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

General General

Connectome-based predictive modeling for functional recovery of acute ischemic stroke.

In NeuroImage. Clinical

Patients of acute ischemic stroke possess considerable chance of recovery of various levels in the first several weeks after stroke onset. Prognosis of functional recovery is important for decision-making in poststroke patient care and placement. Poststroke functional recovery has conventionally been based on demographic and clinical variables such as age, gender, and severity of stroke impairment. On the other hand, the concept of connectome has become a basis of interpreting the functional impairment and recovery of stroke patients. In this research, the connectome-based predictive modeling was used to provide predictive models for prognosing poststroke functional recovery. Predictive models were developed to use the brain connectivity at stroke onset to predict functional assessment scores at one or three months later, or to use the brain connectivity one-month poststroke to predict functional assessment scores at three months after stroke onset. The brain connectivity was computed from the resting-state fMRI signals. The functional assessment scores used in this research included modified Rankin Scale (mRS) and Barthel Index (BI). This research found significant models that used the brain connectivity at onset to predict the mRS one-month poststroke and to predict the BI three-month poststroke for patients with supratentorial infarction, as well as predictive models that used the brain connectivity one-month poststroke to predict the mRS three-month poststroke for patients with supratentorial infarction in the right hemisphere. The connectome-based predictive modeling could provide clinical value in prognosis of acute ischemic stroke.

Peng Syu-Jyun, Chen Yu-Wei, Hung Andrew, Wang Kuo-Wei, Tsai Jang-Zern

2023-Mar-08

BI, Connectome, Functional recovery, Prediction, Resting-state functional MRI, Stroke, mRS

General General

Novel flexible sensing technology for nondestructive detection on live fish health/quality during waterless and low-temperature transportation.

In Biosensors & bioelectronics

Fish health/quality issues are increasingly attracting attention during waterless and low-temperature transportation. Nondestructive detection has become a great need for an effective method to improve fish health/quality. Currently, emerging Internet of Things, novel flexible electronics and data fusion technology have received great interest for nondestructive detection on live fish health/quality. This paper analysized nondestructive detection mechanisms using novel flexible sensing technology to achieve high-precision sensing of key parameters, and machine learning based data fusion modeling to achieve live fish health/quality nondestructive evaluation during waterless and low-temperature transportation. Recent studies on novel flexible electrochemical and physiological biosensors development and application for solving key ambient and physiological parameter sensing were summarized. The ML based data fusion modeling framework and application for live fish health/quality nondestructive evaluation was also highlighted. The future perspective is also proposed to provide promising solutions for accurate sensing of multi-parameter and real applications of live fish health/quality nondestructive detection during waterless and low-temperature transportation.

Feng Huanhuan, Fu Yifan, Huang Shihao, Glamuzina Branko, Zhang Xiaoshuan

2023-Mar-08

Biosensors, Flexible sensing, Internet of things, Machine learning (ML) fusion, Nondestructive detection

General General

The HARM models: Predicting longitudinal physical aggression in patients with schizophrenia at an individual level.

In Journal of psychiatric research ; h5-index 59.0

The prediction and prevention of aggression in individuals with schizophrenia remains a top priority within forensic psychiatric settings. While risk assessment methods are well rooted in forensic psychiatry, there are no available tools to predict longitudinal physical aggression in patients with schizophrenia within forensic settings at an individual level. In the present study, we used evidence-based risk and protective factors, as well as variables related to course of treatment assessed at baseline, to predict prospective incidents of physical aggression (4-month, 12-month, and 18-month follow-up) among 151 patients with schizophrenia within the forensic mental healthcare system. Across our HARM models, the balanced accuracy (sensitivity + specificity/2) of predicting physical aggressive incidents in patients with schizophrenia ranged from 59.73 to 87.33% at 4-month follow-up, 68.31-80.10% at 12-month follow-up, and 46.22-81.63% at 18-month follow-up, respectively. Additionally, we developed separate models, using clinician rated clinical judgement of short term and immediate violent risk, as a measure of comparison. Several modifiable evidence-based predictors of prospective physical aggression in schizophrenia were identified, including impulse control, substance abuse, impulsivity, treatment non-adherence, mood and psychotic symptoms, substance abuse, and poor family support. To the best of our knowledge, our HARM models are the first to predict longitudinal physical aggression at an individual level in patients with schizophrenia in forensic settings. However, it is important to caution that since these machine learning models were developed in the context of forensic settings, they may not be generalisable to individuals with schizophrenia more broadly. Moreover, a low base rate of physical aggression was observed in the testing set (6.0-11.6% across timepoints). As such, larger cohorts will be required to determine the replicability of these findings.

Watts Devon, Mamak Mini, Moulden Heather, Upfold Casey, de Azevedo Cardoso Taiane, Kapczinski Flavio, Chaimowitz Gary

2023-Mar-01

Artificial intelligence, Computational neuroscience, Criminality, Machine learning, Precision psychiatry, Psychotic disorders, Schizophrenia

General General

Exploring the Knowledge Attained by Machine Learning on Ion Transport across Polyamide Membranes Using Explainable Artificial Intelligence.

In Environmental science & technology ; h5-index 132.0

Recent studies have increasingly applied machine learning (ML) to aid in performance and material design associated with membrane separation. However, whether the knowledge attained by ML with a limited number of available data is enough to capture and validate the fundamental principles of membrane science remains elusive. Herein, we applied explainable artificial intelligence (XAI) to thoroughly investigate the knowledge learned by ML on the mechanisms of ion transport across polyamide reverse osmosis (RO) and nanofiltration (NF) membranes by leveraging 1,585 data from 26 membrane types. The Shapley additive explanation method based on cooperative game theory was used to unveil the influences of various ion and membrane properties on the model predictions. XAI shows that the ML can capture the important roles of size exclusion and electrostatic interaction in regulating membrane separation properly. XAI also identifies that the mechanisms governing ion transport possess different relative importance to cation and anion rejections during RO and NF filtration. Overall, we provide a framework to evaluate the knowledge underlying the ML model prediction and demonstrate that ML is able to learn fundamental mechanisms of ion transport across polyamide membranes, highlighting the importance of elucidating model interpretability for more reliable and explainable ML applications to membrane selection and design.

Jeong Nohyeong, Epsztein Razi, Wang Ruoyu, Park Shinyun, Lin Shihong, Tong Tiezheng

2023-Mar-14

explainable artificial intelligence, ion transport, machine learning, membrane separation mechanisms, nanofiltration, reverse osmosis

General General

Taking advantage of quasi-periodic signals for S2S operational forecast from a perspective of deep learning.

In Scientific reports ; h5-index 158.0

The quasi-periodic signals in the earth system could be the predictability source for sub-seasonal to seasonal (S2S) climate prediction because of the connections among the lead-lag time of those signals. The Madden-Julian Oscillation (MJO) is a typical quasi-periodic signal, which is the dominant S2S variability in the tropics. Besides, significantly periodic features in terms of both intensity and location are identified in 10-40 days for the concurrent variation of the subtropical and polar jet streams over Asia in this study. So far, those signals contribute less and are not fully applied to the S2S prediction. The deep learning (DL) approach, especially the long-short term memory (LSTM) networks, has the ability to take advantage of the information at the previous time to improve the prediction after then. This study presents the application of the DL in the postprocessing of S2S prediction using quasi-periodic signals predicted by the operational model to improve the prediction of minimum 2-m air temperature over Asia. With the help of deep learning, it finds the best weights for the ensemble predictions, and the quasi-periodic signals in the atmosphere can further benefit the S2S operational prediction.

Zhou Yang, Zhao Qifan

2023-Mar-13

Pathology Pathology

Task-specific Fine-tuning via Variational Information Bottleneck for Weakly-supervised Pathology Whole Slide Image Classification

ArXiv Preprint

While Multiple Instance Learning (MIL) has shown promising results in digital Pathology Whole Slide Image (WSI) classification, such a paradigm still faces performance and generalization problems due to challenges in high computational costs on Gigapixel WSIs and limited sample size for model training. To deal with the computation problem, most MIL methods utilize a frozen pretrained model from ImageNet to obtain representations first. This process may lose essential information owing to the large domain gap and hinder the generalization of model due to the lack of image-level training-time augmentations. Though Self-supervised Learning (SSL) proposes viable representation learning schemes, the improvement of the downstream task still needs to be further explored in the conversion from the task-agnostic features of SSL to the task-specifics under the partial label supervised learning. To alleviate the dilemma of computation cost and performance, we propose an efficient WSI fine-tuning framework motivated by the Information Bottleneck theory. The theory enables the framework to find the minimal sufficient statistics of WSI, thus supporting us to fine-tune the backbone into a task-specific representation only depending on WSI-level weak labels. The WSI-MIL problem is further analyzed to theoretically deduce our fine-tuning method. Our framework is evaluated on five pathology WSI datasets on various WSI heads. The experimental results of our fine-tuned representations show significant improvements in both accuracy and generalization compared with previous works. Source code will be available at https://github.com/invoker-LL/WSI-finetuning.

Honglin Li, Chenglu Zhu, Yunlong Zhang, Yuxuan Sun, Zhongyi Shui, Wenwei Kuang, Sunyi Zheng, Lin Yang

2023-03-15