Artificial intelligence in retina

Progress in Retinal and Eye Research, Год журнала: 2018, Номер 67, С. 1 - 29

Опубликована: Авг. 1, 2018

Major advances in diagnostic technologies are offering unprecedented insight into the condition of retina and beyond ocular disease. Digital images providing millions morphological datasets can fast non-invasively be analyzed a comprehensive manner using artificial intelligence (AI). Methods based on machine learning (ML) particularly deep (DL) able to identify, localize quantify pathological features almost every macular retinal Convolutional neural networks thereby mimic path human brain for object recognition through from training sets, supervised ML, or even extrapolation patterns recognized independently, unsupervised ML. The methods AI-based analyses diverse differ widely their applicability, interpretability reliability different diseases. Fully automated systems have recently been approved screening diabetic retinopathy (DR). overall potential ML/DL includes screening, grading as well guidance therapy with detection disease activity, recurrences, quantification therapeutic effects identification relevant targets novel approaches. Prediction prognostic conclusions further expand benefit AI which will enable personalized health care large scale management empower ophthalmologist provide high quality diagnosis/therapy successfully deal complexity 21st century ophthalmology.

Язык: Английский

---

Artificial intelligence with multi-functional machine learning platform development for better healthcare and precision medicine

Database, Год журнала: 2020, Номер 2020

Опубликована: Янв. 1, 2020

Precision medicine is one of the recent and powerful developments in medical care, which has potential to improve traditional symptom-driven practice medicine, allowing earlier interventions using advanced diagnostics tailoring better economically personalized treatments. Identifying best pathway population involves ability analyze comprehensive patient information together with broader aspects monitor distinguish between sick relatively healthy people, will lead a understanding biological indicators that can signal shifts health. While complexities disease at individual level have made it difficult utilize healthcare clinical decision-making, some existing constraints been greatly minimized by technological advancements. To implement effective precision enhanced positively impact outcomes provide real-time decision support, important harness power electronic health records integrating disparate data sources discovering patient-specific patterns progression. Useful analytic tools, technologies, databases, approaches are required augment networking interoperability clinical, laboratory public systems, as well addressing ethical social issues related privacy protection balance. Developing multifunctional machine learning platforms for extraction, aggregation, management analysis support clinicians efficiently stratifying subjects understand specific scenarios optimize decision-making. Implementation artificial intelligence compelling vision leading significant improvements achieving goals providing real-time, lower costs. In this study, we focused on analyzing discussing various published solutions, perspectives, aiming advance academic solutions paving way new data-centric era discovery healthcare.

Язык: Английский

---

Artificial Intelligence for Mental Health and Mental Illnesses: an Overview

Current Psychiatry Reports, Год журнала: 2019, Номер 21(11)

Опубликована: Ноя. 1, 2019

Язык: Английский

---

Acceptability of artificial intelligence (AI)-led chatbot services in healthcare: A mixed-methods study

Digital Health, Год журнала: 2019, Номер 5

Опубликована: Янв. 1, 2019

Artificial intelligence (AI) is increasingly being used in healthcare. Here, AI-based chatbot systems can act as automated conversational agents, capable of promoting health, providing education, and potentially prompting behaviour change. Exploring the motivation to use health chatbots required predict uptake; however, few studies date have explored their acceptability. This research aimed explore participants' willingness engage with AI-led chatbots.The study incorporated semi-structured interviews (N-29) which informed development an online survey (N-216) advertised via social media. Interviews were recorded, transcribed verbatim analysed thematically. A 24 items demographic attitudinal variables, including acceptability perceived utility. The quantitative data using binary regressions a single categorical predictor.Three broad themes: 'Understanding chatbots', 'AI hesitancy' 'Motivations for chatbots' identified, outlining concerns about accuracy, cyber-security, inability services empathise. showed moderate (67%), correlated negatively poorer IT skills OR = 0.32 [CI95%:0.13-0.78] dislike talking computers 0.77 [CI95%:0.60-0.99] well positively utility 5.10 [CI95%:3.08-8.43], positive attitude 2.71 [CI95%:1.77-4.16] trustworthiness 1.92 [CI95%:1.13-3.25].Most internet users would be receptive chatbots, although hesitancy regarding this technology likely compromise engagement. Intervention designers focusing on need employ user-centred theory-based approaches addressing patients' optimising user experience order achieve best uptake utilisation. Patients' perspectives, capabilities taken into account when developing assessing effectiveness chatbots.

Язык: Английский

---

Med-BERT: pretrained contextualized embeddings on large-scale structured electronic health records for disease prediction

npj Digital Medicine, Год журнала: 2021, Номер 4(1)

Опубликована: Май 20, 2021

Abstract Deep learning (DL)-based predictive models from electronic health records (EHRs) deliver impressive performance in many clinical tasks. Large training cohorts, however, are often required by these to achieve high accuracy, hindering the adoption of DL-based scenarios with limited data. Recently, bidirectional encoder representations transformers (BERT) and related have achieved tremendous successes natural language processing domain. The pretraining BERT on a very large corpus generates contextualized embeddings that can boost trained smaller datasets. Inspired BERT, we propose Med-BERT, which adapts framework originally developed for text domain structured EHR Med-BERT is embedding model pretrained dataset 28,490,650 patients. Fine-tuning experiments showed substantially improves prediction boosting area under receiver operating characteristics curve (AUC) 1.21–6.14% two disease tasks databases. In particular, obtains promising performances small fine-tuning sets AUC more than 20% or obtain an as set ten times larger, compared deep without Med-BERT. We believe will benefit studies local datasets, reduce data collection expenses, accelerate pace artificial intelligence aided healthcare.

Язык: Английский

---

COVID-19: A Global Challenge with Old History, Epidemiology and Progress So Far

Molecules, Год журнала: 2020, Номер 26(1), С. 39 - 39

Опубликована: Дек. 23, 2020

Humans have witnessed three deadly pandemics so far in the twenty-first century which are associated with novel coronaviruses: SARS, Middle East respiratory syndrome (MERS), and COVID-19. All of these viruses, responsible for causing acute tract infections (ARTIs), highly contagious nature and/or caused high mortalities. The recently emerged COVID-19 disease is a transmittable viral infection by another zoonotic coronavirus named severe 2 (SARS-CoV-2). Similar to other two coronaviruses such as SARS-CoV-1 MERS-CoV, SARS-CoV-2 also likely originated from bats, been serving established reservoirs various pathogenic coronaviruses. Although, it still unknown how transmitted bats humans, rapid human-to-human transmission has confirmed widely. first appeared Wuhan, China, December 2019 quickly spread across globe, infected 48,539,872 people, 1,232,791 deaths 215 countries, spreading at time manuscript preparation. So far, there no definite line treatment approved or vaccine available. However, different types potential vaccines therapeutics evaluated under clinical trials against In this review, we summarize diseases briefly discuss earlier outbreaks compare their occurrence pathogenicity current pandemic. Various epidemiological aspects mode spread, death rate, doubling time, etc., discussed detail. Apart this, technical issues related pandemic including use masks socio-economic problems summarized. Additionally, reviewed patient management strategies mechanism action, available diagnostic tools, development effective therapeutic combinations deal outbreak. Overall, inclusion references, review covers, detail, most important

Язык: Английский

---

IoT for Smart Cities: Machine Learning Approaches in Smart Healthcare—A Review

Future Internet, Год журнала: 2021, Номер 13(8), С. 218 - 218

Опубликована: Авг. 23, 2021

Smart city is a collective term for technologies and concepts that are directed toward making cities efficient, technologically more advanced, greener socially inclusive. These include technical, economic social innovations. This has been tossed around by various actors in politics, business, administration urban planning since the 2000s to establish tech-based changes innovations areas. The idea of smart used conjunction with utilization digital at same time represents reaction economic, political challenges post-industrial societies confronted start new millennium. key focus on dealing faced society, such as environmental pollution, demographic change, population growth, healthcare, financial crisis or scarcity resources. In broader sense, also includes non-technical make life sustainable. So far, using IoT-based sensor networks healthcare applications promising one potential minimizing inefficiencies existing infrastructure. A machine learning approach successful implementation IoT-powered wireless this purpose there large amount data be handled intelligently. Throughout paper, it will discussed detail how AI-powered IoT WSNs applied sector. research baseline study understanding role cities, particular sector, future works.

Язык: Английский

---

Artificial Intelligence and Human Trust in Healthcare: Focus on Clinicians

Journal of Medical Internet Research, Год журнала: 2020, Номер 22(6), С. e15154 - e15154

Опубликована: Июнь 19, 2020

Artificial intelligence (AI) can transform health care practices with its increasing ability to translate the uncertainty and complexity in data into actionable—though imperfect—clinical decisions or suggestions. In evolving relationship between humans AI, trust is one mechanism that shapes clinicians’ use adoption of AI. Trust a psychological deal what known unknown. Several research studies have highlighted need for improving AI-based systems enhancing their capabilities help clinicians. However, assessing magnitude impact human on AI technology demands substantial attention. Will clinician an system? What are factors influence AI? Can be optimized improve decision-making processes? this paper, we focus clinicians as primary users present shaping We highlight critical challenges related should considered during development any system clinical use.

Язык: Английский

---

Unbox the black-box for the medical explainable AI via multi-modal and multi-centre data fusion: A mini-review, two showcases and beyond

Information Fusion, Год журнала: 2021, Номер 77, С. 29 - 52

Опубликована: Июль 31, 2021

Explainable Artificial Intelligence (XAI) is an emerging research topic of machine learning aimed at

Язык: Английский

---

Privacy and artificial intelligence: challenges for protecting health information in a new era

BMC Medical Ethics, Год журнала: 2021, Номер 22(1)

Опубликована: Сен. 15, 2021

Abstract Background Advances in healthcare artificial intelligence (AI) are occurring rapidly and there is a growing discussion about managing its development. Many AI technologies end up owned controlled by private entities. The nature of the implementation could mean such corporations, clinics public bodies will have greater than typical role obtaining, utilizing protecting patient health information. This raises privacy issues relating to data security. Main body first set concerns includes access, use control hands. Some recent public–private partnerships for implementing resulted poor protection privacy. As such, been calls systemic oversight big research. Appropriate safeguards must be place maintain agency. Private custodians can impacted competing goals should structurally encouraged ensure deter alternative thereof. Another relates external risk breaches through AI-driven methods. ability deidentify or anonymize may compromised even nullified light new algorithms that successfully reidentified data. increase under custodianship. Conclusions We currently familiar situation which regulation falling behind they govern. Regulation emphasize agency consent, encourage increasingly sophisticated methods anonymization protection.

Язык: Английский

---