A real-time network-based approach for analysing best–worst data types

Best–worst scaling is a widespread approach in market research used for collecting data on the needs and preferences of people. However, the current preparation of its design and the analysis of the data depends on complex statistical methods. One of the most commonly used models for estimating individual preference probabilities is the hierarchical Bayes model, which can only be applied after the data collection phase. This type of calculation needs more infrastructural background and a large sample to provide accurate estimations. Here, we introduce a new application that enables fast calculations and individual-level real-time estimations, which also has a great potential to ask additional questions depending on the respondent’s answers during live interviews. Our network-based approach (integrating the PageRank algorithm) works well for online surveys, and it supports our dynamic and adaptive, real-time evaluation (DART) of best–worst data types, and results in more relevant decision making in marketing.

Out of Control: Growth and Indirect Discrimination in Ada and Canyon Counties' Rental Processes

Minimal research has been done on race in evictions and the rental process, and those studies that have been performed have been limited to narrow geographical regions (Thomas, 2017; Desmond, 2016). Additionally, research hasn’t been extended to Idaho, a state that is recognized for its rapid population growth. Research on evictions’ impact on New Americans is essentially nonexistent. Employing the Naïve Bayes Model, a modification of the Naïve Bayes Model, and content analysis of interviews, this study sought to uncover the impact of racial discrimination and growth in the eviction process. The results proved that black and Latinx minorities are evicted at higher rates than their white and Asian counterparts and that a lack of tenant protections and rapidly increasing housing prices, among other things, have played pivotal roles in Idaho’s eviction rates, specifically of racial minorities.

An automatic diagnostic system for pediatric genetic disorders developed by linking genotype and phenotype information

Background: Quantitatively describe the phenotype spectrum of pediatric disorders has remarkable power to assist genetic diagnosis. Here, we developed a matrix which provide this quantitative description of genomic-phenotypic association and constructed an automatic system to assist the diagnose of pediatric genetic disorders. Results: 20,580 patients with genetic diagnostic conclusions from the Children's Hospital of Fudan University during 2015 to 2019 were reviewed. Based on that, a phenotype spectrum matrix -- cGPS (clinical Gene's Preferential Synopsis) -- was designed by Naive Bayes model to quantitatively describe genes' contribution to clinical phenotype categories. Further, for patients who have both genomic and phenotype data, we designed a ConsistencyScore based on cGPS. ConsistencyScore aimed to figure out genes that were more likely to be the genetic causal of the patient's phenotype and to prioritize the causal gene among all candidates. When using the ConsistencyScore in each sample to predict the causal gene for patients, the AUC could reach 0.975 for ROC (95% CI 0.972-0.976 and 0.575 for precision-recall curve (95% CI 0.541-0.604). Further, the performance of ConsistencyScore was evaluated on another cohort with 2,323 patients, which could rank the causal gene of the patient as the first for 75.00% (95% CI 70.95%-79.07%) of the 296 positively genetic diagnosed patients. The causal gene of 97.64% (95% CI 95.95%-99.32%) patients could be ranked within top 10 by ConsistencyScore, which is much higher than existing algorithms (p <0.001). Conclusions: cGPS and ConsistencyScore offer useful tools to prioritize disease-causing genes for pediatric disorders and show great potential in clinical applications.

Restaurant Review Classification Using Naives Bayes Model

Numerous restaurants fight for the best quality for clients in the increasingly competitive restaurant sector. A restaurant is a business that demands more attention to customer care through continually enhancing customer service. The situation has an effect on the restaurant’s brand image, which is shaped by whether or not consumers are happy. Restaurant patrons may choose to benefit from others’ experiences by evaluating restaurants based on a range of factors, including meal quality, service, ambience, discounts, and deservingness. Users may leave reviews and ratings of companies and services, or just comment on other reviews. From one standpoint, bad (negative) reviews may influence how potential consumers make purchasing decisions. Sentiment analysis is a technique for determining the emotional content of a text that may be used to evaluate product/service reviews. Additionally, we may categorise them as positive or negative emotions. Understanding how the general public feels about various entities and products enables more relevant marketing, recommendation systems, and market trend research. Prepossessed data is collected, and then categorization is performed using a confusion matrix. This study enables us to create a report on the public’s perception of a particular restaurant. We developed a machine learning model and trained it using Bernoulli’s Naive Bayes classifier. Additionally, we evaluated the classifier’s performance on the test sample using evaluation matrices such as prediction, accuracy, recall, and F1 score. Customer review research has a significant influence on a business’s growth strategy.

Machine Learning increases efficiency and timeliness of National Procedural Clinical Standards KPI reporting (Preprint)

BACKGROUND Background: Quality Assurance activities are frequently dependent on manual assessment of text-based records. Increasingly, these records have digital structures that may be amenable to computer analysis. We used the Australian Commission for Safety and Quality in Healthcare (ACSQHC) National Clinical Care Colonoscopy standard reporting requirement as a proof of concept for an analytics process to streamline and reduce manual reporting overheads. The endoscopy unit performs approximately 4,500 colonoscopies (mainly outpatient) per year. Quarterly reporting of colonoscopy outcomes requires approximately 30 hours of manual data abstraction, collation and combination from a variety of electronic databases. The most time consuming is manual retrieval and abstraction of histopathology records from the EMR. OBJECTIVE 1. To reduce the manual overheads of quarterly National Standards KPI reporting for colonoscopy compliance using an automated data pipeline and Artificial Intelligence tools. 2. The service also wished to minimise the risk of failure to follow up in new cancer diagnoses for outpatient colonoscopies. 3. To develop a data and analytic pipeline that would be easily re-purposed for additional standards, audit and research projects. METHODS A data pipeline and analysis environment were established in the hospitals’ secure Microsoft Azure databricks resource. A Training data set of 1000 colonoscopies was extracted using from the procedural Provation database using the the ProvationMD ® reporting tool and linked to relevant histopathology reports provided from the Clinical Research Data Warehouse (CRDW). The Machine Learning (ML) training data set was created when histopathological reports were manually coded by Gastroenterology Registrars & nurses into the following categories: Adenoma Clinically Significant Sessile Serrated Adenoma Cancer Adequate Bowel Preparation Complete examination A variety of Natural Language Processing (NLP) & ML models were assessed and refined to minimize error rate. Sensitivity was prioritised for the diagnosis of Cancer to minimize missed cases. Reporting to clinicians and quality co-ordinators was established using Microsoft Power BI. RESULTS The Naïve Bayes model for multinomial data resulted in high accuracy, but impacted recall. Sensitivity improved using a virtual ensemble approach, layering models within the processing pipeline and maximised using Microsoft’s ® Text Analytics – Healthcare NLP model with our custom Naïve Bayes model. F1 scores between 0.89 and 0.93 were achieved. The algorithm checks daily for new data and performs the analysis. Quarterly analysis and reporting time decreased from 30 hours to less than 5 minutes and reports can now be continuously updated in the Microsoft Power BI reporting portal. CONCLUSIONS Advanced analytic techniques can be deployed for mandatory quality reporting in a secure, cloud based, hospital data domain. The cost was far less than the manual processes it replaces. Reporting is more timely as it is automated. The potential for training such algorithms for other QA reporting is high. Text based research and audit within the free text domain of the EMR clinical documentation also becomes possible. CLINICALTRIAL Not applicable

Mining the crime data using naïve Bayes model

<p>A massive number of documents on crime has been handled by police departments worldwide and today's criminals are becoming technologically elegant. One obstacle faced by law enforcement is the complexity of processing voluminous crime data. Approximately 439 crimes have been registered in sanchez mira municipality in the past seven years. Police officers have no clear view as to the pattern crimes in the municipality, peak hours, months of the commission and the location where the crimes are concentrated. The naïve Bayes modelis a classification algorithm using the Rapid miner auto model which is used and analyze the crime data set. This approach helps to recognize crime trends and of which, most of the crimes committed were a violation of special penal laws. The month of May has the highest for index and non-index crimes and Tuesday as for the day of crimes. Hotspots were barangay centro 1 for non-index crimes and barangay centro 2 for index crimes. Most non-index crimes committed were violations of special law and for index crime rape recorded the highest crime and usually occurs at 2 o’clock in the afternoon. The crime outcome takes various decisions to maximize the efficacy of crime solutions.</p>