scholarly journals Use of Artificial Intelligence as a Predictor of the Response to Treatment in Alopecia Areata

Iproceedings ◽  
10.2196/35433 ◽  
2021 ◽  
Vol 6 (1) ◽  
pp. e35433
Author(s):  
Fernando Alarcón-Soldevilla ◽  
Francisco José Hernández-Gómez ◽  
Juan Antonio García-Carmona ◽  
Celia Campoy Carreño ◽  
Ramon Grimalt ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Alopecia Areata ◽  
Predictive Value ◽  
Data Augmentation ◽  
Conflicts Of Interest ◽  
The United States ◽  
Response To Treatment ◽  
Disease Evolution ◽  
Dermatological Disease

Background Artificial intelligence (AI) has emerged in dermatology with some studies focusing on skin disorders such as skin cancer, atopic dermatitis, psoriasis, and onychomycosis. Alopecia areata (AA) is a dermatological disease whose prevalence is 0.7%-3% in the United States, and is characterized by oval areas of nonscarring hair loss of the scalp or body without evident clinical variables to predict its response to the treatment. Nonetheless, some studies suggest a predictive value of trichoscopic features in the evaluation of treatment responses. Assuming that black dots, broken hairs, exclamation marks, and tapered hairs are markers of negative predictive value of the treatment response, while yellow dots are markers of no response to treatment according to recent studies, the absence of these trichoscopic features could indicate favorable disease evolution without treatment or even predict its response. Nonetheless, no studies have reportedly evaluated the role of AI in AA on the basis of trichoscopic features. Objective This study aimed to develop an AI algorithm to predict, using trichoscopic images, those patients diagnosed with AA with a better disease evolution. Methods In total, 80 trichoscopic images were included and classified in those with or without features of negative prognosis. Using a data augmentation technique, they were multiplied to 179 images to train an AI algorithm, as previously carried out with dermoscopic images of skin tumors with a favorable response. Subsequently, 82 new images of AA were presented to the algorithm, and the algorithm classified these patients as responders and non-responders; this process was reviewed by an expert trichologist observer and presented a concordance higher than 90% with the algorithm identifying structures described previously. Evolution of the cases was followed up to truly determine their response to treatment and, therefore, to assess the predictive value of the algorithm. Results In total, 32 of 40 (80%) images of patients predicted as nonresponders scarcely showed response to the treatment, while 34 of 42 (81%) images of those predicted as responders showed a favorable response to the treatment. Conclusions The development of an AI algorithm or tool could be useful to predict AA evolution and its response to treatment. However, further research is needed, including larger sample images or trained algorithms, by using images previously classified in accordance with the disease evolution and not with trichoscopic features. Conflicts of Interest None declared.

scholarly journals Use of Artificial Intelligence as a Predictor of the Response to Treatment in Alopecia Areata (Preprint)

2021 ◽  
Author(s):  
Fernando Alarcón-Soldevilla ◽  
Francisco José Hernández-Gómez ◽  
Juan Antonio García-Carmona ◽  
Celia Campoy Carreño ◽  
Ramon Grimalt ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Alopecia Areata ◽  
Predictive Value ◽  
Data Augmentation ◽  
The United States ◽  
Response To Treatment ◽  
Disease Evolution ◽  
Dermatological Disease ◽  
Treatment Responses

BACKGROUND Artificial intelligence (AI) has emerged in dermatology with some studies focusing on skin disorders such as skin cancer, atopic dermatitis, psoriasis, and onychomycosis. Alopecia areata (AA) is a dermatological disease whose prevalence is 0.7%-3% in the United States, and is characterized by oval areas of nonscarring hair loss of the scalp or body without evident clinical variables to predict its response to the treatment. Nonetheless, some studies suggest a predictive value of trichoscopic features in the evaluation of treatment responses. Assuming that black dots, broken hairs, exclamation marks, and tapered hairs are markers of negative predictive value of the treatment response, while yellow dots are markers of no response to treatment according to recent studies, the absence of these trichoscopic features could indicate favorable disease evolution without treatment or even predict its response. Nonetheless, no studies have reportedly evaluated the role of AI in AA on the basis of trichoscopic features. OBJECTIVE This study aimed to develop an AI algorithm to predict, using trichoscopic images, those patients diagnosed with AA with a better disease evolution. METHODS In total, 80 trichoscopic images were included and classified in those with or without features of negative prognosis. Using a data augmentation technique, they were multiplied to 179 images to train an AI algorithm, as previously carried out with dermoscopic images of skin tumors with a favorable response. Subsequently, 82 new images of AA were presented to the algorithm, and the algorithm classified these patients as responders and non-responders; this process was reviewed by an expert trichologist observer and presented a concordance higher than 90% with the algorithm identifying structures described previously. Evolution of the cases was followed up to truly determine their response to treatment and, therefore, to assess the predictive value of the algorithm. RESULTS In total, 32 of 40 (80%) images of patients predicted as nonresponders scarcely showed response to the treatment, while 34 of 42 (81%) images of those predicted as responders showed a favorable response to the treatment. CONCLUSIONS The development of an AI algorithm or tool could be useful to predict AA evolution and its response to treatment. However, further research is needed, including larger sample images or trained algorithms, by using images previously classified in accordance with the disease evolution and not with trichoscopic features.

scholarly journals Application of artificial intelligence in pancreaticobiliary diseases

2021 ◽  
Vol 14 ◽  
pp. 263177452199305
Author(s):  
Hemant Goyal ◽  
Rupinder Mann ◽  
Zainab Gandhi ◽  
Abhilash Perisetti ◽  
Zhongheng Zhang ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Response To Treatment ◽  
Endoscopic Retrograde ◽  
Artificial Intelligence Techniques ◽  
Computer Aided ◽  
Rapid Pace ◽  
Cystic Pancreatic Lesions ◽  
Aided Diagnosis

The role of artificial intelligence and its applications has been increasing at a rapid pace in the field of gastroenterology. The application of artificial intelligence in gastroenterology ranges from colon cancer screening and characterization of dysplastic and neoplastic polyps to the endoscopic ultrasonographic evaluation of pancreatic diseases. Artificial intelligence has been found to be useful in the evaluation and enhancement of the quality measure for endoscopic retrograde cholangiopancreatography. Similarly, artificial intelligence techniques like artificial neural networks and faster region-based convolution network are showing promising results in early and accurate diagnosis of pancreatic cancer and its differentiation from chronic pancreatitis. Other artificial intelligence techniques like radiomics-based computer-aided diagnosis systems could help to differentiate between various types of cystic pancreatic lesions. Artificial intelligence and computer-aided systems also showing promising results in the diagnosis of cholangiocarcinoma and the prediction of choledocholithiasis. In this review, we discuss the role of artificial intelligence in establishing diagnosis, prognosis, predicting response to treatment, and guiding therapeutics in the pancreaticobiliary system.

scholarly journals Modeling the Research Landscapes of Artificial Intelligence Applications in Diabetes (GAPRESEARCH)

2020 ◽  
Vol 17 (6) ◽  
pp. 1982 ◽  
Author(s):  
Giang Thu Vu ◽  
Bach Xuan Tran ◽  
Roger S. McIntyre ◽  
Hai Quang Pham ◽  
Hai Thanh Phan ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Latent Dirichlet Allocation ◽  
Developed Countries ◽  
The United States ◽  
Bibliographic Analysis ◽  
Novel Treatments ◽  
Future Direction ◽  
Bibliometrics Analysis ◽  
Research Domains

The rising prevalence and global burden of diabetes fortify the need for more comprehensive and effective management to prevent, monitor, and treat diabetes and its complications. Applying artificial intelligence in complimenting the diagnosis, management, and prediction of the diabetes trajectory has been increasingly common over the years. This study aims to illustrate an inclusive landscape of application of artificial intelligence in diabetes through a bibliographic analysis and offers future direction for research. Bibliometrics analysis was combined with exploratory factor analysis and latent Dirichlet allocation to uncover emergent research domains and topics related to artificial intelligence and diabetes. Data were extracted from the Web of Science Core Collection database. The results showed a rising trend in the number of papers and citations concerning AI applications in diabetes, especially since 2010. The nucleus driving the research and development of AI in diabetes is centered around developed countries, mainly consisting of the United States, which contributed 44.1% of the publications. Our analyses uncovered the top five emerging research domains to be: (i) use of artificial intelligence in diagnosis of diabetes, (ii) risk assessment of diabetes and its complications, (iii) role of artificial intelligence in novel treatments and monitoring in diabetes, (iv) application of telehealth and wearable technology in the daily management of diabetes, and (v) robotic surgical outcomes with diabetes as a comorbid. Despite the benefits of artificial intelligence, challenges with system accuracy, validity, and confidentiality breach will need to be tackled before being widely applied for patients’ benefits.

scholarly journals Public Opinion on Artificial Intelligence Development

2021 ◽  
Author(s):  
A.V. Merenkov ◽  
R. Campa ◽  
N.P. Dronishinets
Keyword(s):  
Artificial Intelligence ◽  
Public Opinion ◽  
Western Europe ◽  
Social Groups ◽  
Active Role ◽  
The United States ◽  
Master's Programs ◽  
Intelligence Development ◽  
And Control

In connection with the active role of Russia and other countries in the design and implementation of devices with artificial intelligence (AI), there is a need to study the opinion of different social groups on this technology and the problems that arise when using it. The purpose of this work is to analyze public opinion on AI, in Russia and various foreign countries, and the possible consequences of its implementation in different areas of human activity. The research has revealed students’ opinions about AI devices and the problems related to their development in Russia. The research methods adopted are a content analysis of foreign publications devoted to the study of public opinion on AI and a questionnaire survey. Overall, 190 students of the Ural Federal University enrolled in Bachelor’s and Master’s programs were interviewed. The analysis of publications devoted to the study of public opinion in the United States, Japan, and Western Europe, as well as the results of our survey, has led to the conclusion that the majority of people have only a vague idea of what AI devices are. Our study has revealed that 23.6% of the respondents know nothing about AI. 36% of the respondents believe that in the near future the most demanded specialists in the labor market will be those who create robots and control their work. The survey has also shown the important role of mass media and general and special education institutions in informing the population about the opportunities and problems that arise when devices that exceed human mental capabilities are created and enter the social fabric. Keywords: public opinion, artificial intelligence, subjects of public opinion, representations of social groups about artificial intelligence

scholarly journals Clinical Utility of Morphological Evaluation of Day 14 Bone Marrow Biopsies in Acute Myeloid Leukemia Patients Undergoing Standard Induction Chemotherapy: Time to Change Practice?

Blood ◽  
2014 ◽  
Vol 124 (21) ◽  
pp. 1004-1004 ◽  
Author(s):  
Yehuda E. Deutsch ◽  
German Campuzano-Zuluaga ◽  
Matthew P Salzberg ◽  
Alexandra Gomez Arteaga ◽  
Justin M. Watts ◽  
...  
Keyword(s):  
Bone Marrow ◽  
Induction Chemotherapy ◽  
Induction Therapy ◽  
Predictive Value ◽  
Chromosomal Abnormalities ◽  
Conflicts Of Interest ◽  
Lymphoblastic Leukemia ◽  
Response To Treatment ◽  
Bone Marrow Biopsies ◽  
Count Recovery

Abstract Introduction Early bone marrow (BM) evaluation (during aplasia or at “day 14” (D14)) in patients with AML undergoing conventional induction therapy has been adopted from clinical practice in pediatric acute lymphoblastic leukemia (ALL). While it has been shown that early persistence of AML correlates with decreased complete remission (CR) rates and overall survival (OS), unlike in ALL, there are no data to indicate that early initiation of re-induction therapy based on these findings will positively influence outcome. In fact, early re-induction, especially in older patients, may increase morbidity and mortality from prolonged cytopenias, infectious complications, and longer hospital stays. Moreover, it can be challenging to determine the nature of scattered blasts identified in a hypocellular BM at D14, as they may represent normal recovering marrow elements or malignant blasts. Even if malignant, the chemosensitivityof these cells will only be fully determined by later assessment of the BM at the time of expected count recovery (“day 28”). For these reasons, early re-induction therapy may not be advisable. In this retrospective study, we sought to evaluate the validity of D14 BM assessments as post-therapy prognostication to guide treatment decisions in AML. Methods We conducted a retrospective institutional study (2006-2014) of AML patients undergoing routine induction chemotherapy where diagnostic, interim (around D14) and recovery (D21-42) BM evaluations were available for review. Clinical information and pathology data were retrieved from our institutional database. Responses at D14 were categorized morphologically into three categories: optimal response (OR, blasts ≤5%), indeterminate response (IR, blasts 6-19%), and residual leukemia (RL, blasts ≥20% or a relative decrease in blast count from baseline of <20%). Published response criteria were used to define responses at marrow recovery. Suboptimal response (SOR) at D14 was defined as either IR or RL during the assessment period. Mann-Whitney's U test was used to compare non-normally distributed variables. The Fisher's exact test was employed to assess for associations between response to treatment at D14 and likelihood of recovering in CR. The sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) of a D14 BM to predict CR were calculated for patients that were observed without re-induction. Results Evaluable patients (n=98) had a mean age of 51 years (20-73), and 45% were male. The median BM blast percentages at diagnosis, D14 and recovery were respectively 54.5%, 0% and 2.5% (Figure 1). There was a significantly greater absolute decrease in blast percentage from diagnosis to D14 in patients who recovered in CR compared to those who did not achieve CR (median: 53.5% vs 23.0%, P = 0.001). In patients that got early re-induction therapy for SOR at D14, the relative differential in baseline and D14 BM blasts was significantly lower compared to patients with D14 SOR who did not get re-induction therapy (median: 21.8% vs 77.8%, P=0.004) Ninety patients did not receive early re-induction therapy. Of these, 86 (95.6%) achieved CR and 4 patients (4.4%) recovered counts with residual leukemia. Fourteen (14.3%) patients were classified as SOR at D14. Of these, 6 (6.7%) did not receive re-induction therapy and 4 of these 6 patients (67%) achieved a CR. Eight patients received early re-induction therapy based on SOR at D14 (IR = 2, RL = 6); of these, 4 patients (50%) achieved CR at count recovery. Achieving an OR at D14 was predictive of achieving CR at recovery (sensitivity = 95.3%, PPV = 97.6%). However, not achieving an OR at D14 had low specificity (50%) and NPV (33.3%) for achieving CR (P = 0.021). Conclusions Our results indicate that a SOR at the D14 BM evaluation does not uniformly identify patients with primary induction failure (low NPV) and should not be used to dictate the timing of re-induction therapy. We confirmed the PPV of achieving an OR at D14 as previously reported, but we argue that no additional prognostic data is provided by an OR at D14, beyond what can already be predicted by pre-treatment variables (e.g., age and chromosomal abnormalities). We suggest that the D14 BM should be omitted from the routine evaluation of AML patients during induction therapy outside the context of a clinical trial. Figure 1 Figure 1. Progression and percentage of blasts at diagnosis, day 14 and recovery assessments (n = 98). Disclosures No relevant conflicts of interest to declare.

scholarly journals Artificial Intelligence: Serving American Security and Chinese Ambitions

2020 ◽  
Vol 4 (3) ◽  
pp. 42-52
Author(s):  
H. Obeid ◽  
F Hillani, ◽  
R. Fakih ◽  
K. Mozannar
Keyword(s):  
Artificial Intelligence ◽  
United States ◽  
Technological Development ◽  
The United States ◽  
New Era ◽  
The Us ◽  
The One ◽  
The Right ◽  
Technological Strength

In recent years artificial intelligence has entered a new era, which gives rise to many hopes for powerful states such as the United States and China. In this paper, we analyze the importance and role of artificial intelligence in technological development in each of the two countries on the one hand, and its influence on China-American relations in terms of technological and geopolitical conflict. To get the right results, we rely on a literature review of dozens of articles published on the phenomenon in order to compare the power of artificial intelligence between the United States and China where we found that the US still has technological strength, especially in the field of artificial intelligence, but we can say that a large force is beginning pose a threat for it which is China that has great technological capabilities so, we can say that the United States should work more in this field. Also, we found that artificial intelligence has a primary goal in both countries, it helps China to achieve its ambitions to be the leader of the world, and this intelligence, on the other hand, provides protection and security to the United States. This paper is divided into three sections. The first section focuses on the importance of artificial intelligence in achieving China’s ambitions, the second section explains the role of artificial intelligence in the US protection service, and the third section describes the technological and geopolitical conflict resulting from the competition in artificial intelligence between these two countries. Keywords: Artificial intelligence, United States, China, Conflict, leader.

ARTIFICIAL INTELLIGENCE IN ECONOMY AND POLICY NOWADAYS. ARTICLE 3. ARTIFICIAL INTELLIGENCE IN RUSSIAN AND FOREIGN PUBLIC POLICY

2021 ◽  
pp. 3-32
Author(s):  
V.N. Leksin
Keyword(s):  
Artificial Intelligence ◽  
United States ◽  
Public Policy ◽  
The United States ◽  
The Third ◽  
China And India ◽  
The World ◽  
Final Article ◽  
Country Differences

The third and final article of the three-part series of articles «Artificial intelligence in the economy and politics of our time» (the first and second articles of the series were published in the fourth and fifth issues of the journal for this year, respectively) presents the results of a study of the goals, motivations and specifics of the adoption of national strategies to support the development of artificial intelligence in different countries. It is shown that such a strategy in Russia is based on the idea of the most important role of using artificial intelligence in solving the most complex economic, social, and military-political problems of the country. Differences in conceptual approaches to the development of research and practical use of artificial intelligence developments in the national strategies of the largest countries of the world — the United States, China and India.

Pharmaceuticals and Public Policy: A Look Ahead

2018 ◽  
Author(s):  
Stuart O. Schweitzer ◽  
Z. John Lu
Keyword(s):  
Artificial Intelligence ◽  
Market Equilibrium ◽  
The United States ◽  
Bundled Payment ◽  
The Past ◽  
Look Ahead ◽  
The Future ◽  
Pharmaceutical Prices ◽  
Digital Healthcare

Recognizing that the past often does not predict the future well, this chapter nevertheless offers prescience for the pharmaceutical industry in the next five to ten years. Using the standard economics paradigm of supply, demand, and market equilibrium, it considers the future of the industry in the following aspects: industrial organization, the nascent biosimilar sector, the promise of personalized medicine and digital healthcare information, artificial intelligence, the prospects for outpatient bundled payment programs, the setting of pharmaceutical prices, and the role of the FDA. The most important among them will be the scope and nature of health care reform in the United States and the jurisdiction of the FDA in the coming years.

scholarly journals Conflicts of Interest in Financial Distress: The Role of Employees

2017 ◽  
Vol 9 (12) ◽  
pp. 101
Author(s):  
Wenchien Liu
Keyword(s):  
Financial Distress ◽  
Conflicts Of Interest ◽  
Positive Impact ◽  
The United States ◽  
Asset Sales ◽  
Union Power ◽  
Significant Relationships ◽  
Distressed Firms ◽  
The Media

The interests of employees are not consistent with those of other stakeholders when firms are in financial distress. Hence, conflicts of interest among stakeholders are more severe, especially for those firms with strong union power, as news is reported in the media. However, little attention has been paid to the impacts of employees on bankruptcy resolutions. This study examines the impacts of employees (i.e., union power) on the conflicts of interest of distressed firms in the United States from 1983 to 2015. We find that union power has strong effects on conflicts of interest related to employees, such as asset sales, debtor-in-possession financing, successful emergence from bankruptcy, CEO replacement, and refiling for bankruptcy. On the contrary, for conflicts of interest unrelated to employees, including the costs of bankruptcy resolution, choice of bankruptcy resolution method, and conflicts of interest between creditors and debtors, we find no significant relationships. Finally, we also find a positive impact of union power on the probability of refiling for bankruptcy in the future after emerging successfully.

Sign in / Sign up

Export Citation Format

Share Document