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

Pathology Pathology

Preface: Artificial intelligence (AI), machine learning ML) and digital pathology integration are the next major chapter in our diagnostic pathology and laboratory medicine arena.

In Seminars in diagnostic pathology

This timely captivating topic is organized and presented in this special issue of the journal of Seminar in diagnostic pathology. This special issue will be dedicated to the utilization of machine learning within the digital pathology and laboratory medicine fields. Special thanks to all the authors whose contributions to this review series has not only enhanced our overall understanding of this exciting new field but will also enrich the reader's understanding of this important discipline.

Rashidi Hooman H, Chen Mingyi

2023-Mar-02

AI-ML, Digital pathology

General General

Transparent machine learning suggests a key driver in the decision to start insulin therapy in individuals with type 2 diabetes.

In Journal of diabetes

AIMS : The objective of this study is to establish a predictive model using transparent machine learning (ML) to identify any drivers that characterize therapeutic inertia.

METHODS : Data in the form of both descriptive and dynamic variables collected from electronic records of 1.5 million patients seen at clinics within the Italian Association of Medical Diabetologists between 2005-2019 were analyzed using logic learning machine (LLM), a "clear box" ML technique. Data were subjected to a first stage of modeling to allow ML to automatically select the most relevant factors related to inertia, and then four further modeling steps individuated key variables that discriminated the presence or absence of inertia.

RESULTS : The LLM model revealed a key role for average glycated hemoglobin (HbA1c) threshold values correlated with the presence or absence of insulin therapeutic inertia with an accuracy of 0.79. The model indicated that a patient's dynamic rather than static glycemic profile has a greater effect on therapeutic inertia. Specifically, the difference in HbA1c between two consecutive visits, what we call the HbA1c gap, plays a crucial role. Namely, insulin therapeutic inertia is correlated with an HbA1c gap of <6.6 mmol/mol (0.6%), but not with an HbA1c gap of >11 mmol/mol (1.0%).

CONCLUSIONS : The results reveal, for the first time, the interrelationship between a patient's glycemic trend defined by sequential HbA1c measurements and timely or delayed initiation of insulin therapy. The results further demonstrate that LLM can provide insight in support of evidence-based medicine using real world data.

Musacchio Nicoletta, Zilich Rita, Ponzani Paola, Guaita Giacomo, Giorda Carlo, Heidbreder Rebeca, Santin Pierluigi, Di Cianni Graziano

2023-Mar-08

artificial intelligence, insulin therapy, machine learning, therapeutic inertia, type 2 diabetes

Internal Medicine Internal Medicine

Predicting Malignant Ventricular Arrhythmias Using Real-Time Remote Monitoring.

In Journal of the American College of Cardiology ; h5-index 167.0

BACKGROUND : Although implantable cardioverter-defibrillator (ICD) therapies are associated with increased morbidity and mortality, the prediction of malignant ventricular arrhythmias has remained elusive.

OBJECTIVES : The purpose of this study was to evaluate whether daily remote-monitoring data may predict appropriate ICD therapies for ventricular tachycardia or ventricular fibrillation.

METHODS : This was a post hoc analysis of IMPACT (Randomized trial of atrial arrhythmia monitoring to guide anticoagulation in patients with implanted defibrillator and cardiac resynchronization devices), a multicenter, randomized, controlled trial of 2,718 patients evaluating atrial tachyarrhythmias and anticoagulation for patients with heart failure and ICD or cardiac resynchronization therapy with defibrillator devices. All device therapies were adjudicated as either appropriate (to treat ventricular tachycardia or ventricular fibrillation) or inappropriate (all others). Remote monitoring data in the 30 days before device therapy were utilized to develop separate multivariable logistic regression and neural network models to predict appropriate device therapies.

RESULTS : A total of 59,807 device transmissions were available for 2,413 patients (age 64 ± 11 years, 26% women, 64% ICD). Appropriate device therapies (141 shocks, 10 antitachycardia pacing) were delivered to 151 patients. Logistic regression identified shock lead impedance and ventricular ectopy as significantly associated with increased risk of appropriate device therapy (sensitivity 39%, specificity 91%, AUC: 0.72). Neural network modeling yielded significantly better (P < 0.01 for comparison) predictive performance (sensitivity 54%, specificity 96%, AUC: 0.90), and also identified patterns of change in atrial lead impedance, mean heart rate, and patient activity as predictors of appropriate therapies.

CONCLUSIONS : Daily remote monitoring data may be utilized to predict malignant ventricular arrhythmias in the 30 days before device therapies. Neural networks complement and enhance conventional approaches to risk stratification.

Ginder Curtis, Li Jin, Halperin Jonathan L, Akar Joseph G, Martin David T, Chattopadhyay Ishanu, Upadhyay Gaurav A

2023-Mar-14

artificial intelligence, implantable defibrillator shocks, machine learning, ventricular fibrillation, ventricular tachycardia

General General

Lipid management in ischaemic stroke or transient ischaemic attack in China: result from China National Stroke Registry III.

In BMJ open

OBJECTIVES : The aims of the study were to assess the management of low-density lipoprotein cholesterol (LDL-C) and the goal achievement, as well as to investigate the association between baseline LDL-C level, lipid-lowering treatment (LLT), and stroke recurrence in patients with ischaemic stroke or transient ischaemic attack (TIA).

DESIGN : Our study was a post hoc analysis of the Third China National Stroke Registry (CNSR-III).

SETTING : We derived data from the CNSR-III - a nationwide clinical registry of ischaemic stroke and TIA based on 201 participating hospitals in mainland China.

PARTICIPANTS : 15,166 patients were included in this study with demographic characteristics, etiology, imaging, and biological markers from August 2015 to March 2018.

PRIMARY AND SECONDARY OUTCOME MEASURES : The primary outcome was a new stroke, LDL-C goal (LDL-C<1.8mmol/L and LDL-C<1.4mmol/L, respectively) achievement rates, and LLT compliance within 3, 6, and 12 months. The secondary outcomes included major adverse cardiovascular events (MACE) and all caused death at 3 and 12 months.

RESULTS : Among the 15,166 patients, over 90% of patients received LLT during hospitalization and 2 weeks after discharge; the LLT compliance was 84.5% at 3 months, 75.6% at 6 months, and 64.8% at 12 months. At 12 months, LDL-C goal achievement rate for 1.8mmol/L and 1.4mmol/L was 35.4% and 17.6%, respectively. LLT at discharge was associated with reduced risk of ischemic stroke recurrence (HR=0.69, 95% CI: 0.48-0.99, p=0.04) at 3 months. The rate of LDL-C reduction from baseline to 3-month follow-up was not associated with a reduced risk of stroke recurrence or major adverse cardiovascular events (MACE) at 12 months. Patients with baseline LDL-C ≤1.4mmol/L had a numerically lower risk of stroke, ischemic stroke and MACE at both 3 months and 12 months.

CONCLUSIONS : The LDL-C goal achievement rate has increased mildly in the stroke and TIA population in mainland China. Lowered baseline LDL-C level was significantly associated with a decreased short- and long-term risk of ischemic stroke among stroke and TIA patients. LDL-C<1.4mmol/L might be a safe standard for this population.

Xu Yu-Yuan, Chen Wei-Qi, Wang Meng-Xing, Pan Yue-Song, Li Zi-Xiao, Liu Li-Ping, Zhao Xing-Quan, Wang Yi-Long, Li Hao, Wang Yong-Jun, Meng Xia

2023-Mar-08

Lipid disorders, Neurology, Stroke, Stroke medicine

General General

Diagnosis of Alzheimer's Disease and Tauopathies on Whole Slide Histopathology Images Using a Weakly Supervised Deep Learning Algorithm.

In Laboratory investigation; a journal of technical methods and pathology ; h5-index 42.0

Neuropathological assessment at autopsy is the gold standard for diagnosing neurodegenerative disorders. Neurodegenerative conditions, such as Alzheimer's disease (AD), neuropathological changes are a continuous process from normal aging rather than categorical; therefore, diagnosing neurodegenerative disorders is a complicated task. We aimed to develop a pipeline for diagnosing AD and other tauopathies, including corticobasal degeneration (CBD), globular glial tauopathy (GGT), Pick's disease (PiD), and progressive supranuclear palsy (PSP). We used a weakly supervised deep learning-based approach called clustering-constrained-attention multiple instance learning (CLAM) on whole slide images (WSIs) of patients with AD (n=30), CBD (n=20), GGT (n=10), PiD (n=20), and PSP (n=20), as well as non-tauopathy controls (n=21). Three sections (A: motor cortex; B: cingulate gyrus and superior frontal gyrus; C: corpus striatum) that had been immunostained for phosphorylated-tau were scanned and converted to WSIs. We evaluated three models (classical multiple instance learning, single-attention-branch CLAM, and multi-attention-branch CLAM) using 5-fold cross-validation. Attention-based interpretation analysis was performed to identify morphological features contributing to the classification. Within highly attended regions, we also augmented gradient-weighted class activation mapping (Grad-CAM) to the model to visualize cellular-level evidence of the model's decisions. The multi-attention-branch CLAM model using Section B achieved the highest area under the curve (0.970 ± 0.037) and diagnostic accuracy (0.873 ± 0.087). A heatmap showed the highest attention in the gray matter of the superior frontal gyrus in AD and the white matter of the cingulate gyrus in CBD. Grad-CAM showed the highest attention in characteristic tau lesions for each disease (e.g., numerous tau-positive threads in the white matter inclusions for CBD). Our findings supported the feasibility of deep learning-based approaches for the classification of neurodegenerative disorders on WSIs. Further investigation of this method focusing on clinicopathological correlations, is warranted.

Kim Minji, Sekiya Hiroaki, Yao Gary, Martin Nicholas B, Castanedes-Casey Monica, Dickson Dennis W, Hwang Tae Hyun, Koga Shunsuke

2023-Mar-06

Alzheimer’s disease, CLAM, Grad-CAM, Pick’s disease, corticobasal degeneration, globular glial tauopathy, neuropathology, progressive supranuclear palsy, tauopathy, weakly supervised deep learning

Cardiology Cardiology

The sustainable antihypertensive and target organ damage protective effect of transcranial focused ultrasound stimulation in spontaneously hypertensive rats.

In Journal of hypertension ; h5-index 56.0

OBJECTIVE : In this study, we aimed to investigate the sustainable antihypertensive effects and protection against target organ damage caused by low-intensity focused ultrasound (LIFU) stimulation and the underlying mechanism in spontaneously hypertensive rats (SHRs) model.

METHODS AND RESULTS : SHRs were treated with ultrasound stimulation of the ventrolateral periaqueductal gray (VlPAG) for 20 min every day for 2 months. Systolic blood pressure (SBP) was compared among normotensive Wistar-Kyoto rats, SHR control group, SHR Sham group, and SHR LIFU stimulation group. Cardiac ultrasound imaging and hematoxylin-eosin and Masson staining of the heart and kidney were performed to assess target organ damage. The c-fos immunofluorescence analysis and plasma levels of angiotensin II, aldosterone, hydrocortisone, and endothelin-1 were measured to investigate the neurohumoral and organ systems involved. We found that SBP was reduced from 172 ± 4.2 mmHg to 141 ± 2.1 mmHg after 1 month of LIFU stimulation, P < 0.01. The next month of treatment can maintain the rat's blood pressure at 146 ± 4.2 mmHg at the end of the experiment. LIFU stimulation reverses left ventricular hypertrophy and improves heart and kidney function. Furthermore, LIFU stimulation enhanced the neural activity from the VLPAG to the caudal ventrolateral medulla and reduced the plasma levels of ANGII and Aldo.

CONCLUSION : We concluded that LIFU stimulation has a sustainable antihypertensive effect and protects against target organ damage by activating antihypertensive neural pathways from VLPAG to the caudal ventrolateral medulla and further inhibiting the renin-angiotensin system (RAS) activity, thereby supporting a novel and noninvasive alternative therapy to treat hypertension.

Li Dapeng, Zhang Siyuan, Cao Fangyuan, Han Jie, Wang Mengke, Lai Chunhao, Zhang Jingjing, Xu Tianqi, Bouakaz Ayache, Wan Mingxi, Ren Pengyu

2023-Mar-03