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

General General

Prediction of short-term antidepressant response using probabilistic graphical models with replication across multiple drugs and treatment settings.

In Neuropsychopharmacology : official publication of the American College of Neuropsychopharmacology

Heterogeneity in the clinical presentation of major depressive disorder and response to antidepressants limits clinicians' ability to accurately predict a specific patient's eventual response to therapy. Validated depressive symptom profiles may be an important tool for identifying poor outcomes early in the course of treatment. To derive these symptom profiles, we first examined data from 947 depressed subjects treated with selective serotonin reuptake inhibitors (SSRIs) to delineate the heterogeneity of antidepressant response using probabilistic graphical models (PGMs). We then used unsupervised machine learning to identify specific depressive symptoms and thresholds of improvement that were predictive of antidepressant response by 4 weeks for a patient to achieve remission, response, or nonresponse by 8 weeks. Four depressive symptoms (depressed mood, guilt feelings and delusion, work and activities and psychic anxiety) and specific thresholds of change in each at 4 weeks predicted eventual outcome at 8 weeks to SSRI therapy with an average accuracy of 77% (p = 5.5E-08). The same four symptoms and prognostic thresholds derived from patients treated with SSRIs correctly predicted outcomes in 72% (p = 1.25E-05) of 1996 patients treated with other antidepressants in both inpatient and outpatient settings in independent publicly-available datasets. These predictive accuracies were higher than the accuracy of 53% for predicting SSRI response achieved using approaches that (i) incorporated only baseline clinical and sociodemographic factors, or (ii) used 4-week nonresponse status to predict likely outcomes at 8 weeks. The present findings suggest that PGMs providing interpretable predictions have the potential to enhance clinical treatment of depression and reduce the time burden associated with trials of ineffective antidepressants. Prospective trials examining this approach are forthcoming.

Athreya Arjun P, Brückl Tanja, Binder Elisabeth B, John Rush A, Biernacka Joanna, Frye Mark A, Neavin Drew, Skime Michelle, Monrad Ditlev, Iyer Ravishankar K, Mayes Taryn, Trivedi Madhukar, Carter Rickey E, Wang Liewei, Weinshilboum Richard M, Croarkin Paul E, Bobo William V

2021-Jan-15

General General

Investigation on performance of particle swarm optimization (PSO) algorithm based fuzzy inference system (PSOFIS) in a combination of CFD modeling for prediction of fluid flow.

In Scientific reports ; h5-index 158.0

Herein, a reactor of bubble column type with non-equilibrium thermal condition between air and water is mechanistically modeled and simulated by the CFD technique. Moreover, the combination of the adaptive network (AN) trainer with the fuzzy inference system (FIS) as the artificial intelligence method calling ANFIS has already shown potential in the optimization of CFD approach. Although the artificial intelligence method of particle swarm optimization (PSO) algorithm based fuzzy inference system (PSOFIS) has a good background for optimizing the other fields of research, there are not any investigations on the cooperation of this method with the CFD. The PSOFIS can reduce all the difficulties and simplify the investigation by elimination of the additional CFD simulations. In fact, after achieving the best intelligence, all the predictions can be done by the PSOFIS instead of the massive computational efforts needed for CFD modeling. The first aim of this study is to develop the PSOFIS for use in the CFD approach application. The second one is to make a comparison between the PSOFIS and ANFIS for the accurate prediction of the CFD results. In the present study, the CFD data are learned by the PSOFIS for prediction of the water velocity inside the bubble column. The values of input numbers, swarm sizes, and inertia weights are investigated for the best intelligence. Once the best intelligence is achieved, there is no need to mesh refinement in the CFD domain. The mesh density can be increased, and the newer predictions can be done in an easier way by the PSOFIS with much less computational efforts. For a strong verification, the results of the PSOFIS in the prediction of the liquid velocity are compared with those of the ANFIS. It was shown that for the same fuzzy set parameters, the PSOFIS predictions are closer to the CFD in comparison with the ANFIS. The regression number (R) of the PSOFIS (0.98) was a little more than that of the ANFIS (0.97). The PSOFIS showed a powerful potential in mesh density increment from 9477 to 774,468 and accurate predictions for the new nodes independent of the CFD modeling.

Babanezhad Meisam, Behroyan Iman, Nakhjiri Ali Taghvaie, Marjani Azam, Rezakazemi Mashallah, Heydarinasab Amir, Shirazian Saeed

2021-Jan-15

General General

Summer weather conditions influence winter survival of honey bees (Apis mellifera) in the northeastern United States.

In Scientific reports ; h5-index 158.0

Honey bees are crucial pollinators for agricultural and natural ecosystems, but are experiencing heavy mortality in North America and Europe due to a complex suite of factors. Understanding the relative importance of each factor would enable beekeepers to make more informed decisions and improve assessment of local and regional habitat suitability. We used 3 years of Pennsylvania beekeepers' survey data to assess the importance of weather, topography, land use, and management factors on overwintering mortality at both apiary and colony levels, and to predict survival given current weather conditions and projected climate changes. Random Forest, a tree-based machine learning approach suited to describing complex nonlinear relationships among factors, was used. A Random Forest model predicted overwintering survival with 73.3% accuracy for colonies and 65.7% for apiaries where Varroa mite populations were managed. Growing degree days and precipitation of the warmest quarter of the preceding year were the most important predictors at both levels. A weather-only model was used to predict colony survival probability, and to create a composite map of survival for 1981-2019. Although 3 years data were likely not enough to adequately capture the range of possible climatic conditions, the model performed well within its constraints.

Calovi Martina, Grozinger Christina M, Miller Douglas A, Goslee Sarah C

2021-Jan-15

General General

Coupling machine learning and crop modeling improves crop yield prediction in the US Corn Belt.

In Scientific reports ; h5-index 158.0

This study investigates whether coupling crop modeling and machine learning (ML) improves corn yield predictions in the US Corn Belt. The main objectives are to explore whether a hybrid approach (crop modeling + ML) would result in better predictions, investigate which combinations of hybrid models provide the most accurate predictions, and determine the features from the crop modeling that are most effective to be integrated with ML for corn yield prediction. Five ML models (linear regression, LASSO, LightGBM, random forest, and XGBoost) and six ensemble models have been designed to address the research question. The results suggest that adding simulation crop model variables (APSIM) as input features to ML models can decrease yield prediction root mean squared error (RMSE) from 7 to 20%. Furthermore, we investigated partial inclusion of APSIM features in the ML prediction models and we found soil moisture related APSIM variables are most influential on the ML predictions followed by crop-related and phenology-related variables. Finally, based on feature importance measure, it has been observed that simulated APSIM average drought stress and average water table depth during the growing season are the most important APSIM inputs to ML. This result indicates that weather information alone is not sufficient and ML models need more hydrological inputs to make improved yield predictions.

Shahhosseini Mohsen, Hu Guiping, Huber Isaiah, Archontoulis Sotirios V

2021-Jan-15

General General

TreeMap, a tree-level model of conterminous US forests circa 2014 produced by imputation of FIA plot data.

In Scientific data

A 30 × 30m-resolution gridded dataset of forest plot identifiers was developed for the conterminous United States (CONUS) using a random forests machine-learning imputation approach. Forest plots from the US Forest Service Forest Inventory and Analysis program (FIA) were imputed to gridded c2014 landscape data provided by the LANDFIRE project using topographic, biophysical, and disturbance variables. The output consisted of a raster map of plot identifiers. From the plot identifiers, users of the dataset can link to a number of tree- and plot-level attributes stored in the accompanying tables and in the publicly available FIA DataMart, and then produce maps of any of these attributes, including number of trees per acre, tree species, and forest type. Of 67,141 FIA plots available, 62,758 of these (93.5%) were utilized at least once in imputation to 2,841,601,981 forested pixels in CONUS. Continuous high-resolution forest structure data at a national scale will be invaluable for analyzing carbon dynamics, habitat distributions, and fire effects.

Riley Karin L, Grenfell Isaac C, Finney Mark A, Wiener Jason M

2021-Jan-15

Ophthalmology Ophthalmology

Detection of active and inactive phases of thyroid-associated ophthalmopathy using deep convolutional neural network.

In BMC ophthalmology

BACKGROUND : This study aimed to establish a deep learning system for detecting the active and inactive phases of thyroid-associated ophthalmopathy (TAO) using magnetic resonance imaging (MRI). This system could provide faster, more accurate, and more objective assessments across populations.

METHODS : A total of 160 MRI images of patients with TAO, who visited the Ophthalmology Clinic of the Ninth People's Hospital, were retrospectively obtained for this study. Of these, 80% were used for training and validation, and 20% were used for testing. The deep learning system, based on deep convolutional neural network, was established to distinguish patients with active phase from those with inactive phase. The accuracy, precision, sensitivity, specificity, F1 score and area under the receiver operating characteristic curve were analyzed. Besides, visualization method was applied to explain the operation of the networks.

RESULTS : Network A inherited from Visual Geometry Group network. The accuracy, specificity and sensitivity were 0.863±0.055, 0.896±0.042 and 0.750±0.136 respectively. Due to the recurring phenomenon of vanishing gradient during the training process of network A, we added parts of Residual Neural Network to build network B. After modification, network B improved the sensitivity (0.821±0.021) while maintaining a good accuracy (0.855±0.018) and a good specificity (0.865±0.021).

CONCLUSIONS : The deep convolutional neural network could automatically detect the activity of TAO from MRI images with strong robustness, less subjective judgment, and less measurement error. This system could standardize the diagnostic process and speed up the treatment decision making for TAO.

Lin Chenyi, Song Xuefei, Li Lunhao, Li Yinwei, Jiang Mengda, Sun Rou, Zhou Huifang, Fan Xianqun

2021-Jan-14

Machine learning, Magnetic resonance imaging, Thyroid-associated ophthalmopathy