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

General General

Artificial Intelligence Screening of Medical School Applications: Development and Validation of a Machine-Learning Algorithm.

In Academic medicine : journal of the Association of American Medical Colleges

PURPOSE : To explore whether a machine-learning algorithm could accurately perform the initial screening of medical school applications.

METHOD : Using application data and faculty screening outcomes from the 2013 to 2017 application cycles (n = 14,555 applications), the authors created a virtual faculty screener algorithm. A retrospective validation using 2,910 applications from the 2013 to 2017 cycles and a prospective validation using 2,715 applications during the 2018 application cycle were performed. To test the validated algorithm, a randomized trial was performed in the 2019 cycle, with 1,827 eligible applications being reviewed by faculty and 1,873 by algorithm.

RESULTS : The retrospective validation yielded area under the receiver operating characteristic (AUROC) values of 0.83, 0.64, and 0.83 and area under the precision-recall curve (AUPRC) values of 0.61, 0.54, and 0.65 for the invite for interview, hold for review, and reject groups, respectively. The prospective validation yielded AUROC values of 0.83, 0.62, and 0.82 and AUPRC values of 0.66, 0.47, and 0.65 for the invite for interview, hold for review, and reject groups, respectively. The randomized trial found no significant differences in overall interview recommendation rates according to faculty or algorithm and among female or underrepresented in medicine applicants. In underrepresented in medicine applicants, there were no significant differences in the rates at which the admissions committee offered an interview (70 of 71 in the faculty reviewer arm and 61 of 65 in the algorithm arm; P = .14). No difference in the rate of the committee agreeing with the recommended interview was found among female applicants (224 of 229 in the faculty reviewer arm and 220 of 227 in the algorithm arm; P = .55).

CONCLUSIONS : The virtual faculty screener algorithm successfully replicated faculty screening of medical school applications and may aid in the consistent and reliable review of medical school applicants.

Triola Marc M, Reinstein Ilan, Marin Marina, Gillespie Colleen, Abramson Steven, Grossman Robert I, Rivera Rafael

2023-Mar-06

General General

Prediction of septic and hypovolemic shock in intensive care unit patients using machine learning.

In Revista Brasileira de terapia intensiva

OBJECTIVE : To create and validate a model for predicting septic or hypovolemic shock from easily obtainable variables collected from patients at admission to an intensive care unit.

METHODS : A predictive modeling study with concurrent cohort data was conducted in a hospital in the interior of northeastern Brazil. Patients aged 18 years or older who were not using vasoactive drugs on the day of admission and were hospitalized from November 2020 to July 2021 were included. The Decision Tree, Random Forest, AdaBoost, Gradient Boosting and XGBoost classification algorithms were tested for use in building the model. The validation method used was k-fold cross validation. The evaluation metrics used were recall, precision and area under the Receiver Operating Characteristic curve.

RESULTS : A total of 720 patients were used to create and validate the model. The models showed high predictive capacity with areas under the Receiver Operating Characteristic curve of 0.979; 0.999; 0.980; 0.998 and 1.00 for the Decision Tree, Random Forest, AdaBoost, Gradient Boosting and XGBoost algorithms, respectively.

CONCLUSION : The predictive model created and validated showed a high ability to predict septic and hypovolemic shock from the time of admission of patients to the intensive care unit.

Pessoa Stela Mares Brasileiro, Oliveira Bianca Silva de Sousa, Santos Wendy Gomes Dos, Oliveira Augusto Novais Macedo, Camargo Marianne Silveira, Matos Douglas Leandro Aparecido Barbosa de, Silva Miquéias Martins Lima, Medeiros Carolina Cintra de Queiroz, Coelho Cláudia Soares de Sousa, Andrade Neto José de Souza, Mistro Sóstenes

2022

General General

A self-attention-based neural network for three-dimensional multivariate modeling and its skillful ENSO predictions.

In Science advances

Large biases and uncertainties remain in real-time predictions of El Niño-Southern Oscillation (ENSO) using process-based dynamical models; recent advances in data-driven deep learning algorithms provide a promising mean to achieve superior skill in the tropical Pacific sea surface temperature (SST) modeling. Here, a specific self-attention-based neural network model is developed for ENSO predictions based on the much sought-after Transformer model, named 3D-Geoformer, which is used to predict three-dimensional (3D) upper-ocean temperature anomalies and wind stress anomalies. This purely data-driven and time-space attention-enhanced model achieves surprisingly high correlation skills for Niño 3.4 SST anomaly predictions made 18 months in advance and initiated beginning in boreal spring. Further, sensitivity experiments demonstrate that the 3D-Geoformer model can depict the evolution of upper-ocean temperature and the coupled ocean-atmosphere dynamics following the Bjerknes feedback mechanism during ENSO cycles. Such successful realizations of the self-attention-based model in ENSO predictions indicate its great potential for multidimensional spatiotemporal modeling in geoscience.

Zhou Lu, Zhang Rong-Hua

2023-Mar-10

General General

Sloppiness: Fundamental study, new formalism and its application in model assessment.

In PloS one ; h5-index 176.0

Computational modelling of biological processes poses multiple challenges in each stage of the modelling exercise. Some significant challenges include identifiability, precisely estimating parameters from limited data, informative experiments and anisotropic sensitivity in the parameter space. One of these challenges' crucial but inconspicuous sources is the possible presence of large regions in the parameter space over which model predictions are nearly identical. This property, known as sloppiness, has been reasonably well-addressed in the past decade, studying its possible impacts and remedies. However, certain critical unanswered questions concerning sloppiness, particularly related to its quantification and practical implications in various stages of system identification, still prevail. In this work, we systematically examine sloppiness at a fundamental level and formalise two new theoretical definitions of sloppiness. Using the proposed definitions, we establish a mathematical relationship between the parameter estimates' precision and sloppiness in linear predictors. Further, we develop a novel computational method and a visual tool to assess the goodness of a model around a point in parameter space by identifying local structural identifiability and sloppiness and finding the most sensitive and least sensitive parameters for non-infinitesimal perturbations. We demonstrate the working of our method in benchmark systems biology models of various complexities. The pharmacokinetic HIV infection model analysis identified a new set of biologically relevant parameters that can be used to control the free virus in an active HIV infection.

Jagadeesan Prem, Raman Karthik, Tangirala Arun K

2023

Pathology Pathology

Detection of malignancy in whole slide images of endometrial cancer biopsies using artificial intelligence.

In PloS one ; h5-index 176.0

In this study we use artificial intelligence (AI) to categorise endometrial biopsy whole slide images (WSI) from digital pathology as either "malignant", "other or benign" or "insufficient". An endometrial biopsy is a key step in diagnosis of endometrial cancer, biopsies are viewed and diagnosed by pathologists. Pathology is increasingly digitised, with slides viewed as images on screens rather than through the lens of a microscope. The availability of these images is driving automation via the application of AI. A model that classifies slides in the manner proposed would allow prioritisation of these slides for pathologist review and hence reduce time to diagnosis for patients with cancer. Previous studies using AI on endometrial biopsies have examined slightly different tasks, for example using images alongside genomic data to differentiate between cancer subtypes. We took 2909 slides with "malignant" and "other or benign" areas annotated by pathologists. A fully supervised convolutional neural network (CNN) model was trained to calculate the probability of a patch from the slide being "malignant" or "other or benign". Heatmaps of all the patches on each slide were then produced to show malignant areas. These heatmaps were used to train a slide classification model to give the final slide categorisation as either "malignant", "other or benign" or "insufficient". The final model was able to accurately classify 90% of all slides correctly and 97% of slides in the malignant class; this accuracy is good enough to allow prioritisation of pathologists' workload.

Fell Christina, Mohammadi Mahnaz, Morrison David, Arandjelović Ognjen, Syed Sheeba, Konanahalli Prakash, Bell Sarah, Bryson Gareth, Harrison David J, Harris-Birtill David

2023

Public Health Public Health

A Comparison of Single and Combined Schemes of Asia-Pacific Colorectal Screening, Faecal Immunochemical and Stool Deoxyribonucleic Acid Testing for Community Colorectal Cancer Screening.

In Journal of multidisciplinary healthcare

OBJECTIVE : To compare the screening efficacy of colonoscopy and pathologically confirmed single and combined Asia-Pacific colorectal screening (APCS), faecal immunochemical testing (FIT) and stool deoxyribonucleic acid (sDNA) testing protocols.

METHODS : From April 2021 to April 2022, 842 volunteers participated in primary colorectal cancer (CRC) screenings using APCS scoring, FIT and sDNA testing and 115 underwent a colonoscopy. One hundred high-risk participants were then identified from the results of both processes. The differences in the three CRC screening tests in combination with the colonoscopy pathology diagnostics were evaluated using Cochran's Q test, the Dunn-Bonferroni test and area under the receiver operating characteristic curve (AUC) value analysis.

RESULTS : Both FIT and sDNA testing demonstrated a 100% performance in detecting CRC. For advanced adenoma, the sensitivity of the FIT + sDNA test scheme (double positive) was 29.2%, and the sensitivities of the combined FIT + sDNA test and APCS scoring + sDNA test schemes were 62.5% and 95.8%, respectively. The FIT + sDNA testing kappa value of advanced colorectal neoplasia was 0.344 (p = 0.011). The sensitivity for nonadvanced adenoma of the APCS score + sDNA test scheme was 91.1%. In terms of positive results, the sensitivity of the APCS score + FIT + sDNA detection protocol was significantly higher than that of the APCS score, FIT, sDNA detection, and FIT + sDNA detection methods (adjusted p < 0.001, respectively). For the FIT + sDNA test, the kappa value was 0.220 (p = 0.015) and the AUC was 0.634 (p = 0.037). The specificity of the FIT + sDNA test scheme was 69.0%.

CONCLUSION : The FIT + sDNA test scheme demonstrated superior diagnostic efficacy, and the combined APCS score + FIT + sDNA test scheme demonstrated remarkable improvements in CRC screening efficiency and sensitivity for detecting positive lesions.

Ze Yuan, Tu Huiming, Zhang Lin, Bai Yu, Ren Yilin, Chen Xin, Xue Yuzheng, Sun Renjuan, Yang Yuling, Yang Jie, Zhou Xuan, Liu Li

2023

colonoscopy, colorectal cancer, faecal immunochemical testing, primary screening, stool DNA test