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

General General

Modeling autosomal dominant Alzheimer's disease with machine learning.

In Alzheimer's & dementia : the journal of the Alzheimer's Association

INTRODUCTION : Machine learning models were used to discover novel disease trajectories for autosomal dominant Alzheimer's disease.

METHODS : Longitudinal structural magnetic resonance imaging, amyloid positron emission tomography (PET), and fluorodeoxyglucose PET were acquired in 131 mutation carriers and 74 non-carriers from the Dominantly Inherited Alzheimer Network; the groups were matched for age, education, sex, and apolipoprotein ε4 (APOE ε4). A deep neural network was trained to predict disease progression for each modality. Relief algorithms identified the strongest predictors of mutation status.

RESULTS : The Relief algorithm identified the caudate, cingulate, and precuneus as the strongest predictors among all modalities. The model yielded accurate results for predicting future Pittsburgh compound B (R2  = 0.95), fluorodeoxyglucose (R2  = 0.93), and atrophy (R2  = 0.95) in mutation carriers compared to non-carriers.

DISCUSSION : Results suggest a sigmoidal trajectory for amyloid, a biphasic response for metabolism, and a gradual decrease in volume, with disease progression primarily in subcortical, middle frontal, and posterior parietal regions.

Luckett Patrick H, McCullough Austin, Gordon Brian A, Strain Jeremy, Flores Shaney, Dincer Aylin, McCarthy John, Kuffner Todd, Stern Ari, Meeker Karin L, Berman Sarah B, Chhatwal Jasmeer P, Cruchaga Carlos, Fagan Anne M, Farlow Martin R, Fox Nick C, Jucker Mathias, Levin Johannes, Masters Colin L, Mori Hiroshi, Noble James M, Salloway Stephen, Schofield Peter R, Brickman Adam M, Brooks William S, Cash David M, Fulham Michael J, Ghetti Bernardino, Jack Clifford R, Vöglein Jonathan, Klunk William, Koeppe Robert, Oh Hwamee, Su Yi, Weiner Michael, Wang Qing, Swisher Laura, Marcus Dan, Koudelis Deborah, Joseph-Mathurin Nelly, Cash Lisa, Hornbeck Russ, Xiong Chengjie, Perrin Richard J, Karch Celeste M, Hassenstab Jason, McDade Eric, Morris John C, Benzinger Tammie L S, Bateman Randall J, Ances Beau M


Pittsburgh compound B (PiB), “autosomal dominant Alzheimers disease (ADAD)”, fluorodeoxyglucose (FDG), machine learning, magnetic resonance imaging (MRI)

General General

Co-designing diagnosis: Towards a responsible integration of Machine Learning decision-support systems in medical diagnostics.

In Journal of evaluation in clinical practice

RATIONALE : This paper aims to show how the focus on eradicating bias from Machine Learning decision-support systems in medical diagnosis diverts attention from the hermeneutic nature of medical decision-making and the productive role of bias. We want to show how an introduction of Machine Learning systems alters the diagnostic process. Reviewing the negative conception of bias and incorporating the mediating role of Machine Learning systems in the medical diagnosis are essential for an encompassing, critical and informed medical decision-making.

METHODS : This paper presents a philosophical analysis, employing the conceptual frameworks of hermeneutics and technological mediation, while drawing on the case of Machine Learning algorithms assisting doctors in diagnosis. This paper unravels the non-neutral role of algorithms in the doctor's decision-making and points to the dialogical nature of interaction not only with the patients but also with the technologies that co-shape the diagnosis.

FINDINGS : Following the hermeneutical model of medical diagnosis, we review the notion of bias to show how it is an inalienable and productive part of diagnosis. We show how Machine Learning biases join the human ones to actively shape the diagnostic process, simultaneously expanding and narrowing medical attention, highlighting certain aspects, while disclosing others, thus mediating medical perceptions and actions. Based on that, we demonstrate how doctors can take Machine Learning systems on board for an enhanced medical diagnosis, while being aware of their non-neutral role.

CONCLUSIONS : We show that Machine Learning systems join doctors and patients in co-designing a triad of medical diagnosis. We highlight that it is imperative to examine the hermeneutic role of the Machine Learning systems. Additionally, we suggest including not only the patient, but also colleagues to ensure an encompassing diagnostic process, to respect its inherently hermeneutic nature and to work productively with the existing human and machine biases.

Kudina Olya, de Boer Bas


Machine Learning, hermeneutics, medical diagnosis, technological mediation

General General

Performance assessment of different machine learning approaches in predicting diabetic ketoacidosis in adults with type 1 diabetes using electronic health records data.

In Pharmacoepidemiology and drug safety

PURPOSE : To assess the performance of different machine learning (ML) approaches in identifying risk factors for diabetic ketoacidosis (DKA) and predicting DKA.

METHODS : This study applied flexible ML (XGBoost, distributed random forest [DRF] and feedforward network) and conventional ML approaches (logistic regression and least absolute shrinkage and selection operator [LASSO]) to 3,400 DKA cases and 11,780 controls nested in adults with type 1 diabetes identified from Optum® de-identified Electronic Health Record dataset (2007-2018). Area under the curve (AUC), accuracy, sensitivity and specificity were computed using 5-fold cross validation, and their 95% confidence intervals (CI) were established using 1,000 bootstrap samples. The importance of predictors was compared across these models.

RESULTS : In the training set, XGBoost and feedforward network yielded higher AUC values (0.89 and 0.86, respectively) than logistic regression (0.83), LASSO (0.83) and DRF (0.81). However, the AUC values were similar (0.82) among these approaches in the test set (95% CI range, 0.80-0.84). While the accuracy values >0.8 and the specificity values >0.9 for all models, the sensitivity values were only 0.4. The differences in these metrics across these models were minimal in the test set. All approaches selected some known risk factors for DKA as the top ten features. XGBoost and DRF included more laboratory measurements or vital signs compared with conventional ML approaches, while feedforward network included more social demographics.

CONCLUSIONS : In our empirical study, all ML approaches demonstrated similar performance, and identified overlapping, but different, top ten predictors. The difference in selected top predictors needs further research. This article is protected by copyright. All rights reserved.

Li Lin, Lee Chuang-Chung, Zhou Fang Liz, Molony Cliona, Doder Zoran, Zalmover Evgeny, Sharma Kristen, Juhaeri Juhaeri, Wu Chuntao


AUC, Diabetic ketoacidosis, Least absolute shrinkage and selection operator, Logistic regression, Machine learning, Prediction model

General General

DeepControl: 2DRF pulses facilitating B 1 + inhomogeneity and B0 off-resonance compensation in vivo at 7 T.

In Magnetic resonance in medicine ; h5-index 66.0

PURPOSE : Rapid 2DRF pulse design with subject-specific B 1 + inhomogeneity and B0 off-resonance compensation at 7 T predicted from convolutional neural networks is presented.

METHODS : The convolution neural network was trained on half a million single-channel transmit 2DRF pulses optimized with an optimal control method using artificial 2D targets, B 1 + and B0 maps. Predicted pulses were tested in a phantom and in vivo at 7 T with measured B 1 + and B0 maps from a high-resolution gradient echo sequence.

RESULTS : Pulse prediction by the trained convolutional neural network was done on the fly during the MR session in approximately 9 ms for multiple hand-drawn regions of interest and the measured B 1 + and B0 maps. Compensation of B 1 + inhomogeneity and B0 off-resonances has been confirmed in the phantom and in vivo experiments. The reconstructed image data agree well with the simulations using the acquired B 1 + and B0 maps, and the 2DRF pulse predicted by the convolutional neural networks is as good as the conventional RF pulse obtained by optimal control.

CONCLUSION : The proposed convolutional neural network-based 2DRF pulse design method predicts 2DRF pulses with an excellent excitation pattern and compensated B 1 + and B0 variations at 7 T. The rapid 2DRF pulse prediction (9 ms) enables subject-specific high-quality 2DRF pulses without the need to run lengthy optimizations.

Vinding Mads Sloth, Aigner Christoph Stefan, Schmitter Sebastian, Lund Torben Ellegaard


2DRF pulses, 7 T, artificial intelligence, deep learning, optimal control

General General

Variables Influencing per Capita Production, Separate Collection, and Costs of Municipal Solid Waste in the Apulia Region (Italy): An Experience of Deep Learning.

In International journal of environmental research and public health ; h5-index 73.0

Municipal solid waste (MSW) must be managed to reduce its impact on environmental matrices and population health as much as possible. In particular, the variables that influence the production, separate waste collection, and costs of MSW must be understood. Although many studies have shown that such factors are specific to an area, the awareness of these factors has created opportunities to implement operations to enable more effective and efficient MSW management services, and to specifically respond to the variables that have the most impact. The deep learning approaches used in this study are effective in achieving this goal and can be used in any other territorial context to ensure that the organizations that deal with these issues are more aware and create useful plans to promote the circular economy. Our findings indicate the important influence of number of rooms in a residential buildings and construction years on MSW production, the combination of services such as municipal collection centers and door-to-door service for separate MSW collection and the characteristics of the residential buildings in the municipalities on MSW management costs.

Fasano Fabrizio, Addante Anna Sabrina, Valenzano Barbara, Scannicchio Giovanni


deep learning, door to door service, municipal collection centers, municipal solid waste, separate collection, waste management

General General

Biochemical features and mutations of key proteins in SARS-CoV-2 and their impacts on RNA therapeutics.

In Biochemical pharmacology ; h5-index 61.0

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has caused a global pandemic. Three viral proteins, the spike protein (S) for attachment of virus to host cells, 3-chymotrypsin-like cysteine protease (Mpro) for digestion of viral polyproteins to functional proteins, and RNA-dependent-RNA-polymerase (RdRp) for RNA synthesis are the most critical proteins for virus infection and replication, rendering them the most important drug targets for both antibody and chemical drugs. Due to its low-fidelity polymerase, the virus is subject to frequent mutations. To date, the sequence data from tens of thousands of virus isolates have revealed hundreds of mutations. Although most mutations have a minimum consequence, a small number of non-synonymous mutations may alter the virulence and antigenicity of the mutants. To evaluate the effects of viral mutations on drug safety and efficacy, we reviewed the biochemical features of the three main proteins and their potentials as drug targets, and analyzed the mutation profiles and their impacts on RNA therapeutics. We believe that monitoring and predicting mutation-introduced protein conformational changes in the three key viral proteins and evaluating their binding affinities and enzymatic activities with the U.S. Food and Drug Administration (FDA) regulated drugs by using computational modeling and machine learning processes can provide valuable information for the consideration of drug efficacy and drug safety for drug developers and drug reviewers. Finally, we propose an interactive database for drug developers and reviewers to use in evaluating the safety and efficacy of U.S. FDA regulated drugs with regard to viral mutations.

Zeng Li, Li Dongying, Tong Weida, Shi Tieliu, Ning Baitang


COVID-19, Drug safety and drug efficacy, Mutation, RNA therapeutics, SARS-CoV-2