Artificial intelligence in pancreatic cancer

Theranostics, Journal Year: 2022, Volume and Issue: 12(16), P. 6931 - 6954

Published: Jan. 1, 2022

Pancreatic cancer is the deadliest disease, with a five-year overall survival rate of just 11%.The pancreatic patients diagnosed early screening have median nearly ten years, compared 1.5 years for those not screening.Therefore, diagnosis and treatment are particularly critical.However, as rare general cost high, accuracy existing tumor markers enough, efficacy methods exact.In terms diagnosis, artificial intelligence technology can quickly locate high-risk groups through medical images, pathological examination, biomarkers, other aspects, then lesions early.At same time, algorithm also be used to predict recurrence risk, metastasis, therapy response which could affect prognosis.In addition, widely in health records, estimating imaging parameters, developing computer-aided systems, etc. Advances AI applications will require concerted effort among clinicians, basic scientists, statisticians, engineers.Although it has some limitations, play an essential role overcoming foreseeable future due its mighty computing power.

Language: Английский

---

From machine learning to deep learning: Advances of the recent data-driven paradigm shift in medicine and healthcare

Current Research in Biotechnology, Journal Year: 2023, Volume and Issue: 7, P. 100164 - 100164

Published: Nov. 22, 2023

The medicine and healthcare sector has been evolving advancing very fast. advancement initiated shaped by the applications of data-driven, robust, efficient machine learning (ML) to deep (DL) technologies. ML in medical is developing quickly, causing rapid progress, reshaping medicine, improving clinician patient experiences. technologies evolved into data-hungry DL approaches, which are more robust dealing with data. This article reviews some critical data-driven aspects intelligence field. In this direction, illustrated recent progress science using two categories: firstly, development data uses and, secondly, Chabot particularly on ChatGPT. Here, we discuss ML, DL, transition requirements from DL. To science, illustrate prospective studies image data, newly interpretation EMR or EHR, big personalized dataset shifts artificial (AI). Simultaneously, recently developed DL-enabled ChatGPT technology. Finally, summarize broad role significant challenges for implementing healthcare. overview paradigm shift will benefit researchers immensely.

Language: Английский

---

An energy-aware and Q-learning-based area coverage for oil pipeline monitoring systems using sensors and Internet of Things

Scientific Reports, Journal Year: 2022, Volume and Issue: 12(1)

Published: June 10, 2022

Pipelines are the safest tools for transporting oil and gas. However, environmental effects sabotage of hostile people cause corrosion decay pipelines, which bring financial damages. Today, new technologies such as Internet Things (IoT) wireless sensor networks (WSNs) can provide solutions to monitor timely detect pipelines. Coverage is a fundamental challenge in pipeline monitoring systems resolve leakage corrosion. To ensure appropriate coverage on systems, one solution design scheduling mechanism nodes reduce energy consumption. In this paper, we propose reinforcement learning-based area technique called CoWSN intelligently gas CoWSN, sensing range each node converted digital matrix estimate overlap with other neighboring nodes. Then, Q-learning-based designed determine activity time based their overlapping, energy, distance base station. Finally, predict death replace them at right time. This work does not allow be disrupted data transmission process between BS. simulated using NS2. our scheme compared three schemes, including Rahmani et al., CCM-RL, CCA according several parameters, average number active nodes, rate, consumption, network lifetime. The simulation results show that has better performance than methods.

Language: Английский

---

Machine learning in perioperative medicine: a systematic review

Journal of Anesthesia Analgesia and Critical Care, Journal Year: 2022, Volume and Issue: 2(1)

Published: Jan. 15, 2022

Risk stratification plays a central role in anesthetic evaluation. The use of Big Data and machine learning (ML) offers considerable advantages for collection evaluation large amounts complex health-care data. We conducted systematic review to understand the ML development predictive post-surgical outcome models risk stratification.Following Preferred Reporting Items Systematic Reviews Meta-analyses (PRISMA) guidelines, we selected period research studies from 1 January 2015 up 30 March 2021. A search Scopus, CINAHL, Cochrane Library, PubMed, MeSH databases was performed; strings included different combinations keywords: "risk prediction," "surgery," "machine learning," "intensive care unit (ICU)," "anesthesia" "perioperative." identified 36 eligible studies. This study evaluates quality reporting prediction using Transparent Multivariable Prediction Model Individual Prognosis or Diagnosis (TRIPOD) checklist.The most considered outcomes were mortality risk, systemic complications (pulmonary, cardiovascular, acute kidney injury (AKI), etc.), ICU admission, anesthesiologic prolonged length hospital stay. Not all completely followed TRIPOD checklist, but overall acceptable with 75% (Rev #2, comm #minor issue) showing an adherence rate more than 60%. frequently used algorithms gradient boosting (n = 13), random forest 10), logistic regression (LR; n 7), artificial neural networks (ANNs; 6), support vector machines (SVM; 6). Models best performance boosting, AUC > 0.90.The application medicine appears have great potential. From our analysis, depending on input features specific task, seem effective accurately validated prognostic scores traditional statistics. Thus, encourages healthcare domain intelligence (AI) developers adopt interdisciplinary approach evaluate impact AI perioperative assessment further health settings as well.

Language: Английский

---

Reinforcement Learning-Based Routing Protocols in Flying Ad Hoc Networks (FANET): A Review

Mathematics, Journal Year: 2022, Volume and Issue: 10(16), P. 3017 - 3017

Published: Aug. 22, 2022

In recent years, flying ad hoc networks have attracted the attention of many researchers in industry and universities due to easy deployment, proper operational costs, diverse applications. Designing an efficient routing protocol is challenging unique characteristics these such as very fast motion nodes, frequent changes topology, low density. Routing protocols determine how provide communications between drones a wireless network. Today, reinforcement learning (RL) provides powerful solutions solve existing problems protocols, designs autonomous, adaptive, self-learning protocols. The main purpose ensure stable solution with delay minimum energy consumption. this paper, learning-based methods FANET are surveyed studied. Initially, learning, Markov decision process (MDP), algorithms briefly described. Then, networks, various types drones, their applications, introduced. Furthermore, its challenges explained FANET. classification suggested for networks. This categorizes based on algorithm, data dissemination process. Finally, we present opportunities field detailed accurate view be aware future research directions order improve algorithms.

Language: Английский

---

Identification of kidney stones in KUB X-ray images using VGG16 empowered with explainable artificial intelligence

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: March 14, 2024

Abstract A kidney stone is a solid formation that can lead to failure, severe pain, and reduced quality of life from urinary system blockages. While medical experts interpret kidney-ureter-bladder (KUB) X-ray images, specific images pose challenges for human detection, requiring significant analysis time. Consequently, developing detection becomes crucial accurately classifying KUB images. This article applies transfer learning (TL) model with pre-trained VGG16 empowered explainable artificial intelligence (XAI) establish takes categorizes them as stones or normal cases. The findings demonstrate the achieves testing accuracy 97.41% in identifying X-rays dataset used. delivers highly accurate predictions but lacks fairness explainability their decision-making process. study incorporates Layer-Wise Relevance Propagation (LRP) technique, an enhance transparency effectiveness address this concern. XAI specifically LRP, increases model's transparency, facilitating comprehension predictions. play important role assisting doctors identification stones, thereby execution effective treatment strategies.

Language: Английский

---

Advancements in Pancreatic Cancer Detection: Integrating Biomarkers, Imaging Technologies, and Machine Learning for Early Diagnosis

Cureus, Journal Year: 2024, Volume and Issue: unknown

Published: March 20, 2024

Artificial intelligence (AI) has come to play a pivotal role in revolutionizing medical practices, particularly the field of pancreatic cancer detection and management. As leading cause cancer-related deaths, warrants innovative approaches due its typically advanced stage at diagnosis dismal survival rates. Present methods, constrained by limitations accuracy efficiency, underscore necessity for novel solutions. AI-driven methodologies present promising avenues enhancing early prognosis forecasting. Through analysis imaging data, biomarker profiles, clinical information, AI algorithms excel discerning subtle abnormalities indicative with remarkable precision. Moreover, machine learning (ML) facilitate amalgamation diverse data sources optimize patient care. However, despite huge potential, implementation faces various challenges. Issues such as scarcity comprehensive datasets, biases algorithm development, concerns regarding privacy security necessitate thorough scrutiny. While offers immense promise transforming management, ongoing research collaborative efforts are indispensable overcoming technical hurdles ethical dilemmas. This review delves into evolution AI, application detection, challenges considerations inherent integration.

Language: Английский

---

A Survey of Machine Learning Approaches for Mobile Robot Control

Robotics, Journal Year: 2024, Volume and Issue: 13(1), P. 12 - 12

Published: Jan. 9, 2024

Machine learning (ML) is a branch of artificial intelligence that has been developing at dynamic pace in recent years. ML also linked with Big Data, which are huge datasets need special tools and approaches to process them. algorithms make use data learn how perform specific tasks or appropriate decisions. This paper presents comprehensive survey have applied the task mobile robot control, they divided into following: supervised learning, unsupervised reinforcement learning. The distinction methods wheeled robots walking presented paper. strengths weaknesses compared formulated, future prospects proposed. results carried out literature review enable one state different tasks, such as position estimation, environment mapping, SLAM, terrain classification, obstacle avoidance, path following, walk, multirobot coordination. allowed us associate most commonly used robotic tasks. There still exist many open questions challenges complex limited computational resources on board robot; decision making motion control real time; adaptability changing environments; acquisition large volumes valuable data; assurance safety reliability robot’s operation. development for nature-inspired seems be challenging research issue there exists very amount solutions literature.

Language: Английский

---

Learning across diverse biomedical data modalities and cohorts: Challenges and opportunities for innovation

Patterns, Journal Year: 2024, Volume and Issue: 5(2), P. 100913 - 100913

Published: Jan. 17, 2024

In healthcare, machine learning (ML) shows significant potential to augment patient care, improve population health, and streamline healthcare workflows. Realizing its full is, however, often hampered by concerns about data privacy, diversity in sources, suboptimal utilization of different modalities. This review studies the utility cross-cohort cross-category (C

Language: Английский

---

Understanding machine learning applications in dementia research and clinical practice: a review for biomedical scientists and clinicians

Alzheimer s Research & Therapy, Journal Year: 2024, Volume and Issue: 16(1)

Published: Aug. 1, 2024

Abstract Several (inter)national longitudinal dementia observational datasets encompassing demographic information, neuroimaging, biomarkers, neuropsychological evaluations, and muti-omics data, have ushered in a new era of potential for integrating machine learning (ML) into research clinical practice. ML, with its proficiency handling multi-modal high-dimensional has emerged as an innovative technique to facilitate early diagnosis, differential predict onset progression mild cognitive impairment dementia. In this review, we evaluate current applications including history research, how it compares traditional statistics, the types uses general workflow. Moreover, identify technical barriers challenges ML implementations Overall, review provides comprehensive understanding non-technical explanations broader accessibility biomedical scientists clinicians.

Language: Английский

---