerful prognostic tools for a complex nAMD treatment landscape; however, additional work remains before these tools are applicable to informing treatment decisions for nAMD in clinical practice.

Gaps in standards for integrating artificial intelligence technologies into ophthalmic practice.

The purpose of this review is to provide an overview of healthcare standards and their relevance to multiple ophthalmic workflows, with a specific emphasis on describing gaps in standards development needed for improved integration of artificial intelligence technologies into ophthalmic practice. Healthcare standards are an essential component of data exchange and critical for clinical practice, research, and public health surveillance activities. Standards enable interoperability between clinical information systems, healthcare information exchange between institutions, and clinical decision support in a complex health information technology ecosystem. There are several gaps in standards in ophthalmology, including relatively low adoption of imaging standards, lack of use cases for integrating apps providing artificial intelligence -based decision support, lack of common data models to harmonize big data repositories, and no standards regarding interfaces and algorithmic outputs. These gaps in standards represent opportunities for future work to develop improved data flow between various elements of the digital health ecosystem. This will enable more widespread adoption and integration of artificial intelligence-based tools into clinical practice. Engagement and support from the ophthalmology community for standards development will be important for advancing this work.

Usage of Artificial Intelligence and Remote Sensing as Efficient Devices to Increase Agricultural System Yields

Artificial Intelligence is an emerging technology in the field of agriculture. Artificial Intelligence-based tools and equipment have actually taken the agriculture sector to a different level. This new technology has improved crop production and enhanced instantaneous monitoring, processing, and collection. The most recent computerized structures using remote sensing and drones have made a significant contribution to the agro-based domain. Moreover, remote sensing has the capability to support the development of farming applications with the aim of facing this main defy, via giving cyclic records on yield status during studied periods at diverse degrees and for diverse parameters. Various hi-tech, computer-supported structures are created to determine different central factors such as plant detection, yield recognition, crop quality, and several other methods. This paper includes the techniques employed for the analysis of collected information in order to enhance the productivity, forecast eventual threats, and reduce the task load on cultivators.

Prognostic implications of body composition change during primary treatment in patients with ovarian cancer: A retrospective study using an artificial intelligence-based volumetric technique

ObjectiveTo investigate the impact of changes in body composition during primary treatment on survival outcomes in patients with epithelial ovarian cancer (EOC). MethodsWe retrospectively identified patients diagnosed with EOC between 2010 and 2019. Using an artificial intelligence-based tool, the volumes of skeletal muscle, visceral fat, and subcutaneous fat were measured automatically at the waist level from pre-treatment and post-treatment computed tomography scans. Associations between changes in body mass index (BMI) and volume of each body composition component and survival outcomes were evaluated. ResultsA total of 208 patients were included. A significant decrease in BMI and waist volumes of skeletal muscle and visceral fat was observed during the primary treatment. Patients with BMI loss ≥5% showed significantly worse progression-free survival (PFS) and overall survival (OS) than those with BMI loss <5%. In multivariate analyses adjusting for clinicopathologic factors, BMI loss ≥5% was identified as an independent poor prognostic factor for PFS (adjusted HR, 1.565; 95% CI, 1.074–2.280; P = 0.020) and OS (adjusted HR, 2.754; 95% CI, 1.382–5.488; P = 0.004). Meanwhile, both muscle loss ≥10% and visceral fat loss ≥20% were associated with an increased mortality rate but did not affect disease recurrence. In multivariate analyses, muscle loss ≥10% (adjusted HR, 2.069; 95% CI, 1.055–4.058; P = 0.034) and visceral fat loss ≥20% (adjusted HR, 2.292; 95% CI, 1.023–5.133; P = 0.044) were poor prognostic factors for OS. Consistent results were observed in the advanced-stage disease subgroup (n = 173). ConclusionsChanges in BMI and waist volume of skeletal muscle and visceral fat were associated with survival outcomes in patients with EOC.

Accuracy of automated three-dimensional ultrasound imaging technique for fetal head biometry.

To evaluate the accuracy of an automated three-dimensional (3D) ultrasound technique for fetal intracranial measurements compared with manual acquisition. This was a prospective observational study of patients presenting for routine anatomical survey between 18 + 0 and 22 + 6 weeks' gestation. After providing informed consent, each patient underwent two consecutive ultrasound examinations of the fetal head, one by a sonographer and one by a physician. Each operator obtained manual measurements of the biparietal diameter (BPD), head circumference (HC), transcerebellar diameter (TCD), cisterna magna (CM) and posterior horn of the lateral ventricle (Vp), followed by automated measurements of these structures using an artificial intelligence-based tool, SonoCNS® Fetal Brain. Both operators repeated the automated approach until all five measurements were obtained in a single sweep, up to a maximum of three attempts. The accuracy of automated measurements was compared with that of manual measurements using intraclass correlation coefficients (ICC) by operator type, accounting for patient and ultrasound characteristics. One hundred and forty-three women were enrolled in the study. Median body mass index was 24.0 kg/m2 (interquartile range (IQR), 22.5-26.8 kg/m2 ) and median subcutaneous thickness was 1.6 cm (IQR, 1.3-2.0 cm). Fifteen (10%) patients had at least one prior Cesarean delivery, 17 (12%) had other abdominal surgery and 78 (55%) had an anterior placenta. Successful acquisition of the automated measurements was achieved on the first, second and third attempts in 70%, 22% and 3% of patients, respectively, by sonographers and in 76%, 16% and 3% of cases, respectively, by physicians. The automated algorithm was not able to identify and measure all five structures correctly in six (4%) and seven (5%) patients scanned by the sonographers and physicians, respectively. The ICCs reflected good reliability (0.80-0.88) of the automated compared with the manual approach for BPD and HC and poor to moderate reliability (0.23-0.50) for TCD, CM and Vp. Fetal lie, head position, placental location, maternal subcutaneous thickness and prior Cesarean section were not associated with the success or accuracy of the automated technique. Automated 3D ultrasound imaging of the fetal head using SonoCNS reliably identified and measured BPD and HC but was less consistent in accurately identifying and measuring TCD, CM and Vp. While these results are encouraging, further optimization of the automated technology is necessary prior to incorporation of the technique into routine sonographic protocols. © 2020 International Society of Ultrasound in Obstetrics and Gynecology.

Validation of an artificial intelligence-based tool for automated evaluation of RV size and function from ultrasound examinations

Funding AcknowledgementsType of funding sources: Private company. Main funding source(s): Study sponsored by DiA Imaging AnalysisBackground The assessment of the right ventricular (RV) function is an essential part of every transthoracic echocardiographic examination. It plays an important role in the diagnosis and management of many diseases and conditions. In covid-19 patients, there is evidence showing that enlarged RV and abnormal Free Wall Strain (FWS) correlate with high mortality. Assessment of the RV in the Point of Care settings can assist the differential diagnosis and provide important clinical information in early stages, close to the onset of symptoms, however, it is done qualitatively by visual estimation and thus subjective and requires high level of expertise. The presented study aims to validate the use of a novel artificial intelligence tool (LVivo RV by DiA imaging analysis) that uses deep learning and image processing algorithms to automatically evaluate RV size and function from apical 4 chamber (4CH) focused or modified ultrasound clips.Methods A retrospective study of 100 patients who underwent routine echocardiographic examination was conducted in three medical centers in US and Israel. The apical 4CH focused or modified clips were interpreted by experts to evaluate RV size and function. The End Diastolic Area (EDA) measured manually by two sonographers and the FWS measured by semi-automated Velocity Vector Imaging software (VVI by Siemens) were compared to the same parameters obtained automatically by the LVivo RV, using linear regression and Bland Altman analysis.Results 100 cases were included, 39% females and 61% males. Mean age was 64.7 [19-92]. Mean BMI was 28.1 [6.8-17.6]. 74% had pulmonary hypertension and 19% had lung disease. 36% were considered abnormal by their fractional area change values and 64% were considered normal. Three cases were non-interpretable by the physicians thus excluded from the analysis. The LVivo RV was able to process 99% of the cases. Excellent correlation was obtained for EDA between the sonographers" average of manual measurements and the automated EDA by LVivo RV with r = 0.92 (p < 0.0001, 95%CI 0.88-0.94). The bias and limits of agreement for EDA were 0.87 ± 5.76cm^2. For FWS, 4 cases were manually excluded due to insufficient image quality. The Bland Altman analysis for FWS showed small bias and limits of agreement of 0.7 ± 12.2%. A very good correlation of r= 0.78, (95% CI 0.69-0.85) was found, indicating good compatibility between the methods. The specificity and sensitivity for FWS were 80% and 77% respectively, using an optimal cutoff value of -16%, and the overall agreement was 79%.Conclusions The performance of LVivo RV demonstrated a very good agreement with manual and semi-automated quantitative methods for RV assessment. LVivo RV provides fast, accurate, objective and reproducible results and has the potential to be used at the Point of Care settings as a powerful tool for RV size and function evaluation. Figure.

Machine learning approach for automatic diagnosis of Chlorosis in Vigna mungo leaves

Viral infection in crops is something that may lead to a huge loss in crop yield as there are no known recovery procedures. Also, at the onset of yellowing in a leaf, no observable changes occur in leaf structure and geometry. Therefore, the manual inspection and diagnosis of such diseases by the framers in agricultural fields are difficult on a large scale. The automatic artificial intelligence-based tool can be used for early-stage diagnosis of viral growth, where the symptoms may be available in certain parts like leaves. An automatic computer vision-based method is proposed for the identification of yellow disease, also called Chlorosis, in a prominent leguminous crop like Vigna mungo. The proposed method involves fully automatic partitioning of plant leaves, followed by feature extraction in the spatial domain and disease prediction using a support vector machine (SVM) learned upon several training samples. The method is entirely automatic and non-destructive which can predict the classification of plant health category with an accuracy rate of 95.69% with low computation complexity. This accuracy and computational complexity can be used in real-time situations for a large scale of Vigna mungo plantation using drones and remote camera.

Artificial neural network to predict the effect of obesity on the risk of tuberculosis infection.

Background: Body weight has been implicated as a risk factor for latent tuberculosis infection (LTBI) and the active disease.Design and Methods: This study aimed to develop artificial neural network (ANN) models for predicting LTBI from body weight and other host-related disease risk factors.We used datasets from participants of the US-National Health and Nutrition Examination Survey (NHANES; 2012; n=5,156; 514 with LTBI and 4,642 controls) to develop three ANNs employing body mass index (BMI, Network I), BMI and HbA1C (as a proxy for diabetes; Network II) and BMI, HbA1C and education (as a proxy for socioeconomic status; Network III). The models were trained on n=1018 age- and sex-matched subjects equally distributed between the control and LTBI groups. The endpoint was the prediction of LTBI.Results: When data was adjusted for age, sex, diabetes and level of education, odds ratio (OR) and 95% confidence intervals (CI) for risk of LTBI with increased BMI was 0.85 (95%CI: 0.77 – 0.96, p=0.01). The three ANNs had a predictive accuracy varied from 75 to 80% with sensitivities ranged from 85% to 94% and specificities of approximately 70%. Areas under the receiver operating characteristic curve (AUC) were between 0.82 and 0.87. Optimal ANN performance was noted using BMI as a risk indicator.Conclusion: Body weight can be employed in developing artificial intelligence-based tool to predict LTBI. This can be useful in precise decision making in clinical and public health practices aiming to curb the burden of tuberculosis, e.g., in the management and monitoring of the tuberculosis prevention programs and to evaluate the impact of healthy weight on tuberculosis risk and burden.Significance for public healthThe study aims at developing artificial neural network (ANN) models to predict latent tuberculosis infection (LTBI) from body weight and other host-related disease risk factors in the general population. Three ANNs were developed and trained age- and sex-matched subjects equally distributed between the control and LTBI groups. The predictive accuracy of the three ANNs varied from 75 to 80% with sensitivities ranged from 85% to 94% and specificities of approximately 70%. Areas under the receiver operating characteristic curve (AUC) were between 0.82 and 0.87 with the optimal performance noted using BMI as a risk indicator. Body weight can be employed in developing artificial intelligence-based tool to predict LTBI in the general population and to curb the incidence of active tuberculosis as a major public health problem.

Automated diabetic retinopathy screening for primary care settings using deep learning

Diabetic Retinopathy (DR) is one of the leading causes of blindness in the United States and other high-income countries. Early detection is key to prevention, which could be achieved effectively with a fully automated screening tool performing well on clinically relevant measures in primary care settings. We have built an artificial intelligence-based tool on a cloud-based platform for large-scale screening of DR as referable or non-referable. In this paper, we aim to validate this tool built using deep learning based techniques. The cloud-based screening model was developed and tested using deep learning techniques with 88702 images from the Kaggle dataset and externally validated using 1748 high-resolution images of the retina (or fundus images) from the Messidor-2 dataset. For validation in the primary care settings, 264 images were taken prospectively from two diabetes clinics in Queens, New York. The images were uploaded to the cloud-based software for testing the automated system as compared to expert ophthalmologists' evaluations of referable DR. Measures used were area under the curve (AUC), sensitivity, and specificity of the screening model with respect to professional graders. The screening system achieved a high sensitivity of 99.21% and a specificity of 97.59% on the Kaggle test dataset with an AUC of 0.9992. The system was also externally validated in Messidor-2, where it achieved a sensitivity of 97.63% and a specificity of 99.49% (AUC, 0.9985). On primary care data, the sensitivity was 92.3% overall (12/13 referable images are correctly identified), and overall specificity was 94.8% (233/251 non-referable images). The proposed DR screening tool achieves state-of-the-art performance among the publicly available datasets: Kaggle and Messidor-2 to the best of our knowledge. The performance on various clinically relevant measures demonstrates that the tool is suitable for screening and early diagnosis of DR in primary care settings.