Pulmonary Hypertension in Association with Lung Disease: Quantitative CT and Artificial Intelligence to the Rescue? State-of-the-Art Review

Accurate phenotyping of patients with pulmonary hypertension (PH) is an integral part of informing disease classification, treatment, and prognosis. The impact of lung disease on PH outcomes and response to treatment remains a challenging area with limited progress. Imaging with computed tomography (CT) plays an important role in patients with suspected PH when assessing for parenchymal lung disease, however, current assessments are limited by their semi-qualitative nature. Quantitative chest-CT (QCT) allows numerical quantification of lung parenchymal disease beyond subjective visual assessment. This has facilitated advances in radiological assessment and clinical correlation of a range of lung diseases including emphysema, interstitial lung disease, and coronavirus disease 2019 (COVID-19). Artificial Intelligence approaches have the potential to facilitate rapid quantitative assessments. Benefits of cross-sectional imaging include ease and speed of scan acquisition, repeatability and the potential for novel insights beyond visual assessment alone. Potential clinical benefits include improved phenotyping and prediction of treatment response and survival. Artificial intelligence approaches also have the potential to aid more focused study of pulmonary arterial hypertension (PAH) therapies by identifying more homogeneous subgroups of patients with lung disease. This state-of-the-art review summarizes recent QCT developments and potential applications in patients with PH with a focus on lung disease.

Download Full-text

State of the Art: The Impact of Artificial Intelligence in Endoscopy 2020

Current Gastroenterology Reports ◽

10.1007/s11894-021-00810-9 ◽

2021 ◽

Vol 23 (5) ◽

Author(s):

Jiyoung Lee ◽

Michael B. Wallace

Keyword(s):

Artificial Intelligence ◽

State Of The Art ◽

The Impact

Download Full-text

Artificial Intelligence for Caregivers of Persons With Alzheimer’s Disease and Related Dementias: Systematic Literature Review (Preprint)

10.2196/preprints.18189 ◽

2020 ◽

Author(s):

Bo Xie ◽

Cui Tao ◽

Juan Li ◽

Robin C Hilsabeck ◽

Alyssa Aguirre

Keyword(s):

Artificial Intelligence ◽

Alzheimer’S Disease ◽

Alzheimer's Disease ◽

Digital Library ◽

Full Text ◽

Interdisciplinary Collaboration ◽

Exclusion Criteria ◽

Cross Sectional ◽

Meta Analyses ◽

The Impact

BACKGROUND Artificial intelligence (AI) has great potential for improving the care of persons with Alzheimer’s disease and related dementias (ADRD) and the quality of life of their family caregivers. To date, however, systematic review of the literature on the impact of AI on ADRD management has been lacking. OBJECTIVE This paper aims to (1) identify and examine literature on AI that provides information to facilitate ADRD management by caregivers of individuals diagnosed with ADRD and (2) identify gaps in the literature that suggest future directions for research. METHODS Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines for conducting systematic literature reviews, during August and September 2019, we performed 3 rounds of selection. First, we searched predetermined keywords in PubMed, Cumulative Index to Nursing and Allied Health Literature Plus with Full Text, PsycINFO, IEEE Xplore Digital Library, and the ACM Digital Library. This step generated 113 nonduplicate results. Next, we screened the titles and abstracts of the 113 papers according to inclusion and exclusion criteria, after which 52 papers were excluded and 61 remained. Finally, we screened the full text of the remaining papers to ensure that they met the inclusion or exclusion criteria; 31 papers were excluded, leaving a final sample of 30 papers for analysis. RESULTS Of the 30 papers, 20 reported studies that focused on using AI to assist in activities of daily living. A limited number of specific daily activities were targeted. The studies’ aims suggested three major purposes: (1) to test the feasibility, usability, or perceptions of prototype AI technology; (2) to generate preliminary data on the technology’s performance (primarily accuracy in detecting target events, such as falls); and (3) to understand user needs and preferences for the design and functionality of to-be-developed technology. The majority of the studies were qualitative, with interviews, focus groups, and observation being their most common methods. Cross-sectional surveys were also common, but with small convenience samples. Sample sizes ranged from 6 to 106, with the vast majority on the low end. The majority of the studies were descriptive, exploratory, and lacking theoretical guidance. Many studies reported positive outcomes in favor of their AI technology’s feasibility and satisfaction; some studies reported mixed results on these measures. Performance of the technology varied widely across tasks. CONCLUSIONS These findings call for more systematic designs and evaluations of the feasibility and efficacy of AI-based interventions for caregivers of people with ADRD. These gaps in the research would be best addressed through interdisciplinary collaboration, incorporating complementary expertise from the health sciences and computer science/engineering–related fields.

Download Full-text

Study of the post tuberculosis lung diseases and the impact of various patient and disease related factors on its occurrence

International Journal of Advances in Medicine ◽

10.18203/2349-3933.ijam20193278 ◽

2019 ◽

Vol 6 (4) ◽

pp. 1241

Author(s):

Jayasri Helen Gali ◽

Harsha Vardhana Varma ◽

Aruna Kumari Badam

Keyword(s):

Lung Disease ◽

Urban Areas ◽

Lung Diseases ◽

Lung Damage ◽

Common Symptom ◽

Related Factors ◽

Cross Sectional ◽

Restrictive Lung Disease ◽

Co Morbidity ◽

The Impact

Background: More than fifty percent of the cured cases of pulmonary tuberculosis develop some form of chronic pulmonary dysfunction. It can present with varying degrees of lung damage, ranging from minimum functional abnormalities to severe forms of dysfunction that can be an important cause of death. Objective of the study to identify the various Post Tuberculosis Lung Diseases (PTBLDs) and to study impact of the patient and disease related factors on its occurrence.Methods: Cross-sectional, observational study was conducted in 134 adult, post tuberculosis patients, aged between 18-65 years, who have completed at least one year after the end of anti-tubercular treatment. All symptomatic post TB lung disease patients coming to the pulmonology out-patient clinic at the Apollo Institute of Medical sciences and Research were included in the study.Results: Majority were more than 50 years (35.3%) and males (59.4%). Majority were from urban areas (70.7%), low social class (72.2%), and unskilled workers (56.4%). Most common symptom was cough in 74.4% cases. Majority of the cases had symptoms from one week to one month i.e. 47.4%. Only eight cases were found out to be very prompt in reporting their symptoms. 39 cases had some or the other co-morbidity. Current chest X-ray status was normal in only three cases. Mean FEV1 was 1.38 which increased to 1.52; mean FVC was 1.23 which increased to 1.58; mean FEV1/FVC was 67.37 which increased to 72.76 after giving the bronchodilator. 78(58.6%) cases had obstructive and 27(20.3%) had restrictive lung disease. In 30 cases the disease was reversible. Majority of the cases were of pulmonary fibrosis followed by bronchiectasis.Conclusion: Further studies are needed to develop approaches for the prevention, care and treatment of patients with post TBLD.

Download Full-text

The Impact of Explanations on Layperson Trust in Artificial Intelligence–Driven Symptom Checker Apps: Experimental Study (Preprint)

10.2196/preprints.29386 ◽

2021 ◽

Author(s):

Claire Woodcock ◽

Brent Mittelstadt ◽

Dan Busbridge ◽

Grant Blank

Keyword(s):

Artificial Intelligence ◽

Temporal Arteritis ◽

Statistical Significance ◽

Group Differences ◽

P System ◽

Cross Sectional Survey ◽

Cross Sectional ◽

Information Gap ◽

Social Theories ◽

The Impact

BACKGROUND Artificial intelligence (AI)–driven symptom checkers are available to millions of users globally and are advocated as a tool to deliver health care more efficiently. To achieve the promoted benefits of a symptom checker, laypeople must trust and subsequently follow its instructions. In AI, explanations are seen as a tool to communicate the rationale behind black-box decisions to encourage trust and adoption. However, the effectiveness of the types of explanations used in AI-driven symptom checkers has not yet been studied. Explanations can follow many forms, including why-explanations and how-explanations. Social theories suggest that why-explanations are better at communicating knowledge and cultivating trust among laypeople. OBJECTIVE The aim of this study is to ascertain whether explanations provided by a symptom checker affect explanatory trust among laypeople and whether this trust is impacted by their existing knowledge of disease. METHODS A cross-sectional survey of 750 healthy participants was conducted. The participants were shown a video of a chatbot simulation that resulted in the diagnosis of either a migraine or temporal arteritis, chosen for their differing levels of epidemiological prevalence. These diagnoses were accompanied by one of four types of explanations. Each explanation type was selected either because of its current use in symptom checkers or because it was informed by theories of contrastive explanation. Exploratory factor analysis of participants’ responses followed by comparison-of-means tests were used to evaluate group differences in trust. RESULTS Depending on the treatment group, two or three variables were generated, reflecting the prior knowledge and subsequent mental model that the participants held. When varying explanation type by disease, migraine was found to be nonsignificant (P=.65) and temporal arteritis, marginally significant (P=.09). Varying disease by explanation type resulted in statistical significance for input influence (P=.001), social proof (P=.049), and no explanation (P=.006), with counterfactual explanation (P=.053). The results suggest that trust in explanations is significantly affected by the disease being explained. When laypeople have existing knowledge of a disease, explanations have little impact on trust. Where the need for information is greater, different explanation types engender significantly different levels of trust. These results indicate that to be successful, symptom checkers need to tailor explanations to each user’s specific question and discount the diseases that they may also be aware of. CONCLUSIONS System builders developing explanations for symptom-checking apps should consider the recipient’s knowledge of a disease and tailor explanations to each user’s specific need. Effort should be placed on generating explanations that are personalized to each user of a symptom checker to fully discount the diseases that they may be aware of and to close their information gap.

Download Full-text

CHARACTERISTICS OF QUANTITATIVE CT ANALYSIS AND PULMONARY HYPERTENSION IN PATIENTS WITH SYSTEMIC SCLEROSIS-ASSOCIATED INTERSTITIAL LUNG DISEASE

CHEST Journal ◽

10.1016/j.chest.2021.07.1895 ◽

2021 ◽

Vol 160 (4) ◽

pp. A2145-A2146

Author(s):

Sirus Jesudasen ◽

Badar Patel ◽

Kristin D'Silva ◽

Pietro Nardelli ◽

Ruben San José Estépar ◽

...

Keyword(s):

Pulmonary Hypertension ◽

Systemic Sclerosis ◽

Interstitial Lung Disease ◽

Lung Disease ◽

Quantitative Ct ◽

Ct Analysis ◽

Quantitative Ct Analysis

Download Full-text

Artificial intelligence in radiology: does it impact medical students preference for radiology as their future career?

BJR|Open ◽

10.1259/bjro.20200037 ◽

2020 ◽

Vol 2 (1) ◽

pp. 20200037

Author(s):

Abdulmajeed Bin Dahmash ◽

Mohammed Alabdulkareem ◽

Aljabriyah Alfutais ◽

Ahmed M Kamel ◽

Feras Alkholaiwi ◽

...

Keyword(s):

Artificial Intelligence ◽

Medical Students ◽

Negative Influence ◽

Specialty Choice ◽

Cross Sectional ◽

First Choice ◽

Multicenter Survey ◽

The Future ◽

Potential Impact ◽

The Impact

Objective: To test medical students’ perceptions of the impact of artificial intelligence (AI) on radiology and the influence of these perceptions on their choice of radiology as a lifetime career. Methods: A cross-sectional multicenter survey of medical students in Saudi Arabia was conducted in April 2019. Results: Of the 476 respondents, 34 considered radiology their first specialty choice, 26 considered it their second choice, and 65 considered it their third choice. Only 31% believed that AI would replace radiologists in their lifetime, while 44.8% believed that AI would minimize the number of radiologists needed in the future. Approximately 50% believed they had a good understanding of AI; however, when knowledge of AI was tested using five questions, on average, only 22% of the questions were answered correctly. Among the respondents who ranked radiology as their first choice, 58.8% were anxious about the uncertain impact of AI on radiology. The number of respondents who ranked radiology as one of their top three choices increased by 14 when AI was not a consideration. Radiology conferences and the opinions of radiologists had the most influence on the respondents’ preferences for radiology. Conclusion: The worry that AI might displace radiologists in the future had a negative influence on medical students’ consideration of radiology as a career. Academic radiologists are encouraged to educate their students about AI and its potential impact when students are considering radiology as a lifetime career choice. Advances in knowledge: Rapid advances of AI in radiology will certainly impact the specialty, the concern of AI impact on radiology had negative influence in our participants and investing in AI education and is highly recommended.

Download Full-text

The Impact of Explanations on Layperson Trust in Artificial Intelligence–Driven Symptom Checker Apps: Experimental Study

Journal of Medical Internet Research ◽

10.2196/29386 ◽

2021 ◽

Vol 23 (11) ◽

pp. e29386

Author(s):

Claire Woodcock ◽

Brent Mittelstadt ◽

Dan Busbridge ◽

Grant Blank

Keyword(s):

Artificial Intelligence ◽

Temporal Arteritis ◽

Statistical Significance ◽

Group Differences ◽

Cross Sectional Survey ◽

Cross Sectional ◽

Information Gap ◽

Social Theories ◽

Social Proof ◽

The Impact

Background Artificial intelligence (AI)–driven symptom checkers are available to millions of users globally and are advocated as a tool to deliver health care more efficiently. To achieve the promoted benefits of a symptom checker, laypeople must trust and subsequently follow its instructions. In AI, explanations are seen as a tool to communicate the rationale behind black-box decisions to encourage trust and adoption. However, the effectiveness of the types of explanations used in AI-driven symptom checkers has not yet been studied. Explanations can follow many forms, including why-explanations and how-explanations. Social theories suggest that why-explanations are better at communicating knowledge and cultivating trust among laypeople. Objective The aim of this study is to ascertain whether explanations provided by a symptom checker affect explanatory trust among laypeople and whether this trust is impacted by their existing knowledge of disease. Methods A cross-sectional survey of 750 healthy participants was conducted. The participants were shown a video of a chatbot simulation that resulted in the diagnosis of either a migraine or temporal arteritis, chosen for their differing levels of epidemiological prevalence. These diagnoses were accompanied by one of four types of explanations. Each explanation type was selected either because of its current use in symptom checkers or because it was informed by theories of contrastive explanation. Exploratory factor analysis of participants’ responses followed by comparison-of-means tests were used to evaluate group differences in trust. Results Depending on the treatment group, two or three variables were generated, reflecting the prior knowledge and subsequent mental model that the participants held. When varying explanation type by disease, migraine was found to be nonsignificant (P=.65) and temporal arteritis, marginally significant (P=.09). Varying disease by explanation type resulted in statistical significance for input influence (P=.001), social proof (P=.049), and no explanation (P=.006), with counterfactual explanation (P=.053). The results suggest that trust in explanations is significantly affected by the disease being explained. When laypeople have existing knowledge of a disease, explanations have little impact on trust. Where the need for information is greater, different explanation types engender significantly different levels of trust. These results indicate that to be successful, symptom checkers need to tailor explanations to each user’s specific question and discount the diseases that they may also be aware of. Conclusions System builders developing explanations for symptom-checking apps should consider the recipient’s knowledge of a disease and tailor explanations to each user’s specific need. Effort should be placed on generating explanations that are personalized to each user of a symptom checker to fully discount the diseases that they may be aware of and to close their information gap.

Download Full-text

Use of Artificial Intelligence in Smart Cities for Smart Decision-Making: A Social Innovation Perspective

Sustainability ◽

10.3390/su14020620 ◽

2022 ◽

Vol 14 (2) ◽

pp. 620

Author(s):

Syed Asad A. Bokhari ◽

Seunghwan Myeong

Keyword(s):

Artificial Intelligence ◽

Decision Making ◽

Social Innovation ◽

Survey Design ◽

Smart Cities ◽

Mediating Effect ◽

Decision Making Process ◽

Science Literature ◽

Cross Sectional ◽

The Impact

The goal of this study is to investigate the direct and indirect relationships that exist between artificial intelligence (AI), social innovation (SI), and smart decision-making (SDM). This study used a survey design and collected cross-sectional data from South Korea and Pakistan using survey questionnaires. Four hundred sixty respondents from the public and private sectors were obtained and empirically analyzed using SPSS multiple regression. The study discovered a strong and positive mediating effect of SI between the relationship of AI and SDM, as predicted. Previous researchers have investigated some of the factors that influence the decision-making process. This study adds to the social science literature by examining the impact of a mediating factor on decision-making. The findings of this study will contribute to the local government in building smart cities such that the factor of social innovations should be involved in the decision-making process because smart decision-making would share such collected data with entrepreneurs, businesses, and industries and would benefit society and all relevant stakeholders, including such social innovators.

Download Full-text

Non-Group 1 Pulmonary Hypertension Associated With Systemic Sclerosis: An Under-studied Patient Population

Advances in Pulmonary Hypertension ◽

10.21693/1933-088x-16.2.68 ◽

2017 ◽

Vol 16 (2) ◽

pp. 68-75

Author(s):

Zafia Anklesaria ◽

Rajeev Saggar ◽

Ariss Derhovanessian ◽

Rajan Saggar

Keyword(s):

Pulmonary Hypertension ◽

Systemic Sclerosis ◽

World Health ◽

Response To Treatment ◽

Specific Therapy ◽

Pulmonary Manifestations ◽

Group 3 ◽

Group 2 ◽

The Impact ◽

Group 1

Background: Systemic sclerosis (SSc) is a heterogeneous disorder that results in multiorgan dysfunction. The most common pulmonary manifestations are pulmonary hypertension (PH) and interstitial lung disease (ILD). Systemic sclerosis may be complicated by World Health Organization (WHO) Group 1 PH (SSc-PAH), which is the most well-studied subtype. The PH associated with SSc may also be secondary to underlying left heart disease (SSc-PH-LHD) or ILD (SSc-PH-ILD), and these subgroups are classified as WHO Group 2 and Group 3 PH, respectively. These non-WHO Group 1 PH subsets are notoriously under-studied. Available data suggest that the impact of PH-specific therapy in SSc-PH-LHD and SSc-PH-ILD is limited and survival is poor despite attempted treatment. Implication for clinicians: Most research and clinical trials surrounding PH in SSc have thus far focused on WHO Group 1 SSc-PAH. There are limited data surrounding therapeutic options for WHO Group 2 (SSc-PH-LHD) and Group 3 PH (SSc-PH-ILD) phenotypes. This review aims to summarize and consolidate the data surrounding these 2 distinct clinical phenotypes and to emphasize the available prognostic and treatment considerations. Conclusions: Given the unique pathophysiology, prognostic implications, and poor response to treatment of WHO Group 2 and 3 SSc-PH phenotypes, there is an overwhelming need for more data to best understand optimal management strategies. The focus should be individual patient-level prognostication, how and when to initiate and manage PH-specific therapy, and appropriate triage with regard to the timing of lung (or heart-lung) transplantation.

Download Full-text