Algorithmic fairness in artificial intelligence for medicine and healthcare

Nature Biomedical Engineering, Journal Year: 2023, Volume and Issue: 7(6), P. 719 - 742

Published: June 28, 2023

Language: Английский

---

Reactive azo compounds as a potential chemotherapy drugs in the treatment of malignant glioblastoma (GBM): Experimental and theoretical studies

Journal of Photochemistry and Photobiology, Journal Year: 2022, Volume and Issue: 10, P. 100116 - 100116

Published: March 10, 2022

This research work focuses on the synthesis, spectroscopic characterization, DFT studies, and in silico molecular docking of two azo compounds; (E)-6-((4,6-dichloro-1,3,5-triazin-2-yl)amino)-4-hydroxy-3-(phenyldiazenyl)naphthalen-2-yl hydrogen sulfite (compound A) (E)-6-((4,6-dichloro-1,3,5-triazin-2-yl)amino)-3-((4-formylphenyl)diazenyl)-4-hydroxynaphthalen-2-yl D) to determine their application as chemotherapeutic drug for treatment malignant glioblastoma multiforme (GBM). The experimental theoretical vibrational wavenumbers synthesized compounds were compared observed be good agreement. Density functional theory (DFT) at B3LYP/6-311++G(d,p) level was further utilized investigate frontier orbitals, Fukui reactivity functions, excitation energies, natural bond orbital (NBO) analysis investigation bonding interactions studied compounds. binding affinities standard (temozolomide) against four different GBM proteins: 6bft, 6s79, 1Is5, 1z2b investigated using approach. Compound A displayed highest relative -8.7 -8.6 with 6s79 1Is5 proteins respectively compound D affinity -7.6. Both showed little no interaction protein but 6s76 are relatively higher than those drug. Pharmacological studies also that both exhibit solubility water resulting lipophilicity. With obtained results, it is safe say derivatives could considered a potential or precursor synthesis other pharmaceutical products.

Language: Английский

---

Glioblastoma Therapy: Past, Present and Future

International Journal of Molecular Sciences, Journal Year: 2024, Volume and Issue: 25(5), P. 2529 - 2529

Published: Feb. 21, 2024

Glioblastoma (GB) stands out as the most prevalent and lethal form of brain cancer. Although great efforts have been made by clinicians researchers, no significant improvement in survival has achieved since Stupp protocol became standard care (SOC) 2005. Despite multimodality treatments, recurrence is almost universal with rates under 2 years after diagnosis. Here, we discuss recent progress our understanding GB pathophysiology, particular, importance glioma stem cells (GSCs), tumor microenvironment conditions, epigenetic mechanisms involved growth, aggressiveness recurrence. The discussion on therapeutic strategies first covers SOC treatment targeted therapies that shown to interfere different signaling pathways (pRB/CDK4/RB1/P16

Language: Английский

---

Artificial intelligence in neuro-oncology: advances and challenges in brain tumor diagnosis, prognosis, and precision treatment

npj Precision Oncology, Journal Year: 2024, Volume and Issue: 8(1)

Published: March 29, 2024

Abstract This review delves into the most recent advancements in applying artificial intelligence (AI) within neuro-oncology, specifically emphasizing work on gliomas, a class of brain tumors that represent significant global health issue. AI has brought transformative innovations to tumor management, utilizing imaging, histopathological, and genomic tools for efficient detection, categorization, outcome prediction, treatment planning. Assessing its influence across all facets malignant management- diagnosis, prognosis, therapy- models outperform human evaluations terms accuracy specificity. Their ability discern molecular aspects from imaging may reduce reliance invasive diagnostics accelerate time diagnoses. The covers techniques, classical machine learning deep learning, highlighting current applications challenges. Promising directions future research include multimodal data integration, generative AI, large medical language models, precise delineation characterization, addressing racial gender disparities. Adaptive personalized strategies are also emphasized optimizing clinical outcomes. Ethical, legal, social implications discussed, advocating transparency fairness integration neuro-oncology providing holistic understanding impact patient care.

Language: Английский

---

Brain tumor classification from MRI scans: a framework of hybrid deep learning model with Bayesian optimization and quantum theory-based marine predator algorithm

Frontiers in Oncology, Journal Year: 2024, Volume and Issue: 14

Published: Feb. 8, 2024

Brain tumor classification is one of the most difficult tasks for clinical diagnosis and treatment in medical image analysis. Any errors that occur throughout brain process may result a shorter human life span. Nevertheless, currently used techniques ignore certain features have particular significance relevance to problem favor extracting choosing deep features. One important area research learning-based categorization tumors using magnetic resonance imaging (MRI). This paper proposes an automated learning model optimal information fusion framework classifying from MRI images. The dataset this work was imbalanced, key challenge training selected networks. imbalance impacts performance models because it causes classifier become biased majority class. We designed sparse autoencoder network generate new images resolve imbalance. After that, two pretrained neural networks were modified hyperparameters initialized Bayesian optimization, which later utilized process. extracted global average pooling layer. contain few irrelevant information; therefore, we proposed improved Quantum Theory-based Marine Predator Optimization algorithm (QTbMPA). QTbMPA selects both networks’ best finally fuses serial-based approach. fused feature set passed classifiers final classification. tested on augmented Figshare accuracy 99.80%, sensitivity rate 99.83%, false negative 17%, precision 99.83% obtained. Comparison ablation study show improvement work.

Language: Английский

---

Harnessing the Stem Cell Niche in Regenerative Medicine: Innovative Avenue to Combat Neurodegenerative Diseases

International Journal of Molecular Sciences, Journal Year: 2024, Volume and Issue: 25(2), P. 993 - 993

Published: Jan. 12, 2024

Regenerative medicine harnesses the body's innate capacity for self-repair to restore malfunctioning tissues and organs. Stem cell therapies represent a key regenerative strategy, but effectively harness their potential necessitates nuanced understanding of stem niche. This specialized microenvironment regulates critical behaviors including quiescence, activation, differentiation, homing. Emerging research reveals that dysfunction within endogenous neural niches contributes neurodegenerative pathologies impedes regeneration. Strategies such as modifying signaling pathways, or epigenetic interventions niche homeostasis signaling, hold promise revitalizing neurogenesis repair in diseases like Alzheimer's Parkinson's. Comparative studies highly species provide evolutionary clues into niche-mediated renewal mechanisms. Leveraging bioelectric cues crosstalk between gut, brain, vascular further illuminates promising therapeutic opportunities. techniques single-cell transcriptomics, organoids, microfluidics, artificial intelligence, silico modeling, transdifferentiation will continue unravel complexity. By providing comprehensive synthesis integrating diverse views on components, developmental transitions, dynamics, this review unveils new layers complexity integral behavior function, which unveil novel prospects modulate function revolutionary treatments diseases.

Language: Английский

---

Successful application of dietary ketogenic metabolic therapy in patients with glioblastoma: a clinical study

Frontiers in Nutrition, Journal Year: 2025, Volume and Issue: 11

Published: Feb. 18, 2025

Glioblastoma multiforme (GBM) ranks as one of the most aggressive primary malignant tumor affecting brain. The persistent challenge treatment failure and high relapse rates in GBM highlights need for new approaches. Recent research has pivoted toward exploring alternative therapeutic methods, such ketogenic diet, GBM. A total 18 patients with GBM, 8 women 10 men, aged between 34 75 years participated a prospective study, examining impact diet on progression. pool originated from our hospital during period January 2016 until July 2021 were followed 2024. As an assessment criterion, we set optimistic target adherence to beyond 6 months. We considered combination successful if survival reached at least 3 years. Among participating adhered more than Of these patients, patient passed away 43 months after diagnosis, achieving years; another 36 months, narrowly missing 3-year mark; is still alive 33 post-diagnosis but yet reach milestone is, therefore, not included final rate calculation. remaining are also alive, completing 84,43 44 life, respectively. Consequently, among 4 out 6, or 66.7%. 12 who did adhere only survival, while rest have died average time 15.7 ± 6.7 8.3%. Comparing two groups, see that difference 58.3% (66.7% versus 8.3%) statistically significant p < 0.05 (0.0114) X2 = 6.409. outcomes observed offer promising insights into potential benefits progression glioblastoma when compared those follow consistently.

Language: Английский

---

Bias and Class Imbalance in Oncologic Data—Towards Inclusive and Transferrable AI in Large Scale Oncology Data Sets

Cancers, Journal Year: 2022, Volume and Issue: 14(12), P. 2897 - 2897

Published: June 12, 2022

Recent technological developments have led to an increase in the size and types of data medical field derived from multiple platforms such as proteomic, genomic, imaging, clinical data. Many machine learning models been developed support precision/personalized medicine initiatives computer-aided detection, diagnosis, prognosis, treatment planning by using large-scale Bias class imbalance represent two most pressing challenges for learning-based problems, particularly (e.g., oncologic) sets, due limitations patient numbers, cost, privacy, security sharing, complexity generated Depending on set research question, methods applied address problems can provide more effective, successful, meaningful results. This review discusses essential strategies addressing mitigating different oncologic domain.

Language: Английский

---

Multimodal brain tumor segmentation and classification from MRI scans based on optimized DeepLabV3+ and interpreted networks information fusion empowered with explainable AI

Computers in Biology and Medicine, Journal Year: 2024, Volume and Issue: 182, P. 109183 - 109183

Published: Oct. 2, 2024

Language: Английский

---

Sex difference in human diseases: mechanistic insights and clinical implications

Signal Transduction and Targeted Therapy, Journal Year: 2024, Volume and Issue: 9(1)

Published: Sept. 10, 2024

Abstract Sex characteristics exhibit significant disparities in various human diseases, including prevalent cardiovascular cancers, metabolic disorders, autoimmune and neurodegenerative diseases. Risk profiles pathological manifestations of these diseases notable variations between sexes. The underlying reasons for sex encompass multifactorial elements, such as physiology, genetics, environment. Recent studies have shown that body systems demonstrate sex-specific gene expression during critical developmental stages editing processes. These genes, differentially expressed based on different sex, may be regulated by androgen or estrogen-responsive thereby influencing the incidence presentation cardiovascular, oncological, metabolic, immune, neurological across However, despite existence differences patients with treatment guidelines predominantly rely male data due to underrepresentation women clinical trials. At present, there exists a substantial knowledge gap concerning mechanisms treatments diverse Therefore, this review aims elucidate advances examining epidemiological factors, pathogenesis, innovative progress accordance distinctive risk each disease provide new theoretical practical basis further optimizing individualized improving patient prognosis.

Language: Английский

---