Objective To review and present the relationship and need for integrating EMR, EHR and PHR data, by highlighting its use and value challenges and threats. Method Critical overview of the literature. Results Electronic Medical Records (EMR) and Electronic Health Records (EHR) are used by physicians to improve quality of care and contain costs. Whereas EMR is usually considered an internal organizational system, the EHR is defined as an inter-organizational system. Recently, a computerized platform for patient-centered medical care known as Personal health records (PHR) was introduced, as an enabler for self-management of medical records. PHRs are online systems used by patients. Their transparency of information should lead to better informed and engaged patients. PHR, EMR and EHR can reside on different platforms under various technologies and standards. Although EMR contains local information and provides fast and accurate delivery, the major advantage of EHR in medical practice is the availability of cross-provider medical information. Patient-centered health initiatives such as PHR enable the integration of the prime information components in the EMR and the EHR systems. Conclusion This integration of medical information combines demographic, lifestyle and behavioral data with health records, thus providing a comprehensive view that coincides with the definition of patient-centered medical care. It can lead to a dramatic amelioration in personalized care as well as public health decision-making, resulting in improved health and wellness, but also poses serious challenges and threats to security and privacy.

A review of PHR, EMR and EHR integration: A more personalized healthcare and public health policy

Data mining and machine learning techniques applied to public health problems: A bibliometric analysis from 2009 to 2018

Data mining techniques are applied in many applications as a standard procedure for analyzing the large volume of available data, extracting useful information and knowledge to support the major decision-making processes. Diabetes mellitus is a continuing, general, deadly syndrome occurring all around the world. It is characterized by hyperglycemia occurring due to abnormalities in insulin secretion which would in turn result in irregular rise of glucose level. In recent years, the impact of Diabetes mellitus has increased to a great extent especially in developing countries like India. This is mainly due to the irregularities in the food habits and life style. Thus, early diagnosis and classification of this deadly disease has become an active area of research in the last decade. Numerous clustering and classifications techniques are available in the literature to visualize temporal data to identify trends for controlling diabetes mellitus. This work presents an experimental study of several algorithms which classifies Diabetes Mellitus data effectively. The existing algorithms are analyzed thoroughly to identify their advantages and limitations. The performance assessment of the existing algorithms is carried out to determine the best approach.

/pdf/a-comparative-analysis-on-the-evaluation-of-classification-42xijq47gv.pdf

A Comparative Analysis on the Evaluation of Classification Algorithms in the Prediction of Diabetes

Background: Though artificial intelligence (AI) has the potential to augment the patient-physician relationship in primary care, bias in intelligent health care systems has the potential to differentially impact vulnerable patient populations.
Objective: The purpose of this scoping review is to summarize the extent to which AI systems in primary care examine the inherent bias toward or against vulnerable populations and appraise how these systems have mitigated the impact of such biases during their development.
Methods: We will conduct a search update from an existing scoping review to identify studies on AI and primary care in the following databases: Medline-OVID, Embase, CINAHL, Cochrane Library, Web of Science, Scopus, IEEE Xplore, ACM Digital Library, MathSciNet, AAAI, and arXiv. Two screeners will independently review all abstracts, titles, and full-text articles. The team will extract data using a structured data extraction form and synthesize the results in accordance with PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) guidelines.
Results: This review will provide an assessment of the current state of health care equity within AI for primary care. Specifically, we will identify the degree to which vulnerable patients have been included, assess how bias is interpreted and documented, and understand the extent to which harmful biases are addressed. As of October 2020, the scoping review is in the title- and abstract-screening stage. The results are expected to be submitted for publication in fall 2021.
Conclusions: AI applications in primary care are becoming an increasingly common tool in health care delivery and in preventative care efforts for underserved populations. This scoping review would potentially show the extent to which studies on AI in primary care employ a health equity lens and take steps to mitigate bias.

Health Equity in Artificial Intelligence and Primary Care Research: Protocol for a Scoping Review

The objective of this paper is to assess and synthesize the published literature related to the application of data analytics, big data, data mining and machine learning to healthcare engineering systems.,A systematic literature review (SLR) was conducted to obtain the most relevant papers related to the research study from three different platforms: EBSCOhost, ProQuest and Scopus. The literature was assessed and synthesized, conducting analysis associated with the publications, authors and content.,From the SLR, 576 publications were identified and analyzed. The research area seems to show the characteristics of a growing field with new research areas evolving and applications being explored. In addition, the main authors and collaboration groups publishing in this research area were identified throughout a social network analysis. This could lead new and current authors to identify researchers with common interests on the field.,The use of the SLR methodology does not guarantee that all relevant publications related to the research are covered and analyzed. However, the authors' previous knowledge and the nature of the publications were used to select different platforms.,To the best of the authors' knowledge, this paper represents the most comprehensive literature-based study on the fields of data analytics, big data, data mining and machine learning applied to healthcare engineering systems.

A systematic literature review of data science, data analytics and machine learning applied to healthcare engineering systems

Public health care systems routinely collect health-related data from the population. This data can be analyzed using data mining techniques to find novel, interesting patterns, which could help formulate effective public health policies and interventions. The occurrence of chronic illness is rare in the population and the effect of this class imbalance, on the performance of various classifiers was studied. The objective of this work is to identify the best classifiers for class imbalanced health datasets through a cost-based comparison of classifier performance. The popular, open-source data mining tool WEKA, was used to build a variety of core classifiers as well as classifier ensembles, to evaluate the classifiers’ performance. The unequal misclassification costs were represented in a cost matrix, and cost-benefit analysis was also performed.  In another experiment, various sampling methods such as under-sampling, over-sampling, and SMOTE was performed to balance the class distribution in the dataset, and the costs were compared. The Bayesian classifiers performed well with a high recall, low number of false negatives and were not affected by the class imbalance. Results confirm that total cost of Bayesian classifiers can be further reduced using cost-sensitive learning methods. Classifiers built using the random under-sampled dataset showed a dramatic drop in costs and high classification accuracy.

/pdf/learning-from-a-class-imbalanced-public-health-dataset-a-2wm0gq3tim.pdf

Learning from a Class Imbalanced Public Health Dataset: a Cost-based Comparison of Classifier Performance

Many health care providers have adopted Electronic Health Records to represent patient's health conditions. A patient visits many health care facilities like hospitals, private practices or primary health care centres for treatment of different ailments. There is a need to integrate the patient's health data from various sources, to provide a comprehensive view of the patient's health status. This data integration has to be seamless and unaffected by technology issues related to the data representation or exchange. The authors modeled data requirements and designed a Public Health Ontology to represent domain knowledge. The relational health data was mapped into instances of the Public Health Ontology to form a knowledge base of health records. The quality of the ontology and the knowledge base was analyzed using a metric based approach. The semantic representation enables interoperability and results prove that the knowledge base is rich in detail and diversity. The Public Health Ontology uses standardized medical terminology and unique patient identifiers to enable data integration which can enable a complete new level of reasoning over health data. However the public health knowledge base is fairly isolated and it needs to be connected to well-known ontology for meaningful use of the public health knowledge base.

Ontology based semantic representation for Public Health data integration

Patients go to multiple healthcare providers for treatment, and their health data is generally distributed among providers. The distributed health data and the decentralized health care system structure make it ideal for blockchain-based health information systems. The authors consider the referral use case; for instance, a patient goes to his primary health Centre (PHC) for treatment and is referred to a hospital. Authentication is usually done using certificates or key cryptography, which could become cumbersome when multiple parties are involved in a healthcare interaction. The security requirements were defined, and a novel multi-party, mutual patient identity authentication scheme called “Distributed Dynamic Mutual Identity Authentication (DDMIA)” was proposed for the referral use case in a blockchain-based e-health network. The DDMIA enables the PHC to authenticate the patient to the referred hospital. The DDMIA scheme was designed using Elliptic Curve Cryptography. It was proven to be secure by assuming the hardness of the elliptic curve discrete log problem (ECDLP) and Elliptic curve computational Diffie–Hellman problem (ECDH) using CK-Model. The formal security analysis using BAN logic proved that the sessions are secure after authentication. The DDMIA scheme was simulated in the AVISPA tool and proven safe against all active attacks. The scheme allows a patient to be authenticated by multiple parties without registering with all parties. It eliminates the need for multiple registration centers as well as digital certificates. Hence, the DDMIA scheme can be implemented for similar multiparty authentication requirements in blockchain-based networks.

DDMIA: Distributed Dynamic Mutual Identity Authentication for Referrals in Blockchain-Based Health Care Networks

Primary health centres (PHCs) across India provide antenatal, delivery and postnatal healthcare to expecting mothers. In case the expecting mother suffers from a pregnancy-related medical condition that cannot be treated at the PHC, she is referred to the nearest specialist or secondary hospital. The objective of this paper is to present a minimal, affordable and interoperable extensible markup language (XML)-based electronic referral (e-referral) prototype. The e-referral system transfers patient information from the PHC to a specialist at any hospital, for pregnancy-related medical problems. A subject matter expert (SME) panel was formed to identify the minimal dataset and an optimal format for e-referrals in the maternal use case. The data quality of the proposed e-referral information was measured. The e-referral data structures were proven to be complete. The interoperability level achieved by the e-referral prototype was quantified. The minimal e-referral is human processable or syntactically interoperable. The XML-based e-referral data can be very easily integrated with existing hospital information systems.

A minimal e-referral for meaningful share of maternal health information in public health scenarios

Millions of adults suffer from a condition called stuttering or stammering. The authors propose the use of a Speech Assistance tool, which helps stuttered speakers achieve higher fluency and a slower rate of speech. The fluency is achieved by adhering to the proposed fluency enhancing technique. The fluency enhancing technique (FET) is inspired by fluency shaping methods and requires the speaker to use a rhythmic method called gentle onset with words and a slower rate of speech. In the training mode, the Speech assistance tool trains an artificial neural network to identify the speaker's FET based words vs. the non-FET or normal words. The audio features are represented using Mel-Frequency Cepstral Coefficients (MFCC), which captures the prosody of the spoken words. In the real-life conversation mode, the speaker gets visual cues to ensure that the speaker adheres to the proposed FET technique. The tool also performs disfluency analysis and provides feedback to users, in terms of FET words ratio, the disfluency score for a hundred words, and the speech rate. The tool also logs the disfluencies periodically to help the speaker track his/her fluency over time. The DTW analysis of MFCC features proven that there is a clear difference in the prosody of the FET and non-FET words. While using the proposed FET based tool, the fluency of the speaker increases and slower speech rate is also achieved. The Speech assistance tool can be used along with Cognitive Behavior Therapy to help rehabilitate adults who stutter.

Rohini R. Rao

Papers

Learning from a Class Imbalanced Public Health Dataset: a Cost-based Comparison of Classifier Performance

Ontology based semantic representation for Public Health data integration

DDMIA: Distributed Dynamic Mutual Identity Authentication for Referrals in Blockchain-Based Health Care Networks

A minimal e-referral for meaningful share of maternal health information in public health scenarios

Neural Network based Speech Assistance tool to enhance the fluency of adults who stutter