Microwave-absorbing materials (MAMs) have played critical roles in many civil and military applications, such as coating materials on stealth fighters to avoid radar detections. The efficacy of MAMs ...is evaluated with the reflection loss (RL) and the bandwidth (Δf10, which refers to the band where ≥90% microwave irradiation is lost), along with the peak's position (fmax) and the thickness of the coating. Large RL and Δf10 are frequency targeted for optimized performance. In this study, we demonstrate a data-driven discovery approach to reveal the maximized RL and Δf10, using a polypyrrole/paraffin composite as an example, and found that record-setting RL of −62.6 dB and Δf10 of 7.7 GHz, are obtained, as the best values that have been reported for polypyrrole. We believe that this data-driven approach can be widely applied to other composite systems, to allow more exciting discoveries in the future.
A data-driven approach is demonstrated to reveal the best microwave absorption performance of polypyrrole. Display omitted
Recovery following total joint arthroplasty is patient-specific, yet groups of patients tend to fall into certain similar patterns of recovery. The purpose of this study was to identify and ...characterize recovery patterns following total hip arthroplasty (THA) and total knee arthroplasty (TKA) using patient-reported outcomes that represent distinct health domains. We hypothesized that recovery patterns could be defined and predicted using preoperative data.
Adult patients were recruited from a large, urban academic center. To model postoperative responses to THA and TKA across domains such as physical health, mental health, and joint-specific measures, we employed a longitudinal clustering algorithm that incorporates each of these health domains. The clustering algorithm from multiple health domains allows the ability to define distinct recovery trajectories, which could then be predicted from preoperative and perioperative factors using a multinomial regression.
Four hundred forty-one of 1134 patients undergoing THA and 346 of 921 undergoing TKA met eligibility criteria and were used to define distinct patterns of recovery. The clustering algorithm was optimized for 3 distinct patterns of recovery that were observed in THA and TKA patients. Patients recovering from THA were divided into 3 groups: standard responders (50.8%), late mental responders (13.2%), and substandard responders (36.1%). Multivariable, multinomial regression suggested that these 3 groups had defined characteristics. Late mental responders tended to be obese (P = .05) and use more opioids (P = .01). Substandard responders had a larger number of comorbidities (P = .02) and used more opioids (P = .001). Patients recovering from TKA were divided among standard responders (55.8%), poor mental responders (24%), and poor physical responders (20.2%). Poor mental responders were more likely to be female (P = .04) and American Society of Anesthesiologists class III/IV (P = .004). Poor physical responders were more likely to be female (P = .03), younger (P = .04), American Society of Anesthesiologists III/IV (P = .04), use more opioids (P = .02), and be discharged to a nursing facility (P = .001). The THA and TKA models demonstrated areas under the curve of 0.67 and 0.72.
This multidomain, longitudinal clustering analysis defines 3 distinct patterns in the recovery of THA and TKA patients, with most patients in both cohorts experiencing robust improvement, while others had equally well defined yet less optimal recovery trajectories that were either delayed in recovery or failed to achieve a desired outcome. Patients in the delayed recovery and poor outcome groups were slightly different between THA and TKA. These groups of patients with similar recovery patterns were defined by patient characteristics that include potentially modifiable comorbid factors. This research suggests that there are multiple defined recovery trajectories after THA and TKA, which provides a new perspective on THA and TKA recovery.
III.
Early-stage lung adenocarcinoma (LUAD) is treated with local therapy alone, though patients with grade 3 stage I LUAD a 50% 5-year recurrence rate. Our objective is to determine if analysis of the ...tumor microenvironment can create a predictive model for recurrence.
Thirty-four grade 3 stage I LUAD patients underwent surgical resection. Digital spatial profiling was utilized to perform genomic (n=31) and proteomic (n=34) analysis of pancytokeratin positive (PanCK+) and negative (PanCK-) tumor cells. K-means clustering was performed on the top 50 differential genes and top 20 differential proteins, with Kaplan-Meier recurrence curves based on patient clustering. External validation of high expression genes was performed with Kaplan-Meier Plotter.
There were no significant clinicopathologic differences between patients who did (n=14) and did not (n=20) recur. Median time to recurrence was 806 days; median follow up with no recurrence was 2897 days. K-means clustering of PanCK+ genes resulted in a model with a Kaplan-Meier curve with C-index of 0.75. K-means clustering for PanCK- genes was less successful at differentiating recurrence (C-index 0.6). Genes upregulated or downregulated for recurrence were externally validated using available public databases. Proteomic data did not reach statistical significance but did internally validate the genomic data described above.
Genomic difference in LUAD may be able to predict risk of recurrence. After further validation, stratifying patients by this risk may help guide who will benefit from adjuvant therapy.
Display omitted
Predictive modeling approaches in business process management provide a way to streamline operational business processes. For instance, they can warn decision makers about undesirable events that are ...likely to happen in the future, giving the decision maker an opportunity to intervene. The topic is gaining momentum in process mining, a field of research that has traditionally developed tools to discover business process models from data sets of past process behavior. Predictive modeling techniques are built on top of process-discovery algorithms. As these algorithms describe business process behavior using models of formal languages (e.g., Petri nets), strong language biases are necessary in order to generate models with the limited amounts of data included in the data set. Naturally, corresponding predictive modeling techniques reflect these biases. Based on theory from grammatical inference, a field of research that is concerned with inducing language models, we design a new predictive modeling technique based on weaker biases. Fitting a probabilistic model to a data set of past behavior makes it possible to predict how currently running process instances will behave in the future. To clarify how this technique works and to facilitate its adoption, we also design a way to visualize the probabilistic models. We assess the effectiveness of the technique in an experimental evaluation with synthetic and real-world data.
The ability to sustain attention differs across people and changes within a single person over time. Although recent work has demonstrated that patterns of functional brain connectivity predict ...individual differences in sustained attention, whether these same patterns capture fluctuations in attention within individuals remains unclear. Here, across five independent studies, we demonstrate that the sustained attention connectome-based predictive model (CPM), a validated model of sustained attention function, generalizes to predict attentional state from data collected across minutes, days, weeks, and months. Furthermore, the sustained attention CPM is sensitive to within-subject state changes induced by propofol as well as sevoflurane, such that individuals show functional connectivity signatures of stronger attentional states when awake than when under deep sedation and light anesthesia. Together, these results demonstrate that fluctuations in attentional state reflect variability in the same functional connectivity patterns that predict individual differences in sustained attention.
Acquiring meaningful representations of gene expression is essential for the accurate prediction of downstream regulatory tasks, such as identifying promoters and transcription factor binding sites. ...However, the current dependency on supervised learning, constrained by the limited availability of labeled genomic data, impedes the ability to develop robust predictive models with broad generalization capabilities. In response, recent advancements have pivoted towards the application of self-supervised training for DNA sequence modeling, enabling the adaptation of pre-trained genomic representations to a variety of downstream tasks. Departing from the straightforward application of masked language learning techniques to DNA sequences, approaches such as MoDNA enrich genome language modeling with prior biological knowledge. In this study, we advance DNA language models by utilizing the Motif-oriented DNA (MoDNA) pre-training framework, which is established for self-supervised learning at the pre-training stage and is flexible enough for application across different downstream tasks. MoDNA distinguishes itself by efficiently learning semantic-level genomic representations from an extensive corpus of unlabeled genome data, offering a significant improvement in computational efficiency over previous approaches. The framework is pre-trained on a comprehensive human genome dataset and fine-tuned for targeted downstream tasks. Our enhanced analysis and evaluation in promoter prediction and transcription factor binding site prediction have further validated MoDNA’s exceptional capabilities, emphasizing its contribution to advancements in genomic predictive modeling.
Ecologists frequently ask questions that are best addressed with a model comparison approach. Under this system, the merit of several models is considered without necessarily requiring that (1) ...models are nested, (2) one of the models is true, and (3) only current data be used. This is in marked contrast to the pragmatic blend of Neyman-Pearson and Fisherian significance testing conventionally emphasized in biometric texts (Christensen 2005), in which (1) just two hypotheses are under consideration, representing a pairwise comparison of models, (2) one of the models, H sub(0), is assumed to be true, and (3) a single data set is used to quantify evidence concerning H sub(0).
Purpose
Machine learning classification algorithms (classifiers) for prediction of treatment response are becoming more popular in radiotherapy literature. General Machine learning literature ...provides evidence in favor of some classifier families (random forest, support vector machine, gradient boosting) in terms of classification performance. The purpose of this study is to compare such classifiers specifically for (chemo)radiotherapy datasets and to estimate their average discriminative performance for radiation treatment outcome prediction.
Methods
We collected 12 datasets (3496 patients) from prior studies on post‐(chemo)radiotherapy toxicity, survival, or tumor control with clinical, dosimetric, or blood biomarker features from multiple institutions and for different tumor sites, that is, (non‐)small‐cell lung cancer, head and neck cancer, and meningioma. Six common classification algorithms with built‐in feature selection (decision tree, random forest, neural network, support vector machine, elastic net logistic regression, LogitBoost) were applied on each dataset using the popular open‐source R package caret. The R code and documentation for the analysis are available online (https://github.com/timodeist/classifier_selection_code). All classifiers were run on each dataset in a 100‐repeated nested fivefold cross‐validation with hyperparameter tuning. Performance metrics (AUC, calibration slope and intercept, accuracy, Cohen's kappa, and Brier score) were computed. We ranked classifiers by AUC to determine which classifier is likely to also perform well in future studies. We simulated the benefit for potential investigators to select a certain classifier for a new dataset based on our study (pre‐selection based on other datasets) or estimating the best classifier for a dataset (set‐specific selection based on information from the new dataset) compared with uninformed classifier selection (random selection).
Results
Random forest (best in 6/12 datasets) and elastic net logistic regression (best in 4/12 datasets) showed the overall best discrimination, but there was no single best classifier across datasets. Both classifiers had a median AUC rank of 2. Preselection and set‐specific selection yielded a significant average AUC improvement of 0.02 and 0.02 over random selection with an average AUC rank improvement of 0.42 and 0.66, respectively.
Conclusion
Random forest and elastic net logistic regression yield higher discriminative performance in (chemo)radiotherapy outcome and toxicity prediction than other studied classifiers. Thus, one of these two classifiers should be the first choice for investigators when building classification models or to benchmark one's own modeling results against. Our results also show that an informed preselection of classifiers based on existing datasets can improve discrimination over random selection.