RESUMEN

STUDY DESIGN: This study was a retrospective propensity-matched study of patients receiving opioid sparing anesthesia (OSA) and those who did not receive an opioid sparing anesthesia regimen. OBJECTIVES: To determine whether patients undergoing spine fusion for deformity fared better with an OSA regimen than those not having an OSA regimen. SUMMARY OF BACKGROUND DATA: There has been a tremendous focus on opioid overuse. Accordingly, OSA regimens are being introduced to reduce narcotic use. However, OSA has not been studied in the adult spine deformity population. METHODS: 43 patients undergoing fusion of at least five levels in the thoracolumbar spine received OSA. They were matched to 43 patients who did receive an OSA regimen. We analyzed a number of metrics including blood loss, anesthesia time, post anesthesia care unit (PACU) pain scores, postoperative pain scores, complications, length of stay, and readmissions. RESULTS: The OSA group had significantly lower pain scores both before transfer to (4.6 vs. 7.6, P=0.000) and after transfer from (4.2 vs. 6.2 P=0.002) the PACU. Opioid use was significantly lower in the OSA group (454 vs. 241 MMEs by POD4, P=0.022). Fewer patients required blood transfusion in the OSA (1 vs. 28, P=0.000) group. Fewer patients in the OSA group had constipation and urinary retention (1 vs. 9, P=0.015). There was no difference in discharge home or to a facility. The lengths of hospital (4.33 vs. 6.19, P=0.009) and ICU (0.12 vs. 0.70 days, P=0.009) stay were significantly shorter in the OSA group. CONCLUSION: OSA regimens have numerous benefits in patients undergoing spinal deformity surgery including less opioid use, fewer postoperative complications, and a reduced length of stay.

RESUMEN

RNA transcripts are potential therapeutic targets, yet bacterial transcripts have uncharacterized biodiversity. We developed an algorithm for transcript prediction called tp.py using it to predict transcripts (mRNA and other RNAs) in Escherichia coli K12 and E2348/69 strains (Bacteria:gamma-Proteobacteria), Listeria monocytogenes strains Scott A and RO15 (Bacteria:Firmicute), Pseudomonas aeruginosa strains SG17M and NN2 strains (Bacteria:gamma-Proteobacteria), and Haloferax volcanii (Archaea:Halobacteria). From >5 million E. coli K12 and >3 million E. coli E2348/69 newly generated Oxford Nanopore Technologies direct RNA sequencing reads, 2,487 K12 mRNAs and 1,844 E2348/69 mRNAs were predicted, with the K12 mRNAs containing more than half of the predicted E. coli K12 proteins. While the number of predicted transcripts varied by strain based on the amount of sequence data used, across all strains examined, the predicted average size of the mRNAs was 1.6-1.7 kbp, while the median size of the 5'- and 3'-untranslated regions (UTRs) were 30-90 bp. Given the lack of bacterial and archaeal transcript annotation, most predictions were of novel transcripts, but we also predicted many previously characterized mRNAs and ncRNAs, including post-transcriptionally generated transcripts and small RNAs associated with pathogenesis in the E. coli E2348/69 LEE pathogenicity islands. We predicted small transcripts in the 100-200 bp range as well as >10 kbp transcripts for all strains, with the longest transcript for two of the seven strains being the nuo operon transcript, and for another two strains it was a phage/prophage transcript. This quick, easy, and reproducible method will facilitate the presentation of transcripts, and UTR predictions alongside coding sequences and protein predictions in bacterial genome annotation as important resources for the research community.IMPORTANCEOur understanding of bacterial and archaeal genes and genomes is largely focused on proteins since there have only been limited efforts to describe bacterial/archaeal RNA diversity. This contrasts with studies on the human genome, where transcripts were sequenced prior to the release of the human genome over two decades ago. We developed software for the quick, easy, and reproducible prediction of bacterial and archaeal transcripts from Oxford Nanopore Technologies direct RNA sequencing data. These predictions are urgently needed for more accurate studies examining bacterial/archaeal gene regulation, including regulation of virulence factors, and for the development of novel RNA-based therapeutics and diagnostics to combat bacterial pathogens, like those with extreme antimicrobial resistance.

RESUMEN

Neofunctionalization of duplicated gene copies is thought to be an important process underlying the origin of evolutionary novelty and provides an elegant mechanism for the origin of new phenotypic traits. One putative case where a new gene copy has been linked to a novel morphological trait is the origin of the arachnid patella, a taxonomically restricted leg segment. In spiders, the origin of this segment has been linked to the origin of the paralog dachshund-2, suggesting that a new gene facilitated the expression of a new trait. However, various arachnid groups that possess patellae do not have a copy of dachshund-2, disfavoring the direct link between gene origin and trait origin. We investigated the developmental genetic basis for patellar patterning in the harvestman Phalangium opilio, which lacks dachshund-2. Here, we show that the harvestman patella is established by a novel expression domain of the transcription factor extradenticle. Leveraging this definition of patellar identity, we surveyed targeted groups across chelicerate phylogeny to assess when this trait evolved. We show that a patellar homolog is present in Pycnogonida (sea spiders) and various arachnid orders, suggesting a single origin of the patella in the ancestor of Chelicerata. A potential loss of the patella is observed in Ixodida. Our results suggest that the modification of an ancient gene, rather than the neofunctionalization of a new gene copy, underlies the origin of the patella. Broadly, this work underscores the value of comparative data and broad taxonomic sampling when testing hypotheses in evolutionary developmental biology.

RESUMEN

PURPOSE: Individuals with walking impairment, such as those with cerebral palsy, often face challenges in leading physically active lives due to the high energy cost of movement. Assistive devices like powered exoskeletons aim to alleviate this burden and improve mobility. Traditionally, optimizing the effectiveness of such devices has relied on time-consuming laboratory-based measurements of energy expenditure, which may not be feasible for some patient populations. To address this, our study aimed to enhance the state-of-the-art predictive model for estimating steady-state metabolic rate from 2-min walking trials to include individuals with and without walking disabilities and for a variety of terrains and wearable device conditions. METHODS: Using over 200 walking trials collected from eight prior exoskeleton-related studies, we trained a simple linear machine learning model to predict metabolic power at steady state based on condition-specific factors, such as whether the trial was conducted on a treadmill (level or incline) or outdoors, as well as demographic information, such as the participant's weight or presence of walking impairment, and 2 minutes of metabolic data. RESULTS: We demonstrated the ability to predict steady-state metabolic rate to within an accuracy of 4.71 ± 2.7% on average across all walking conditions and patient populations, including with assistive devices and on different terrains. CONCLUSION: This work seeks to unlock the use of in-the-loop optimization of wearable assistive devices in individuals with limited walking capacity. A freely available MATLAB application allows other researchers to easily apply our model.

RESUMEN

BACKGROUND: Patients with severe traumatic brain injury (TBI) are at an increased risk of respiratory failure refractory to traditional therapies. The safety of extracorporeal membrane oxygenation (ECMO) in this population remains unclear. We aimed to examine outcomes following ECMO compared with traditional management in severe TBI patients. METHODS: We performed a retrospective cohort study using the Trauma Quality Improvement Program (2017-2020). We identified patients 18 years or older with severe TBI (Abbreviated Injury Score head, ≥3) who underwent ECMO or had either in-hospital cardiac or acute respiratory distress syndrome during their hospitalization. The study excluded pPatients who arrived without signs of life, had a prehospital cardiac arrest, had an unsurvivable injury, were transferred out within 48 hours of arrival, or were received as a transfer and died within 12 hours of arrival Patients with missing information regarding in-hospital mortality were also excluded. Outcomes included mortality, in-hospital complications, and intensive care unit length of stay. To account for patient and injury characteristics, we used 1:1 propensity matching. We performed a subgroup analysis among ECMO patients, comparing patients who received anticoagulants with those who did not. RESULTS: We identified 10,065 patients, of whom 221 (2.2%) underwent ECMO. In the propensity-matched sample of 134 pairs, there was no difference in mortality. Extracorporeal membrane oxygenation was associated with a higher incidence of cerebrovascular accidents (9% vs. 1%, p = 0.006) and a lower incidence of ventilator-associated pneumonia. In the subgroup analysis of 64 matched pairs, patients receiving anticoagulation had lower mortality, higher unplanned return to the operating room, and longer duration of ventilation and intensive care unit length of stay. CONCLUSION: Extracorporeal membrane oxygenation use in severe TBI patients was not associated with higher mortality and should be considered a potential intervention in this patient population. Systemic anticoagulation showed mortality benefit, but further work is required to elucidate the impact on neurological outcomes, and the appropriate dosing and timing of anticoagulation. LEVEL OF EVIDENCE: Therapeutic; Level IV.

RESUMEN

This paper summarizes the history and evolution of the electroencephalogram (EEG). The EEG, used to record the electrical activity of the brain, is a pivotal tool in neuroscience and medicine. Its history and evolution reflect significant advancements in our understanding of brain function and our ability to diagnose and treat neurological conditions. This tool has revolutionized our understanding of the brain's electrical activity and is the cornerstone for the diagnosis and treatment of epilepsy and related disorders. The evolution of the EEG from early experimental observations to sophisticated modern applications highlights the profound progress in our ability to monitor and interpret brain activity. The EEG remains an invaluable tool in clinical and research settings, continually evolving with technological advancements to expand our understanding of the human brain. This review traces the journey of this iconic tool.

RESUMEN

BACKGROUND: Non-hypothalamic glioneural hamartomas are rare entities known to cause medically refractory epilepsy. Olfactory bulb hamartomas, in particular, are exceptionally rare. METHODS: We describe a case of an olfactory bulb hamartoma that was surgically resected at our institution. We also performed a literature review of all glioneural hamartomas and discuss the clinical presentation, diagnosis, and management of these lesions. RESULTS: Herein, we present the unusual case of a typically developing 17-year-old boy with a near life-long history of drug-resistant epilepsy, found to have a 0.8 × 1.0 cm right olfactory bulb hamartoma. Endoscopic endonasal trans-cribriform resection of the lesion led to seizure freedom in the 6-month follow-up period (Engel class 1 outcome). Comprehensive literature review revealed only one other sporadic case, which was also successfully treated with total surgical resection. CONCLUSIONS: Our case of an olfactory bulb hamartoma adds to the limited literature currently available, illustrating key clinical characteristics of these exceedingly rare lesions and outlining an effective, minimally invasive, and low-morbidity treatment strategy.

RESUMEN

Background: Volatile organic compounds (VOCs) are major components of air pollution and tobacco smoke, two known risk factors for cardiovascular diseases. VOCs are ubiquitous in the environment and originate from a wide range of sources, including the burning of biomass, fossil fuels, and consumer products. Direct evidence for associations between specific VOCs and ischemic heart disease (IHD) mortality in the general population is scarce. Methods: In a case-cohort study (stratified by age groups, sex, residence, and tobacco smoking), nested within the population-based Golestan cohort study (n = 50,045, 40-75 years, 58% women, enrollment: 2004-2008) in northeastern Iran, we measured urinary concentrations of 20 smoking-related VOC biomarkers using ultra high-performance liquid chromatography coupled with electrospray ionization tandem mass spectrometry. We calculated hazard ratio (HR) and 95% confidence interval (CI) for their associations with IHD mortality during follow-up to 2018, using Cox regression models adjusted for age, ethnicity, education, marital status, body mass index, physical activity, wealth, and urinary cotinine. Results: There were 575 non-cases from random subcohort and 601 participants who died from IHD, mean (standard deviation) age, 58.2 (9.3) years, with a median of 8.4 years follow-up. Significant associations [3rd vs. 1st tertile, HR (95% CI), P for trend] were observed between biomarkers of acrylamide [1.68(1.05,2.69), 0.025], acrylonitrile [2.06(1.14,3.72), 0.058], acrolein [1.98(1.30,3.01), 0.003 and 2.44(1.43,4.18), 0.002], styrene/ethylbenzene [1.83(1.19,2.84), 0.007 and 1.44(1.01,2.07), 0.046], dimethylformamide/methylisocyanate [2.15(1.33,3.50), 0.001], and 1,3butadiene [2.35(1.52,3.63),<0.001] and IHD mortality. These associations were independent of tobacco smoking, and they were only present in the non-smoking subgroup. Conclusion: Our findings provide direct evidence for associations between exposure to several VOCs with widespread household and commercial use and IHD mortality many years after these exposures. These results highlight the importance of VOC exposure in the general population as a risk factor for cardiovascular diseases and underline the importance of bio-monitoring non-tobacco VOC exposure.

RESUMEN

BACKGROUND AND AIM: Pregnancy is a key setting for engagement in chronic hepatitis B (CHB) care, due to the implications for transmission to the infant and antenatal diagnosis representing an opportunity for ongoing follow-up. This study aimed to identify the coverage and predictors of clinical care for women with CHB during and after pregnancy in a population-level cohort. METHODS: Notified CHB cases in Victoria, Australia, were linked with hospitalizations, medical services, and prescribing data, covering the period 1991-2018. Women with an admission for a live birth were identified and services provided during pregnancy were assessed, including general practitioner (GP) or specialist visits, viral load and serology testing, and antiviral treatment. Viral load and serology testing coverage ware also assessed for the 2-year period following pregnancy. Demographic and clinical predictors of viral load testing during pregnancy were assessed. RESULTS: A total of 11 015 birth events occurred for 6090 women with CHB. During pregnancy most had a GP consultation (91.6%); however, only 39.5% had viral load testing and 41.4% had a gastroenterology or infectious diseases specialist consultation. Viral load testing and serology testing in the 2 years after pregnancy occurred in approximately half (47.9% and 52.2%, respectively) with increases over time. Viral load testing was more likely in those born overseas, those with more than one previous birth, and those living in Melbourne. CONCLUSIONS: Despite improvements over time, key gaps were identified in the provision of CHB clinical care during and after pregnancy, with implications for ongoing transmission and adverse outcomes.

RESUMEN

Recent landmark trials showed that colchicine provides a substantial benefit in reducing major cardiovascular events in patients with coronary artery disease. Yet, its exact mechanism of action is still poorly understood. This study aimed to unravel the effect of colchicine on monocyte and neutrophil phenotype and function. A randomized double-blind placebo-controlled cross-over intervention study was executed in patients with a history of myocardial infarction. In neutrophils, colchicine treatment decreased CD62L expression and NGAL release upon ex vivo stimulation and increased PMA-induced ROS production. The effects of colchicine on monocytes were limited to a decrease in HLA-DR expression in the intermediate and nonclassical monocytes. Also, on the level of RNA expression, colchicine did not affect monocyte phenotype, while affecting various immunomodulating genes in neutrophils. Overall, our study suggests that treatment with colchicine affects neutrophil function, particularly by reducing neutrophil recruitment, lowering concentrations of NGAL, and changing the expression of various genes with immunomodulatory potential, whereas the effect on monocytes is limited.

RESUMEN

OBJECTIVE: Intracranial complications of acute bacterial sinusitis are rare pathologies that occur in children, and are associated with significant neurological morbidity and mortality. There is a subjective concern among neurosurgeons that the incidence of this rare disease has increased since the onset of the novel COVID-19 pandemic. The primary objective of this study was to review the presentation and management of patients admitted at the authors' institution with intracranial extension of sinusitis, to better understand the local disease burden relative to the COVID-19 pandemic. METHODS: This is a single-center retrospective observational cohort study. The patients underwent neurosurgical intervention for intracranial extension of sinusitis between January 1, 2007, and March 1, 2023. The historical cohort was defined as those patients who presented prior to March 2020. Clinical covariates such as surgical and microbiological data were collected and analyzed. RESULTS: A total of 78 patients (55 historical, 23 new) were included; they had a median age of 11.7 years and a male predominance of 69.2%. There was a significant increase in the annual rate of neurosurgical intervention for suppurative intracranial extension of acute bacterial sinusitis after the onset of the COVID-19 pandemic, with an average of 4.2 cases per year prior to March 2020 compared to 7.7 cases per year after that date (p = 0.013). This increase was largely driven by the unprecedented case volume of 13 cases in 2022. Patients in the new cohort were older (p = 0.009) and more likely to have Pott's puffy tumor/frontal bone osteomyelitis (p = 0.003) at the time of presentation than patients in the historical cohort. Patients in the new cohort had lower rates of readmission within 30 days of discharge than those in the historical cohort (p = 0.047). In both cohorts, patients with seizure on presentation were more likely to have neurological sequelae at last follow-up (p = 0.004), which occurred at a median of 2.9 months after discharge. CONCLUSIONS: Clinicians encountering pediatric patients presenting with persistent symptoms of acute bacterial sinusitis must have a high index of suspicion for suppurative intracranial extension. Prompt neuroimaging and subsequent neurosurgical intervention are critical to ensure timely diagnosis and treatment. The results in this study show a significant increase in the number of neurosurgical interventions for suppurative intracranial extension of sinusitis per year after the onset of the COVID-19 pandemic. Further research is needed to understand the underlying pathophysiology of this clinical phenomenon.

RESUMEN

Therapeutically targeting the brain requires interactions with endothelial cells, pericytes, and astrocytes at the blood brain barrier (BBB). We evaluated regional and cell-type specific drug metabolism and transport mechanisms using rhesus macaques and in vitro treatment of primary human cells. Here, we report heterogenous distribution of representative drugs, tenofovir (TFV), emtricitabine (FTC), and their active metabolites, which cerebrospinal fluid measures could not reflect. We found that all BBB cell types possessed functional drug metabolizing enzymes and transporters that promoted TFV and FTC uptake and pharmacologic activation. Pericytes and astrocytes emerged as pharmacologically dynamic cells that rivaled hepatocytes and were uniquely susceptible to modulation by disease and treatment. Together, our findings demonstrate the importance of considering the BBB as a unique pharmacologic entity, rather than viewing it as an extension of the liver, as each cell type possesses distinct drug metabolism and transport capacities that contribute to differential brain drug disposition.

RESUMEN

Individual-based simulation has become an increasingly crucial tool for many fields of population biology. However, implementing realistic and stable simulations in continuous space presents a variety of difficulties, from modeling choices to computational efficiency. This paper aims to be a practical guide to spatial simulation, helping researchers to implement realistic and efficient spatial, individual-based simulations and avoid common pitfalls. To do this, we delve into mechanisms of mating, reproduction, density-dependent feedback, and dispersal, all of which may vary across the landscape, discuss how these affect population dynamics, and describe how to parameterize simulations in convenient ways (for instance, to achieve a desired population density). We also demonstrate how to implement these models using the current version of the individual-based simulator, SLiM. Since SLiM has the capacity to simulate genomes, we also discuss natural selection - in particular, how genetic variation can affect demographic processes. Finally, we provide four short vignettes: simulations of pikas that shift their range up a mountain as temperatures rise; mosquitoes that live in rivers as juveniles and experience seasonally changing habitat; cane toads that expand across Australia, reaching 120 million individuals; and monarch butterflies whose populations are regulated by an explicitly modeled resource (milkweed).

RESUMEN

BACKGROUND: Spina bifida is a type of neural tube defect (NTD); NTDs are developmental malformations of the spinal cord that result from failure of neural tube closure during embryogenesis and are likely caused by interactions between genetic and environmental factors. Arsenic induces NTDs in animal models, and studies demonstrate that mice with genetic defects related to folate metabolism are more susceptible to arsenic's effects. We sought to determine whether 25 single-nucleotide polymorphisms (SNPs) in genes involved in folate and arsenic metabolism modified the associations between maternal arsenic exposure and risk of spina bifida (a common NTD) among a hospital-based case-control study population in Bangladesh. METHODS: We used data from 262 mothers and 220 infants who participated in a case‒control study at the National Institutes of Neurosciences & Hospital and Dhaka Shishu Hospital in Dhaka, Bangladesh. Neurosurgeons assessed infants using physical examinations, review of imaging, and we collected histories using questionnaires. We assessed arsenic from mothers' toenails using inductively coupled plasma mass spectrometry (ICP-MS), and we genotyped participants using the Illumina Global Screening Array v1.0. We chose candidate genes and SNPs through a review of the literature. We assessed SNP-environment interactions using interaction terms and stratified models, and we assessed gene-environment interactions using interaction sequence/SNP-set kernel association tests (iSKAT). RESULTS: The median toenail arsenic concentration was 0.42 µg/g (interquartile range [IQR]: 0.27-0.86) among mothers of cases and 0.47 µg/g (IQR: 0.30-0.97) among mothers of controls. We found an two SNPs in the infants' AS3MT gene (rs11191454 and rs7085104) and one SNP in mothers' DNMT1 gene (rs2228611) were associated with increased odds of spina bifida in the setting of high arsenic exposure (rs11191454, OR 3.01, 95% CI: 1.28-7.09; rs7085104, OR 2.33, 95% CI: 1.20-4.and rs2228611, OR 2.11, 95% CI: 1.11-4.01), along with significant SNP-arsenic interactions. iSKAT analyses revealed significant interactions between mothers' toenail concentrations and infants' AS3MT and MTR genes (p = 0.02), and mothers' CBS gene (p = 0.05). CONCLUSIONS: Our results support the hypothesis that arsenic increases spina bifida risk via interactions with folate and arsenic metabolic pathways and suggests that individuals in the population who have certain genetic polymorphisms in genes involved with arsenic and folate metabolism may be more susceptible than others to the arsenic teratogenicity.

Asunto(s)

RESUMEN

Electronic skins (e-skins) have seen intense research and rapid development in the past two decades. To mimic the capabilities of human skin, a multitude of flexible/stretchable sensors that detect physiological and environmental signals have been designed and integrated into functional systems. Recently, researchers have increasingly deployed machine learning and other artificial intelligence (AI) technologies to mimic the human neural system for the processing and analysis of sensory data collected by e-skins. Integrating AI has the potential to enable advanced applications in robotics, healthcare, and human-machine interfaces but also presents challenges such as data diversity and AI model robustness. In this review, we first summarize the functions and features of e-skins, followed by feature extraction of sensory data and different AI models. Next, we discuss the utilization of AI in the design of e-skin sensors and address the key topic of AI implementation in data processing and analysis of e-skins to accomplish a range of different tasks. Subsequently, we explore hardware-layer in-skin intelligence before concluding with an analysis of the challenges and opportunities in the various aspects of AI-enabled e-skins.

Asunto(s)

RESUMEN

INTRODUCTION: Remote (digital and/or telephone) access and consultation models are being driven by national policy with the goal being that the National Health Service operate on a remote-first (digital-first) basis by 2029. Previous research has suggested that remote methods of access to care and consulting may act to widen health inequalities for certain patients and/or groups such as those from ethnic minorities. South Asian (SA) patients comprise the largest ethnic minority group in England. Understanding the experiences and needs of this group is critical to ensuring that general practice can deliver equitable, quality health care. METHODS: Qualitative study. 37 participants (from Indian, Pakistani and/or Bangladeshi background) were recruited to take part in either in-person preferred language focus groups or remote semistructured interviews in the English language. Thematic analysis was conducted to identify themes in the qualitative data. FINDINGS: Three major interlinked themes were identified: (1) reduced access, (2) reduced patient choice and (3) quality and safety concerns. The findings highlight access issues split by (i) general issues with appointment access via any remote means and (ii) specific issues related to language barriers creating additional barriers to access and care. Some patients valued the convenience of remote access but also raised concerns regarding appointment availability and reduced patient choice. Face-to-face consultations were preferable but less available. The findings underscore how participants perceived remote care to be of lesser quality and less safe. Concerns were greatest for those with limited English proficiency (LEP), with the removal of non-verbal aspects of communication and 'hands-on' care leading to perceptions of reduced psycho-social safety. CONCLUSION: SA patients' experiences of remote-led primary care access and care delivery were negative with only a minority viewing it positively and for certain limited scenarios. Face-to-face models of care remain the preferred mode of consultation, particularly for those with LEP. Hybrid models of access offer patients the greatest choice, and are likely to meet the varying needs of the South-Asian patient population going forwards. The remote first approach to primary care may be achievable as a service ideal, but its limitations need to be recognised and accounted for to ensure that primary care can be an equitable service, both now and in the future. PUBLIC CONTRIBUTION: Members of the public were involved in all phases of research in the study. This included co-working in partnership throughout the study including, reviewing patient-facing documents, recruiting participants, data facilitation, translation work, interpretation of the data and co-authors on this manuscript. The key to the success of our study was collaborative teamwork, which involved experienced members of the public with SA cultural knowledge working together with and integral to the research team for all components.

Asunto(s)

RESUMEN

Heart failure (HF) affects millions of individuals and causes hundreds of thousands of deaths each year in the United States. Despite the public health burden, medical and device therapies for HF significantly improve clinical outcomes and, in a subset of patients, can cause reversal of abnormalities in cardiac structure and function, termed "myocardial recovery." By identifying novel patterns in high-dimensional data, artificial intelligence (AI) and machine learning (ML) algorithms can enhance the identification of key predictors and molecular drivers of myocardial recovery. Emerging research in the area has begun to demonstrate exciting results that could advance the standard of care. Although major obstacles remain to translate this technology to clinical practice, AI and ML hold the potential to usher in a new era of purposeful myocardial recovery programs based on precision medicine. In this review, we discuss applications of ML to the prediction of myocardial recovery, potential roles of ML in elucidating the mechanistic basis underlying recovery, barriers to the implementation of ML in clinical practice, and areas for future research.

Asunto(s)

RESUMEN

Purpose: We address the need for effective stain domain adaptation methods in histopathology to enhance the performance of downstream computational tasks, particularly classification. Existing methods exhibit varying strengths and weaknesses, prompting the exploration of a different approach. The focus is on improving stain color consistency, expanding the stain domain scope, and minimizing the domain gap between image batches. Approach: We introduce a new domain adaptation method, Stain simultaneous augmentation and normalization (SAN), designed to adjust the distribution of stain colors to align with a target distribution. Stain SAN combines the merits of established methods, such as stain normalization, stain augmentation, and stain mix-up, while mitigating their inherent limitations. Stain SAN adapts stain domains by resampling stain color matrices from a well-structured target distribution. Results: Experimental evaluations of cross-dataset clinical estrogen receptor status classification demonstrate the efficacy of Stain SAN and its superior performance compared with existing stain adaptation methods. In one case, the area under the curve (AUC) increased by 11.4%. Overall, our results clearly show the improvements made over the history of the development of these methods culminating with substantial enhancement provided by Stain SAN. Furthermore, we show that Stain SAN achieves results comparable with the state-of-the-art generative adversarial network-based approach without requiring separate training for stain adaptation or access to the target domain during training. Stain SAN's performance is on par with HistAuGAN, proving its effectiveness and computational efficiency. Conclusions: Stain SAN emerges as a promising solution, addressing the potential shortcomings of contemporary stain adaptation methods. Its effectiveness is underscored by notable improvements in the context of clinical estrogen receptor status classification, where it achieves the best AUC performance. The findings endorse Stain SAN as a robust approach for stain domain adaptation in histopathology images, with implications for advancing computational tasks in the field.