Dataset Information

Preferences for Artificial Intelligence Clinicians Before and During the COVID-19 Pandemic: Discrete Choice Experiment and Propensity Score Matching Study.

ABSTRACT:

Background

Artificial intelligence (AI) methods can potentially be used to relieve the pressure that the COVID-19 pandemic has exerted on public health. In cases of medical resource shortages caused by the pandemic, changes in people's preferences for AI clinicians and traditional clinicians are worth exploring.

Objective

We aimed to quantify and compare people's preferences for AI clinicians and traditional clinicians before and during the COVID-19 pandemic, and to assess whether people's preferences were affected by the pressure of pandemic.

Methods

We used the propensity score matching method to match two different groups of respondents with similar demographic characteristics. Respondents were recruited in 2017 and 2020. A total of 2048 respondents (2017: n=1520; 2020: n=528) completed the questionnaire and were included in the analysis. Multinomial logit models and latent class models were used to assess people's preferences for different diagnosis methods.

Results

In total, 84.7% (1115/1317) of respondents in the 2017 group and 91.3% (482/528) of respondents in the 2020 group were confident that AI diagnosis methods would outperform human clinician diagnosis methods in the future. Both groups of matched respondents believed that the most important attribute of diagnosis was accuracy, and they preferred to receive combined diagnoses from both AI and human clinicians (2017: odds ratio [OR] 1.645, 95% CI 1.535-1.763; P<.001; 2020: OR 1.513, 95% CI 1.413-1.621; P<.001; reference: clinician diagnoses). The latent class model identified three classes with different attribute priorities. In class 1, preferences for combined diagnoses and accuracy remained constant in 2017 and 2020, and high accuracy (eg, 100% accuracy in 2017: OR 1.357, 95% CI 1.164-1.581) was preferred. In class 2, the matched data from 2017 were similar to those from 2020; combined diagnoses from both AI and human clinicians (2017: OR 1.204, 95% CI 1.039-1.394; P=.011; 2020: OR 2.009, 95% CI 1.826-2.211; P<.001; reference: clinician diagnoses) and an outpatient waiting time of 20 minutes (2017: OR 1.349, 95% CI 1.065-1.708; P<.001; 2020: OR 1.488, 95% CI 1.287-1.721; P<.001; reference: 0 minutes) were consistently preferred. In class 3, the respondents in the 2017 and 2020 groups preferred different diagnosis methods; respondents in the 2017 group preferred clinician diagnoses, whereas respondents in the 2020 group preferred AI diagnoses. In the latent class, which was stratified according to sex, all male and female respondents in the 2017 and 2020 groups believed that accuracy was the most important attribute of diagnosis.

Conclusions

Individuals' preferences for receiving clinical diagnoses from AI and human clinicians were generally unaffected by the pandemic. Respondents believed that accuracy and expense were the most important attributes of diagnosis. These findings can be used to guide policies that are relevant to the development of AI-based health care.

SUBMITTER: Liu T

PROVIDER: S-EPMC7927951 | biostudies-literature | 2021 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Preferences for Artificial Intelligence Clinicians Before and During the COVID-19 Pandemic: Discrete Choice Experiment and Propensity Score Matching Study.

Liu Taoran T Tsang Winghei W Xie Yifei Y Tian Kang K Huang Fengqiu F Chen Yanhui Y Lau Oiying O Feng Guanrui G Du Jianhao J Chu Bojia B Shi Tingyu T Zhao Junjie J Cai Yiming Y Hu Xueyan X Akinwunmi Babatunde B Huang Jian J Zhang Casper J P CJP Ming Wai-Kit WK

Journal of medical Internet research 20210302 3

<h4>Background</h4>Artificial intelligence (AI) methods can potentially be used to relieve the pressure that the COVID-19 pandemic has exerted on public health. In cases of medical resource shortages caused by the pandemic, changes in people's preferences for AI clinicians and traditional clinicians are worth exploring.<h4>Objective</h4>We aimed to quantify and compare people's preferences for AI clinicians and traditional clinicians before and during the COVID-19 pandemic, and to assess whether ...[more]

PMID: 33556034

Similar Datasets

Project description:BackgroundChina and the United States play critical leading roles in the global effort to contain the COVID-19 virus. Therefore, their population's preferences for initial diagnosis were compared to provide policy and clinical insights.ObjectiveWe aim to quantify and compare the public's preferences for medical management of fever and the attributes of initial diagnosis in the case of presenting symptoms during the COVID-19 pandemic in China and the United States.MethodsWe conducted a cross-sectional study from January to March 2021 in China and the United States using an online discrete choice experiment (DCE) questionnaire distributed through Amazon Mechanical Turk (MTurk; in the United States) and recruited volunteers (in China). Propensity score matching (PSM) was used to match the 2 groups of respondents from China and the United States to minimize confounding effects. In addition, the respondents' preferences for different diagnosis options were evaluated using a mixed logit model (MXL) and latent class models (LCMs). Moreover, demographic data were collected and compared using the chi-square test, Fisher test, and Mann-Whitney U test.ResultsA total of 9112 respondents (5411, 59.4%, from China and 3701, 40.6%, from the United States) who completed our survey were included in our analysis. After PSM, 1240 (22.9%) respondents from China and 1240 (33.5%) from the United States were matched for sex, age, educational level, occupation, and annual salary levels. The segmented sizes of 3 classes of respondents from China were 870 (70.2%), 270 (21.8%), and 100 (8.0%), respectively. Meanwhile, the US respondents' segmented sizes were 269 (21.7%), 139 (11.2%), and 832 (67.1%), respectively. Respondents from China attached the greatest importance to the type of medical institution (weighted importance=40.0%), while those from the United States valued the waiting time (weighted importance=31.5%) the most. Respondents from China preferred the emergency department (coefficient=0.973, reference level: online consultation) and fever clinic (a special clinic for the treatment of fever patients for the prevention and control of acute infectious diseases in China; coefficient=0.974, reference level: online consultation), while those from the United States preferred private clinics (general practices; coefficient=0.543, reference level: online consultation). Additionally, shorter waiting times, COVID-19 nucleic acid testing arrangements, higher reimbursement rates, and lower costs were always preferred.ConclusionsImprovements in the availability of COVID-19 testing and medical professional skills and increased designated health care facilities may help boost potential health care seeking during COVID-19 and prevent unrecognized community spreading of SARS-CoV-2 in China and the United States. Moreover, to better prevent future waves of pandemics, identify undiagnosed patients, and encourage those undiagnosed to seek health care services to curb the pandemic, the hierarchical diagnosis and treatment system needs improvement in China, and the United States should focus on reducing diagnosis costs and raising the reimbursement rate of medical insurance.

Project description:BackgroundOptimal management of hypertension in people with dementia may involve deprescribing antihypertensives. Understanding differing treatment priorities is important to enable patient-centred care. This study explored preferences for antihypertensive deprescribing amongst people living with dementia, carers and clinicians.MethodsDiscrete choice experiments (DCEs) are a stated preference survey method, underpinned by economic theory. A DCE was conducted, and respondents completed 12 labelled choice-questions, each presenting a status quo (continuing antihypertensives) and antihypertensive deprescribing option. The questions included six attributes, including pill burden, and event risks for stroke, myocardial infarction, increased blood pressure, cognitive decline, falls.ResultsOverall, 112 respondents (33 carers, 19 people living with dementia, and 60 clinicians) completed the survey. For people with dementia, lower pill burden increased preferences for deprescribing (odds ratio (OR) 1.95, 95% confidence interval (95% CI) 1.08-3.52). Increased stroke risk (for each additional person out of 100 having a stroke) decreased the likelihood of deprescribing for geriatricians (OR 0.71, 95% CI 0.55-0.92) and non-geriatrician clinicians (OR 0.62, 95% CI 0.45-0.86), and carers (OR 0.71, 95% CI 0.58-0.88). Increased myocardial infarction risk decreased preferences for deprescribing for non-geriatricians (OR 0.81, 95% CI 0.69-0.95) and carers (OR 0.84, 95% CI 0.73-0.98). Avoiding cognitive decline increased preferences for deprescribing for geriatricians (OR 1.17, 95% CI 1.03-1.33) and carers (OR 1.27, 95% CI 1.09-1.48). Avoiding falls increased preferences for deprescribing for clinicians (geriatricians (OR 1.20, 95% CI 1.11-1.29); non-geriatricians (OR 1.16, 95% CI 1.07-1.25)). Other attributes did not significantly influence respondent preferences.ConclusionsAntihypertensive deprescribing preferences differ amongst people with dementia, carers and clinicians. The study emphasises the importance of shared decision-making within the deprescribing process.

Project description:OBJECTIVES:It is desirable that public preferences are established and incorporated in emergency healthcare reforms. The aim of this study was to investigate preferences for local versus centralised provision of all emergency medical services (EMS) and explore what individuals think are important considerations for EMS delivery. DESIGN:A discrete choice experiment was conducted. The attributes used in the choice scenarios were: travel time to the hospital, waiting time to be seen, length of stay in the hospital, risks of dying, readmission and opportunity for outpatient care after emergency treatment at a local hospital. SETTING:North East England. PARTICIPANTS:Participants were a randomly sampled general population, aged 16 years or above recruited from Healthwatch Northumberland network database of lay members and from clinical contact with Northumbria Healthcare National Health Service Foundation Trust via Patient Experience Team. PRIMARY AND SECONDARY OUTCOME MEASURES:Analysis used logistic regression modelling techniques to determine the preference of each attribute. Marginal rates of substitution between attributes were estimated to understand the trade-offs individuals were willing to make. RESULTS:Responses were obtained from 148 people (62 completed a web and 86 a postal version). Respondents preferred shorter travel time to hospital, shorter waiting time, fewer number of days in hospital, low risk of death, low risk of readmission and outpatient follow-up care in their local hospital. However, individuals were willing to trade off increased travel time and waiting time for high-quality centralised care. Individuals were willing to travel 9 min more for a 1-day reduction in length of stay in the hospital, 38 min for a 1% reduction in risk of death and 112 min for having outpatient follow-up care at their local hospital. CONCLUSIONS:People value centralised EMS if it provides higher quality care and are willing to travel further and wait longer.

Project description:Choosing hypodontia treatment requires young people and parents to consider a large amount of information, identify what is important to them, and make trade-offs between options. This study aimed to examine young people and parents' preferences for hypodontia treatment using discrete choice experiment (DCE). This was a cross-sectional survey of young people (12-16 y) with hypodontia of any severity, at any stage of treatment, and their parents. Participants were recruited from NHS Hospitals in England and Wales. A bespoke DCE questionnaire was developed to measure preferences for 6 attributes of hypodontia treatment (waiting time, treatment time, problems during treatment, discomfort during treatment, bite, appearance). The questionnaire was completed 1) online by young people and parents, individually or together, and 2) by child-parent dyads under observation. Preferences were analyzed using regression models. In total, 204 participants (122 young people, 56 parents, 26 dyads) completed the online questionnaire and 15 child-parent dyads completed the questionnaire under observation. The most important attribute in hypodontia treatment was improvement in appearance, but significant heterogeneity was found in preferences. Four distinct groups of participants were found: group 1 (39%): severe discomfort and problems were most important; group 2 (31%): most concerned about improvement in appearance of teeth and improvement in bite; group 3 (22%): appearance 3 times more important than any other attribute; and group 4 (9%): preferences difficult to interpret. There was variation in how child-parent dyads approached decision-making, with some negotiating joint preferences, while for others, one individual dominated. Making trade-offs in DCE tasks helped some people think about treatment and identify their preferences. Appearance is an important outcome from hypodontia treatment, but preferences vary and potential risks and functional outcome are also important to some people. There is a notable level of uncertainty in decision-making, which suggests further shared decision support would be valuable.

Project description:BACKGROUND: Guidelines underline the role of individual preferences in the selection of a screening test, as insufficient evidence is available to recommend one screening test over another. We conducted a study to determine the preferences of individuals and to predict uptake for colorectal cancer (CRC) screening programmes using various screening tests. METHODS: A discrete choice experiment (DCE) questionnaire was distributed among naive subjects, yet to be screened, and previously screened subjects, aged 50-75 years. Subjects were asked to choose between scenarios on the basis of faecal occult blood test (FOBT), flexible sigmoidoscopy (FS), total colonoscopy (TC) with various test-specific screening intervals and mortality reductions, and no screening (opt-out). RESULTS: In total, 489 out of 1498 (33%) screening-naïve subjects (52% male; mean age+/-s.d. 61+/-7 years) and 545 out of 769 (71%) previously screened subjects (52% male; mean age+/-s.d. 61+/-6 years) returned the questionnaire. The type of screening test, screening interval, and risk reduction of CRC-related mortality influenced subjects' preferences (all P<0.05). Screening-naive and previously screened subjects equally preferred 5-yearly FS and 10-yearly TC (P=0.24; P=0.11), but favoured both strategies to annual FOBT screening (all P-values <0.001) if, based on the literature, realistic risk reduction of CRC-related mortality was applied. Screening-naive and previously screened subjects were willing to undergo a 10-yearly TC instead of a 5-yearly FS to obtain an additional risk reduction of CRC-related mortality of 45% (P<0.001). CONCLUSION: These data provide insight into the extent by which interval and risk reduction of CRC-related mortality affect preferences for CRC screening tests. Assuming realistic test characteristics, subjects in the target population preferred endoscopic screening over FOBT screening, partly, due to the more favourable risk reduction of CRC-related mortality by endoscopy screening. Increasing the knowledge of potential screenees regarding risk reduction by different screening strategies is, therefore, warranted to prevent unrealistic expectations and to optimise informed choice.

Project description:BackgroundDementia affects about 55 million people worldwide. Demographic change and shifting lifestyles challenge the organization of dementia care. A discrete choice experiment (DCE) was conducted to elicit preferences for living arrangements in dementia in urban and rural regions of Germany.MethodsPreliminary work included review of previous literature and focus groups. The DCE consists of seven attributes (group size, staff qualifications, organization of care, activities offered, support of religious practice, access to garden, consideration of food preferences) with three levels each. Individuals from the general population between the ages of 50 and 65 years were identified through population registration offices in three rural municipalities and one urban area, and 4390 individuals were approached via postal survey. A hierarchical Bayesian mixed logit model was estimated and interactions with sociodemographic characteristics were investigated.ResultsA total of 428 and 412 questionnaires were returned by rural and urban respondents, respectively. Access to a garden was perceived as the most important attribute (average importance 36.0% in the rural sample and 33.4% in the urban sample), followed by consideration of food preferences (15.8%, 17.8%), staff qualification (14.6%, 15.3%), care organization (11.4%, 12.3%), group size (12.2%, 11.1%), and range of activities (8.0%, 10.1%). The attribute relating to religious practice was given the least importance (2.1%, 0%). Preferences vary according to gender, age, religious beliefs, experience as an informal caregiver, and migrant background.ConclusionHeterogeneous preferences for living arrangements for people with dementia were identified. The expansion of concepts with access to natural environments for persons with dementia might be a viable option for the formal care market in Germany. Further research is needed to meet the challenges of setting up and designing innovative living arrangements for people with dementia. Preferences vary by gender, age, religious beliefs, experience as an informal caregiver, and migrant background.

Dataset Information

Preferences for Artificial Intelligence Clinicians Before and During the COVID-19 Pandemic: Discrete Choice Experiment and Propensity Score Matching Study.

Background

Objective

Methods

Results

Conclusions

Publications

Preferences for Artificial Intelligence Clinicians Before and During the COVID-19 Pandemic: Discrete Choice Experiment and Propensity Score Matching Study.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets