scholarly journals Measuring Regional Quality of Health Care Using Unsolicited Online Data: Text Analysis Study (Preprint)

2018 ◽  
Author(s):  
Roy Johannus Petrus Hendrikx ◽  
Hanneke Wil-Trees Drewes ◽  
Marieke Spreeuwenberg ◽  
Dirk Ruwaard ◽  
Caroline Baan
Keyword(s):  
Machine Learning ◽  
Health Care ◽  
Health Care Policy ◽  
Specific Information ◽  
Online Data ◽  
Online Ratings ◽  
Health Initiatives ◽  
Random Forest Models ◽  
Unsolicited Ratings

BACKGROUND Regional population management (PM) health initiatives require insight into experienced quality of care at the regional level. Unsolicited online provider ratings have shown potential for this use. This study explored the addition of comments accompanying unsolicited online ratings to regional analyses. OBJECTIVE The goal was to create additional insight for each PM initiative as well as overall comparisons between these initiatives by attempting to determine the reasoning and rationale behind a rating. METHODS The Dutch Zorgkaart database provided the unsolicited ratings from 2008 to 2017 for the analyses. All ratings included both quantitative ratings as well as qualitative text comments. Nine PM regions were used to aggregate ratings geographically. Sentiment analyses were performed by categorizing ratings into negative, neutral, and positive ratings. Per category, as well as per PM initiative, word frequencies (ie, unigrams and bigrams) were explored. Machine learning—naïve Bayes and random forest models—was applied to identify the most important predictors for rating overall sentiment and for identifying PM initiatives. RESULTS A total of 449,263 unsolicited ratings were available in the Zorgkaart database: 303,930 positive ratings, 97,739 neutral ratings, and 47,592 negative ratings. Bigrams illustrated that feeling like not being “taken seriously” was the dominant bigram in negative ratings, while bigrams in positive ratings were mostly related to listening, explaining, and perceived knowledge. Comparing bigrams between PM initiatives showed a lot of overlap but several differences were identified. Machine learning was able to predict sentiments of comments but was unable to distinguish between specific PM initiatives. CONCLUSIONS Adding information from text comments that accompany online ratings to regional evaluations provides insight for PM initiatives into the underlying reasons for ratings. Text comments provide useful overarching information for health care policy makers but due to a lot of overlap, they add little region-specific information. Specific outliers for some PM initiatives are insightful.

scholarly journals Measuring Regional Quality of Health Care Using Unsolicited Online Data: Text Analysis Study

10.2196/13053 ◽  
2019 ◽  
Vol 7 (4) ◽  
pp. e13053
Author(s):  
Roy Johannus Petrus Hendrikx ◽  
Hanneke Wil-Trees Drewes ◽  
Marieke Spreeuwenberg ◽  
Dirk Ruwaard ◽  
Caroline Baan
Keyword(s):  
Machine Learning ◽  
Health Care ◽  
Health Care Policy ◽  
Specific Information ◽  
Online Data ◽  
Online Ratings ◽  
Health Initiatives ◽  
Random Forest Models ◽  
Unsolicited Ratings

Background Regional population management (PM) health initiatives require insight into experienced quality of care at the regional level. Unsolicited online provider ratings have shown potential for this use. This study explored the addition of comments accompanying unsolicited online ratings to regional analyses. Objective The goal was to create additional insight for each PM initiative as well as overall comparisons between these initiatives by attempting to determine the reasoning and rationale behind a rating. Methods The Dutch Zorgkaart database provided the unsolicited ratings from 2008 to 2017 for the analyses. All ratings included both quantitative ratings as well as qualitative text comments. Nine PM regions were used to aggregate ratings geographically. Sentiment analyses were performed by categorizing ratings into negative, neutral, and positive ratings. Per category, as well as per PM initiative, word frequencies (ie, unigrams and bigrams) were explored. Machine learning—naïve Bayes and random forest models—was applied to identify the most important predictors for rating overall sentiment and for identifying PM initiatives. Results A total of 449,263 unsolicited ratings were available in the Zorgkaart database: 303,930 positive ratings, 97,739 neutral ratings, and 47,592 negative ratings. Bigrams illustrated that feeling like not being “taken seriously” was the dominant bigram in negative ratings, while bigrams in positive ratings were mostly related to listening, explaining, and perceived knowledge. Comparing bigrams between PM initiatives showed a lot of overlap but several differences were identified. Machine learning was able to predict sentiments of comments but was unable to distinguish between specific PM initiatives. Conclusions Adding information from text comments that accompany online ratings to regional evaluations provides insight for PM initiatives into the underlying reasons for ratings. Text comments provide useful overarching information for health care policy makers but due to a lot of overlap, they add little region-specific information. Specific outliers for some PM initiatives are insightful.

scholarly journals Automatic Identification of Information Quality Metrics in Health News Stories

2020 ◽  
Vol 8 ◽  
Author(s):  
Majed Al-Jefri ◽  
Roger Evans ◽  
Joon Lee ◽  
Pietro Ghezzi
Keyword(s):  
Machine Learning ◽  
Health Care ◽  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Information Quality ◽  
Evaluation Process ◽  
Health News ◽  
News Stories

Objective: Many online and printed media publish health news of questionable trustworthiness and it may be difficult for laypersons to determine the information quality of such articles. The purpose of this work was to propose a methodology for the automatic assessment of the quality of health-related news stories using natural language processing and machine learning.Materials and Methods: We used a database from the website HealthNewsReview.org that aims to improve the public dialogue about health care. HealthNewsReview.org developed a set of criteria to critically analyze health care interventions' claims. In this work, we attempt to automate the evaluation process by identifying the indicators of those criteria using natural language processing-based machine learning on a corpus of more than 1,300 news stories. We explored features ranging from simple n-grams to more advanced linguistic features and optimized the feature selection for each task. Additionally, we experimented with the use of pre-trained natural language model BERT.Results: For some criteria, such as mention of costs, benefits, harms, and “disease-mongering,” the evaluation results were promising with an F1 measure reaching 81.94%, while for others the results were less satisfactory due to the dataset size, the need of external knowledge, or the subjectivity in the evaluation process.Conclusion: These used criteria are more challenging than those addressed by previous work, and our aim was to investigate how much more difficult the machine learning task was, and how and why it varied between criteria. For some criteria, the obtained results were promising; however, automated evaluation of the other criteria may not yet replace the manual evaluation process where human experts interpret text senses and make use of external knowledge in their assessment.

Legal and policy lessons from the Schiavo case: Is our right to choose the medical care we want seriously at risk?

2006 ◽  
Vol 4 (2) ◽  
pp. 145-153 ◽  
Author(s):  
ZITA LAZZARINI ◽  
STEPHEN ARONS ◽  
ALICE WISNIEWSKI
Keyword(s):  
Health Care ◽  
Medical Care ◽  
Health Care Policy ◽  
Legal Status ◽  
Medical Futility ◽  
Medical Practitioners ◽  
Political Interests ◽  
Quality Of Medical Care ◽  
The Individual

The article explores the individual patient's right to refuse, withdraw, or insist on medical treatment where there is conflict over these issues involving health care personnel or institutions, family members, legal requirements, or third parties concerned with public policy or religious/ideological/political interests. Issues of physician assistance in dying and medical futility are considered. The basis and the current legal status of these rights is examined, and it is concluded that threats to the autonomy of patients, to the privacy of the doctor/patient relationship, and to the quality of medical care should be taken seriously by individuals, medical practitioners, and others concerned with developing and maintaining reasonable, effective, and ethical health care policy.

Changes in the Perception of Health Care Policy and Delivery Among Manitoba Elders During the Downsizing of the Hospital Sector

2000 ◽  
Vol 19 (1) ◽  
pp. 18-34 ◽  
Author(s):  
Evelyn Shapiro ◽  
Robert B. Tate ◽  
Brock Wright ◽  
Joy Plohman
Keyword(s):  
Health Care ◽  
Older Persons ◽  
Health Care Policy ◽  
Special Interest Groups ◽  
Qualité Des Soins ◽  
Political Issue ◽  
Hospital Sector ◽  
Soins De Santé ◽  
One Year

RésuméDans un monde où l'assurance des soins de santé est universelle, la fermeture de lits d'hôpitaux se transforme inévitablement en un dossier politique chaud et les médias deviennent le véhicule du débat et des pressions exercées par certains groupes d'intérêt. Cette étude repose sur les données d'une interview d'aîné(e)s du Manitoba avant, puis un an après, la diminution substantielle du secteur hospitalier à Winnipeg. Nous comparons les réponses des résidents de Winnipeg à celles de résidents de l'extérieur de Winnipeg à des questions sur leurs opinions concernant la qualité générale des soins de santé et l'aecès aux soins hospitaliers. Nous comparons également les réponses aux mêmes questions données par des aîné(e)s qui ont été hospitalisés avant la première interview, par d'autres qui ont été hospitalisés avant la seconde interview et enfin par des aîné(e)s qui n'ont pas été hospitalisés. Bien qu'il n'y ait pas eu de fermeture de lits d'hôpitaux à l'extérieur de Winnipeg, l'opinion sur la qualité des soins chez les citoyens de Winnipeg et ceux de l'extérieur était moins positive après la réduction de Winnipeg et la publicité négative dont l'événement a été entouré. Cependant, les opinions sur la qualité et l'accès de ceux qui avaient été hospitalisés alors que les lits se fermaient étaient sensiblement plus positives que celles des ainé(e)s qui avaient été hospitalisés avant la fermeture ou qui n'avaient pas été hospitalisés.AbstractIn a universally-insured health care system, closing hospital beds inevitably becomes a hot political issue and the media often become the vehicle for debate and pressure from special interest groups. This study uses data from a representative sample of Manitoba older persons, interviewed before and again one year after the substantial downsizing of the hospital sector in Winnipeg. We compare the responses of Winnipeg residents with those of non-Winnipeg residents to questions about their opinion regarding the overall quality of health care and access to hospital care. Also compared were the responses to the same questions by older persons who were hospitalized before the first interview, those hospitalized before the second interview and those who were not hospitalized. Despite experiencing no bed closures outside Winnipeg, the opinions about the overall quality of care among both non-Winnipeggers and Winnipeggers were less favourable after the Winnipeg downsizing and the accompanying negative publicity. However, the opinions about quality and access among those who were actually hospitalized when most of the beds were being closed were significantly more favourable than among those hospitalized before the bed closures or not hospitalized at all.

A Call to Arms: Economic Barriers to Optimal Dialysis Care

2000 ◽  
Vol 20 (1) ◽  
pp. 7-12 ◽  
Author(s):  
Philip A. McFarlane ◽  
David C. Mendelssohn
Keyword(s):  
Health Care ◽  
Renal Disease ◽  
Health Care Policy ◽  
Unit Cost ◽  
Cost Effective ◽  
Patient Choice ◽  
Health Care Economics ◽  
Dialysis Modality ◽  
Stage Renal Disease

Epidemic growth rates and the enormous cost of dialysis pressure end-stage renal disease (ESRD) delivery systems around the world. Payers of dialysis services can constrain costs through ( 1 ) limiting access to dialysis, ( 2 ) reducing the quality of dialysis, and ( 3 ) placing constraints on modality distribution. In order to secure the necessary resources for ESRD care, we propose that the nephrology community consider the following suggestions: First, future leaders in dialysis should acquire additional advanced training in innovative pathways such as health care economics, business and health care administration, and health care policy. Second, the international nephrology community must strongly engage in ongoing advocacy for accessible, high quality, cost-effective care. Third, efforts should be made to better define and then implement optimal dialysis modality distributions that maximize patient outcomes but limit unnecessary costs. Fourth, industry should be encouraged to lower the unit cost of dialysis, allowing for improved access to dialysis, especially in developing countries. Fifth, research should be encouraged that seeks to identify measures that will reduce dialysis costs but will not impair quality of care. Finally, early referral of patients with progressive renal disease to nephrology clinics, empowerment of informed patient choice of dialysis modality, and proper and timely access creation should be encouraged and can be expected to help limit overall expenditures. Ongoing efforts in these areas by the nephrology community will be essential if we are to overcome the challenges of ESRD growth in this new decade.

scholarly journals To Enhance the Quality of HCRS using Fuzzy-Genetic Approach

2022 ◽  
Author(s):  
Latha Banda ◽  
Karan Singh ◽  
Vikash Arya ◽  
Devendra Gautam ◽  
Ali Ahmadian
Keyword(s):  
Machine Learning ◽  
Genetic Algorithm ◽  
Health Care ◽  
Medical Data ◽  
Machine Learning Algorithms ◽  
Genetic Approach ◽  
Data Set ◽  
Proposed Model ◽  
Fuzzy Genetic

Abstract Social media is recent generation of Recommender Systems (RS). Health Care Recommender System (HCRS) term used to analyse the medical data and then predict the disease of a patient with the help of various techniques used in RS. To ensure the quality and trustworthiness of medical data, machine learning algorithms are applied. Even though, there is a much gap between health care diagnosis and IT solutions. To evade this gap, the hybrid Fuzzy-genetic approach is used in HCRS. In this, Genetic algorithm is used for similarity computations with the help of mutation and crossover operators. Later fuzzy rules are generated for the data set with the additional personalized information of a user. Considering these approaches, the proposed model enhances the quality of recommendation in HCRS.

scholarly journals Current Status and Future Directions of mHealth Interventions for Health System Strengthening in India: Systematic Review (Preprint)

2018 ◽  
Author(s):  
Abhinav Bassi ◽  
Oommen John ◽  
Devarsetty Praveen ◽  
Pallab K Maulik ◽  
Rajmohan Panda ◽  
...  
Keyword(s):  
Health Care ◽  
Service Delivery ◽  
Health System ◽  
Health Systems ◽  
Health Care Delivery ◽  
Care Delivery ◽  
Health Systems Strengthening ◽  
Noncommunicable Disease ◽  
Health Initiatives

BACKGROUND With the exponential increase in mobile phone users in India, a large number of public health initiatives are leveraging information technology and mobile devices for health care delivery. Given the considerable financial and human resources being invested in these initiatives, it is important to ascertain their role in strengthening health care systems. OBJECTIVE We undertook this review to identify the published mobile health (mHealth) or telemedicine initiatives in India in terms of their current role in health systems strengthening. The review classifies these initiatives based on the disease areas, geographical distribution, and target users and assesses the quality of the available literature. METHODS A search of the literature was done to identify mHealth or telemedicine articles published between January 1997 and June 2017 from India. The electronic bibliographic databases and registries searched included MEDLINE, EMBASE, Joanna Briggs Institute Database, and Clinical Trial Registry of India. The World Health Organization health system building block framework was used to categorize the published initiatives as per their role in the health system. Quality assessment of the selected articles was done using the Cochrane risk of bias assessment and National Institutes of Health, US tools. RESULTS The combined search strategies yielded 2150 citations out of which 318 articles were included (primary research articles=125; reviews and system architectural, case studies, and opinion articles=193). A sharp increase was seen after 2012, driven primarily by noncommunicable disease–focused articles. Majority of the primary studies had their sites in the south Indian states, with no published articles from Jammu and Kashmir and north-eastern parts of India. Service delivery was the primary focus of 57.6% (72/125) of the selected articles. A majority of these articles had their focus on 1 (36.0%, 45/125) or 2 (45.6%, 57/125) domains of health system, most frequently service delivery and health workforce. Initiatives commonly used client education as a tool for improving the health system. More than 91.2% (114/125) of the studies, which lacked a sample size justification, had used convenience sampling. Methodological rigor of the selected trials (n=11) was assessed to be poor as majority of the studies had a high risk for bias in at least 2 categories. CONCLUSIONS In conclusion, mHealth initiatives are being increasingly tested to improve health care delivery in India. Our review highlights the poor quality of the current evidence base and an urgent need for focused research aimed at generating high-quality evidence on the efficacy, user acceptability, and cost-effectiveness of mHealth interventions aimed toward health systems strengthening. A pragmatic approach would be to include an implementation research component into the existing and proposed digital health initiatives to support the generation of evidence for health systems strengthening on strategically important outcomes.

Sign in / Sign up

Export Citation Format

Share Document