Receive a weekly summary and discussion of the top papers of the week by leading researchers in the field.

General General

The Scope of In-Context Learning for the Extraction of Medical Temporal Constraints

ArXiv Preprint

Medications often impose temporal constraints on everyday patient activity. Violations of such medical temporal constraints (MTCs) lead to a lack of treatment adherence, in addition to poor health outcomes and increased healthcare expenses. These MTCs are found in drug usage guidelines (DUGs) in both patient education materials and clinical texts. Computationally representing MTCs in DUGs will advance patient-centric healthcare applications by helping to define safe patient activity patterns. We define a novel taxonomy of MTCs found in DUGs and develop a novel context-free grammar (CFG) based model to computationally represent MTCs from unstructured DUGs. Additionally, we release three new datasets with a combined total of N = 836 DUGs labeled with normalized MTCs. We develop an in-context learning (ICL) solution for automatically extracting and normalizing MTCs found in DUGs, achieving an average F1 score of 0.62 across all datasets. Finally, we rigorously investigate ICL model performance against a baseline model, across datasets and MTC types, and through in-depth error analysis.

Parker Seegmiller, Joseph Gatto, Madhusudan Basak, Diane Cook, Hassan Ghasemzadeh, John Stankovic, Sarah Preum

2023-03-16

Radiology Radiology

MRI-based synthetic CT in the Detection of knee Osteoarthritis: Comparison with CT.

In Journal of orthopaedic research : official publication of the Orthopaedic Research Society

MRI is the gold standard for assessment of soft tissues, however, X-ray based techniques are required for evaluating bone-related pathologies. This study evaluated the performance of synthetic computed tomography (sCT), a novel MRI-based bone visualization technique, compared with CT, for the scoring of knee osteoarthritis. sCT images were generated from the 3T T1-weighted gradient echo MR images using a trained machine learning algorithm. Two readers scored the severity of osteoarthritis in tibiofemoral and patellofemoral joints according to OACT, which enables the evaluation of osteoarthritis, from its characteristics of joint space narrowing, osteophytes, cysts and sclerosis in CT (and sCT) images. Cohen's Kappa was used to assess the inter-reader agreement for each modality, and intermodality agreement of CT- and sCT-based scores for each reader. We also compared the confidence level of readers for grading CT and sCT images using confidence scores collected during grading. Inter-reader agreement for tibiofemoral and patellofemoral joints were almost-perfect for both modalities (κ = 0.83 to κ = 0.88). The inter-modality agreement of osteoarthritis scores between CT and sCT was substantial to almost-perfect for tibiofemoral (κ = 0.63 and κ = 0.84 for the two readers) and patellofemoral joints (κ = 0.78 and κ = 0.81 for the two readers). The analysis of diagnosis confidence scores showed comparable visual quality of the two modalities, where both are showing acceptable confidence levels for scoring OA. In conclusion, in this single-center study, sCT and CT were comparable for the scoring of knee OA. This article is protected by copyright. All rights reserved.

Arbabi Saeed, Foppen Wouter, Gielis Willem Paul, van Stralen Marijn, Jansen Mylène, Arbabi Vahid, de Jong Pim A, Weinans Harrie, Seevinck Peter

2023-Mar-15

CT, MRI, Neural Networks, Osteoarthritis, synthetic CT

General General

Mental wellness: The Jasper and Alice way.

In Journal of medical imaging and radiation sciences

Gerhardus George Visser Koch, also known as Erhard, is a qualified, independent practice, diagnostic radiographer from South Africa. Erhard's work experience ranges from having occupied various positions in both the public and private healthcare sectors. He has a passion for academia and research, currently occupying the role of a lecturer in diagnostic radiography. Erhard has a keen interest in radiation protection, health professions education, professional role extension and artificial intelligence. He loves animals, enjoys spending time in nature, likes to paint and travel. This free form poem is about my two cats, Jasper and Alice, and the significant role they play in my everyday life, more specifically so, my mental wellness. I simply cannot imagine my life without the two of them. Many have asked me where their names come from, and the answer is always: "No, it does not stem from the Twilight movies". Jasper and Alice were both rescued as kittens. They were abandoned and left to die. Shortly after, I adopted them from an animal rescue agency who shared their stories on social media. Jasper and Alice have always been by my side; through both personal and professional, downfalls and victories. Up to now, and from my 12 years of experience in the field, I have relocated several times. I have moved from one city to the next, all for the love of what I do and for the opportunities that came my way. I am happy to report that I have found my way back to academia, and this is where I'd like to stay.

George Visser Koch Gerhardus

2023-Mar-13

Radiology Radiology

Addressing the Challenges of Implementing Artificial Intelligence Tools in Clinical Practice: Principles From Experience.

In Journal of the American College of Radiology : JACR

The multitude of artificial intelligence (AI)-based solutions, vendors, and platforms poses a challenging proposition to an already complex clinical radiology practice. Apart from assessing and ensuring acceptable local performance and workflow fit to improve imaging services, AI tools require multiple stakeholders, including clinical, technical, and financial, who collaborate to move potential deployable applications to full clinical deployment in a structured and efficient manner. Postdeployment monitoring and surveillance of such tools require an infrastructure that ensures proper and safe use. Herein, the authors describe their experience and framework for implementing and supporting the use of AI applications in radiology workflow.

Bizzo Bernardo C, Dasegowda Giridhar, Bridge Christopher, Miller Benjamin, Hillis James M, Kalra Mannudeep K, Durniak Kimberly, Stout Markus, Schultz Thomas, Alkasab Tarik, Dreyer Keith J

2023-Mar

Artificial intelligence, deployment, implementation, machine learning, radiology

General General

The forces generated by agonist muscles during isometric contractions arise from motor unit synergies.

In The Journal of neuroscience : the official journal of the Society for Neuroscience

The purpose of our study was to identify the low-dimensional latent components, defined hereafter as motor unit modes, underlying the discharge rates of the motor units in two knee extensors (vastus medialis and lateralis, eight men) and two hand muscles (first dorsal interossei and thenars, seven men and one woman) during submaximal isometric contractions. Factor analysis identified two independent motor unit modes that captured most of the covariance of the motor unit discharge rates. We found divergent distributions of the motor unit modes for the hand and vastii muscles. On average, 75% of the motor units for the thenar muscles and first dorsal interosseus were strongly correlated with the module for the muscle in which they resided. In contrast, we found a continuous distribution of motor unit modes spanning the two vastii muscle modules. The proportion of the muscle-specific motor unit modes was 60% for vastus medialis and 45% for vastus lateralis. The other motor units were either correlated with both muscle modules (shared inputs) or belonged to the module for the other muscle (15% for vastus lateralis). Moreover, coherence of the discharge rates between motor unit pools was explained by the presence of shared synaptic inputs. In simulations with 480 integrate-and-fire neurons, we demonstrate that factor analysis identifies the motor unit modes with high levels of accuracy. Our results indicate that correlated discharge rates of motor units that comprise motor unit modes arise from at least two independent sources of common input among the motor neurons innervating synergistic muscles.Significance statement:It has been suggested that the nervous system controls synergistic muscles by projecting common synaptic inputs to the engaged motor neurons. In our study, we reduced the dimensionality of the output produced by pools of synergistic motor neurons innervating the hand and thigh muscles during isometric contractions. We found two neural modules, each representing a different common input, that were each specific for one of the muscles. In the vastii muscles, we found a continuous distribution of motor unit modes spanning the two synergistic muscles. Some of the motor units from the homonymous vastii muscle were controlled by the dominant neural module of the other synergistic muscle. In contrast, we found two distinct neural modules for the hand muscles.

Del Vecchio Alessandro, Marconi Germer Carina, Kinfe Thomas Mehari, Nuccio Stefano, Hug François, Eskofier Bjoern, Farina Dario, Enoka Roger Maro

2023-Mar-15

Cardiology Cardiology

Outcomes of ST elevation myocardial infarction in patients with cancer; a nationwide study.

In European heart journal. Quality of care & clinical outcomes

AIMS : To assess processes of care and clinical outcomes in cancer patients with ST elevation myocardial infarction (STEMI) according to cancer type.

METHODS : This is a national population-based study of patients admitted with STEMI in England and Wales between January 2005 and March 2019. Data was obtained from the National Heart attack MINAP registry and HES registry.

RESULTS : We identified 353 448 STEMI indexed admissions between 2005 and 2019. Of those, 8581(2.4%) had active cancer. Prostate cancer (29% of STEMI patients with cancer) was the most common cancer followed by hematologic malignancies (14%) and lung cancer (13%). Cancer patients were less likely to receive invasive coronary revascularization (60.0%, vs. 71.6% p < 0.001) and had higher in-hospital death (OR 1.39, 95% CI 1.25-1.54) and bleeding (OR 1.23, 95% CI 1.03-1.46). Cancer patients had higher mortality at 30 days (HR 2.39, 95% CI 2.19-2.62) and 1 year (HR 3.73, 95% CI 3.58-3.89). lung cancer was the cancer associated with highest risk of death in hospital (OR 1.75, 95% CI 1.39-2.22) and at one year (OR 8.08, 95% CI 7.44-8.78). Colon cancer (OR 1.98, 95% CI 1.24-3.14) was the main cancer associated with major bleeding. All common cancer types were associated with higher mortality at 1 year. Cardiovascular death (62%) was the main cause of death in the first 30 days while cancer (52%) was the main cause of death within one year.

CONCLUSION : STEMI patients with cancer have higher risk of short- and long-term mortality, particularly lung cancer. Colon cancer is the main cancer associated with major bleeding. Cardiovascular disease was the main cause of death in the first month whereas cancer was the main cause of death within one year.

Dafaalla Mohamed, Abdel-Qadir Husam, Gale Chris P, Sun Louise, López-Fernández Teresa, Miller Robert J H, Wojakowski Wojtek, Nolan James, Rashid Muhammad, Mamas Mamas A

2023-Mar-15