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

Surgery Surgery

Pathologist Validation of a Machine Learning-Derived Feature for Colon Cancer Risk Stratification.

In JAMA network open

IMPORTANCE : Identifying new prognostic features in colon cancer has the potential to refine histopathologic review and inform patient care. Although prognostic artificial intelligence systems have recently demonstrated significant risk stratification for several cancer types, studies have not yet shown that the machine learning-derived features associated with these prognostic artificial intelligence systems are both interpretable and usable by pathologists.

OBJECTIVE : To evaluate whether pathologist scoring of a histopathologic feature previously identified by machine learning is associated with survival among patients with colon cancer.

DESIGN, SETTING, AND PARTICIPANTS : This prognostic study used deidentified, archived colorectal cancer cases from January 2013 to December 2015 from the University of Milano-Bicocca. All available histologic slides from 258 consecutive colon adenocarcinoma cases were reviewed from December 2021 to February 2022 by 2 pathologists, who conducted semiquantitative scoring for tumor adipose feature (TAF), which was previously identified via a prognostic deep learning model developed with an independent colorectal cancer cohort.

MAIN OUTCOMES AND MEASURES : Prognostic value of TAF for overall survival and disease-specific survival as measured by univariable and multivariable regression analyses. Interpathologist agreement in TAF scoring was also evaluated.

RESULTS : A total of 258 colon adenocarcinoma histopathologic cases from 258 patients (138 men [53%]; median age, 67 years [IQR, 65-81 years]) with stage II (n = 119) or stage III (n = 139) cancer were included. Tumor adipose feature was identified in 120 cases (widespread in 63 cases, multifocal in 31, and unifocal in 26). For overall survival analysis after adjustment for tumor stage, TAF was independently prognostic in 2 ways: TAF as a binary feature (presence vs absence: hazard ratio [HR] for presence of TAF, 1.55 [95% CI, 1.07-2.25]; P = .02) and TAF as a semiquantitative categorical feature (HR for widespread TAF, 1.87 [95% CI, 1.23-2.85]; P = .004). Interpathologist agreement for widespread TAF vs lower categories (absent, unifocal, or multifocal) was 90%, corresponding to a κ metric at this threshold of 0.69 (95% CI, 0.58-0.80).

CONCLUSIONS AND RELEVANCE : In this prognostic study, pathologists were able to learn and reproducibly score for TAF, providing significant risk stratification on this independent data set. Although additional work is warranted to understand the biological significance of this feature and to establish broadly reproducible TAF scoring, this work represents the first validation to date of human expert learning from machine learning in pathology. Specifically, this validation demonstrates that a computationally identified histologic feature can represent a human-identifiable, prognostic feature with the potential for integration into pathology practice.

L’Imperio Vincenzo, Wulczyn Ellery, Plass Markus, Müller Heimo, Tamini Nicolò, Gianotti Luca, Zucchini Nicola, Reihs Robert, Corrado Greg S, Webster Dale R, Peng Lily H, Chen Po-Hsuan Cameron, Lavitrano Marialuisa, Liu Yun, Steiner David F, Zatloukal Kurt, Pagni Fabio

2023-Mar-01

Ophthalmology Ophthalmology

Electrical Stimulation Induced Current Distribution in Peripheral Nerves Varies Significantly with the Extent of Nerve Damage: A Computational Study Utilizing Convolutional Neural Network and Realistic Nerve Models.

In International journal of neural systems

Electrical stimulation of the peripheral nervous system is a promising therapeutic option for several conditions; however, its effects on tissue and the safety of the stimulation remain poorly understood. In order to devise stimulation protocols that enhance therapeutic efficacy without the risk of causing tissue damage, we constructed computational models of peripheral nerve and stimulation cuffs based on extremely high-resolution cross-sectional images of the nerves using the most recent advances in computing power and machine learning techniques. We developed nerve models using nonstimulated (healthy) and over-stimulated (damaged) rat sciatic nerves to explore how nerve damage affects the induced current density distribution. Using our in-house computational, quasi-static, platform, and the Admittance Method (AM), we estimated the induced current distribution within the nerves and compared it for healthy and damaged nerves. We also estimated the extent of localized cell damage in both healthy and damaged nerve samples. When the nerve is damaged, as demonstrated principally by the decreased nerve fiber packing, the current penetrates deeper into the over-stimulated nerve than in the healthy sample. As safety limits for electrical stimulation of peripheral nerves still refer to the Shannon criterion to distinguish between safe and unsafe stimulation, the capability this work demonstrated is an important step toward the development of safety criteria that are specific to peripheral nerve and make use of the latest advances in computational bioelectromagnetics and machine learning, such as Python-based AM and CNN-based nerve image segmentation.

Du Jinze, Morales Andres, Kosta Pragya, Bouteiller Jean-Marie C, Martinez-Navarrete Gema, Warren David J, Fernandez Eduardo, Lazzi Gianluca

2023-Mar-15

Computational model, electrical stimulation, peripheral nerve, tissue safety

General General

Blind Users Accessing Their Training Images in Teachable Object Recognizers.

In ASSETS. Annual ACM Conference on Assistive Technologies

Teachable object recognizers provide a solution for a very practical need for blind people - instance level object recognition. They assume one can visually inspect the photos they provide for training, a critical and inaccessible step for those who are blind. In this work, we engineer data descriptors that address this challenge. They indicate in real time whether the object in the photo is cropped or too small, a hand is included, the photos is blurred, and how much photos vary from each other. Our descriptors are built into open source testbed iOS app, called MYCam. In a remote user study in (N = 12) blind participants' homes, we show how descriptors, even when error-prone, support experimentation and have a positive impact in the quality of training set that can translate to model performance though this gain is not uniform. Participants found the app simple to use indicating that they could effectively train it and that the descriptors were useful. However, many found the training being tedious, opening discussions around the need for balance between information, time, and cognitive load.

Hong Jonggi, Gandhi Jaina, Mensah Ernest Essuah, Zeraati Farnaz Zamiri, Jarjue Ebrima Haddy, Lee Kyungjun, Kacorri Hernisa

2022-Oct

blind, machine teaching, object recognition, participatory machine learning, visual impairment

General General

Niche-Based Microbial Community Assemblage in Urban Transit Systems and the Influence of City Characteristics.

In Microbiology spectrum

Microbiota residing on the urban transit systems (UTSs) can be shared by travelers and have niche-specific assemblage. However, it remains unclear how the assemblages are influenced by city characteristics, rendering city-specific and microbial-aware urban planning challenging. Here, we analyzed 3,359 UTS microbial samples collected from 16 cities around the world. We found the stochastic process dominated in all UTS microbiota assemblages, with the explanation rate (R2) of the neutral community model (NCM) higher than 0.7. Moreover, city characteristics predominantly drove such assemblage, largely responsible for the variation in the stochasticity ratio (50.1%). Furthermore, by utilizing an artificial intelligence model, we quantified the ability of UTS microbes in discriminating between cities and found that the ability was also strongly affected by city characteristics, especially climate and continent. From these, we found that although the NCM R2 of the New York City UTS microbiota was 0.831, the accuracy of the microbial-based city characteristic classifier was higher than 0.9. This is the first study to demonstrate the effects of city characteristics on the UTS microbiota assemblage, paving the way for city-specific and microbial-aware applications. IMPORTANCE We analyzed the urban transit system microbiota assemblage across 16 cities. The stochastic process was dominant in the urban transit system microbiota assemblage. The urban transit system microbe's ability in discriminating between cities was quantified using transfer learning based on random forest (RF) methods. Certain urban transit system microbes were strongly affected by city characteristics.

Xiong Guangzhou, Ji Lei, Cheng Mingyue, Ning Kang

2023-Mar-14

artificial intelligence, city characteristics, microbiota assemblage, urban transit system

General General

The Rise of ChatGPT: Exploring its Potential in Medical Education.

In Anatomical sciences education

The integration of artificial intelligence (AI) into medical education has the potential to revolutionize the way students learn about biomedical sciences. Large language models, such as ChatGPT, can serve as virtual teaching assistants, providing students with detailed and relevant information and perhaps eventually interactive simulations. ChatGPT has the potential to increase student engagement and enhance student learning, though research is needed to confirm this. The challenges and limitations of ChatGPT must also be considered, including ethical issues and potentially harmful effects. It is crucial for medical educators to keep pace with technology's rapidly changing landscape and consider the implications for curriculum design, assessment strategies, and teaching methods. Continued research and evaluation are necessary to ensure the optimal integration of AI-based learning tools into medical education.

Lee Hyunsu

2023-Mar-14

Artificial Intelligence, ChatGPT, Medical education, Natural language processing, Virtual teaching assistant

Internal Medicine Internal Medicine

Predicting metastasis in gastric cancer patients: machine learning-based approaches.

In Scientific reports ; h5-index 158.0

Gastric cancer (GC), with a 5-year survival rate of less than 40%, is known as the fourth principal reason of cancer-related mortality over the world. This study aims to develop predictive models using different machine learning (ML) classifiers based on both demographic and clinical variables to predict metastasis status of patients with GC. The data applied in this study including 733 of GC patients, divided into a train and test groups at a ratio of 8:2, diagnosed at Taleghani tertiary hospital. In order to predict metastasis in GC, ML-based algorithms, including Naive Bayes (NB), Random Forest (RF), Support Vector Machine (SVM), Neural Network (NN), Decision Tree (RT) and Logistic Regression (LR), with 5-fold cross validation were performed. To assess the model performance, F1 score, precision, sensitivity, specificity, area under the curve (AUC) of receiver operating characteristic (ROC) curve and precision-recall AUC (PR-AUC) were obtained. 262 (36%) experienced metastasis among 733 patients with GC. Although all models have optimal performance, the indices of SVM model seems to be more appropiate (training set: AUC: 0.94, Sensitivity: 0.94; testing set: AUC: 0.85, Sensitivity: 0.92). Then, NN has the higher AUC among ML approaches (training set: AUC: 0.98; testing set: AUC: 0.86). The RF of ML-based models, which determine size of tumor and age as two essential variables, is considered as the third efficient model, because of higher specificity and AUC (84% and 87%). Based on the demographic and clinical characteristics, ML approaches can predict the metastasis status in GC patients. According to AUC, sensitivity and specificity in both SVM and NN can be regarded as better algorithms among 6 applied ML-based methods.

Talebi Atefeh, Celis-Morales Carlos A, Borumandnia Nasrin, Abbasi Somayeh, Pourhoseingholi Mohamad Amin, Akbari Abolfazl, Yousefi Javad

2023-Mar-13