Assessing Free-Living Postural Sway in Persons With Multiple Sclerosis.

Postural instability is associated with disease status and fall risk in Persons with Multiple Sclerosis (PwMS). However, assessments of postural instability, known as postural sway, leverage force platforms or wearable accelerometers, and are most often conducted in laboratory environments and are thus not broadly accessible. Remote measures of postural sway captured during daily life may provide a more accessible alterative, but their ability to capture disease status and fall risk has not yet been established. We explored the utility of remote measures of postural sway in a sample of 33 PwMS. Remote measures of sway differed significantly from lab-based measures, but still demonstrated moderately strong associations with patient-reported measures of balance and mobility impairment. Machine learning models for predicting fall risk trained on lab data provided an Area Under Curve (AUC) of 0.79, while remote data only achieved an AUC of 0.51. Remote model performance improved to an AUC of 0.74 after a new, subject-specific k-means clustering approach was applied for identifying the remote data most appropriate for modelling. This cluster-based approach for analyzing remote data also strengthened associations with patient-reported measures, increasing their strength above those observed in the lab. This work introduces a new framework for analyzing data from remote patient monitoring technologies and demonstrates the promise of remote postural sway assessment for assessing fall risk and characterizing balance impairment in PwMS.

The ChAMP App: A Scalable mHealth Technology for Detecting Digital Phenotypes of Early Childhood Mental Health.

Childhood mental health problems are common, impairing, and can become chronic if left untreated. Children are not reliable reporters of their emotional and behavioral health, and caregivers often unintentionally under- or over-report child symptoms, making assessment challenging. Objective physiological and behavioral measures of emotional and behavioral health are emerging. However, these methods typically require specialized equipment and expertise in data and sensor engineering to administer and analyze. To address this challenge, we have developed the ChAMP (Childhood Assessment and Management of digital Phenotypes) System, which includes a mobile application for collecting movement and audio data during a battery of mood induction tasks and an open-source platform for extracting digital biomarkers. As proof of principle, we present ChAMP System data from 101 children 4-8 years old, with and without diagnosed mental health disorders. Machine learning models trained on these data detect the presence of specific disorders with 70-73% balanced accuracy, with similar results to clinical thresholds on established parent-report measures (63-82% balanced accuracy). Features favored in model architectures are described using Shapley Additive Explanations (SHAP). Canonical Correlation Analysis reveals moderate to strong associations between predictors of each disorder and associated symptom severity (r = .51-.83). The open-source ChAMP System provides clinically-relevant digital biomarkers that may later complement parent-report measures of emotional and behavioral health for detecting kids with underlying mental health conditions and lowers the barrier to entry for researchers interested in exploring digital phenotyping of childhood mental health.

Toward Digital Phenotypes of Early Childhood Mental Health via Unsupervised and Supervised Machine Learning.

Childhood mental health disorders such as anxiety, depression, and ADHD are commonly-occurring and often go undetected into adolescence or adulthood. This can lead to detrimental impacts on long-term wellbeing and quality of life. Current parent-report assessments for pre-school aged children are often biased, and thus increase the need for objective mental health screening tools. Leveraging digital tools to identify the behavioral signature of childhood mental disorders may enable increased intervention at the time with the highest chance of long-term impact. We present data from 84 participants (4-8 years old, 50% diagnosed with anxiety, depression, and/or ADHD) collected during a battery of mood induction tasks using the ChAMP System. Unsupervised Kohonen Self-Organizing Maps (SOM) constructed from movement and audio features indicate that age did not tend to explain clusters as consistently as gender within task-specific and cross-task SOMs. Symptom prevalence and diagnostic status also showed some evidence of clustering. Case studies suggest that high impairment (>80th percentile symptom counts) and diagnostic subtypes (ADHD-Combined) may account for most behaviorally distinct children. Based on this same dataset, we also present results from supervised modeling for the binary classification of diagnoses. Our top performing models yield moderate but promising results (ROC AUC .6-.82, TPR .36-.71, Accuracy .62-.86) on par with our previous efforts for isolated behavioral tasks. Enhancing features, tuning model parameters, and incorporating additional wearable sensor data will continue to enable the rapid progression towards the discovery of digital phenotypes of childhood mental health.Clinical Relevance- This work advances the use of wearables for detecting childhood mental health disorders.

Preterm Preeclampsia Risk Modelling: Examining Hemodynamic, Biochemical, and Biophysical Markers Prior to Pregnancy.

Preeclampsia (PE) is a leading cause of maternal and perinatal death globally and can lead to unplanned preterm birth. Predicting risk for preterm or early-onset PE, has been investigated primarily after conception, and particularly in the early and mid-gestational periods. However, there is a distinct clinical advantage in identifying individuals at risk for PE prior to conception, when a wider array of preventive interventions are available. In this work, we leverage machine learning techniques to identify potential pre-pregnancy biomarkers of PE in a sample of 80 women, 10 of whom were diagnosed with preterm preeclampsia during their subsequent pregnancy. We explore prospective biomarkers derived from hemodynamic, biophysical, and biochemical measurements and several modeling approaches. A support vector machine (SVM) optimized with stochastic gradient descent yields the highest overall performance with ROC AUC and detection rates up to .88 and .70, respectively on subject-wise cross validation. The best performing models leverage biophysical and hemodynamic biomarkers. While preliminary, these results indicate the promise of a machine learning based approach for detecting individuals who are at risk for developing preterm PE before they become pregnant. These efforts may inform gestational planning and care, reducing risk for adverse PE-related outcomes.Clinical Relevance- This work considers the development and optimization of pre-pregnancy biomarkers for improving the identification of preterm (early-onset) preeclampsia risk prior to conception.

The ChAMP App: A Scalable mHealth Technology for Detecting Digital Phenotypes of Early Childhood Mental Health.

Childhood mental health problems are common, impairing, and can become chronic if left untreated. Children are not reliable reporters of their emotional and behavioral health, and caregivers often unintentionally under- or over-report child symptoms, making assessment challenging. Objective physiological and behavioral measures of emotional and behavioral health are emerging. However, these methods typically require specialized equipment and expertise in data and sensor engineering to administer and analyze. To address this challenge, we have developed the ChAMP (Childhood Assessment and Management of digital Phenotypes) System, which includes a mobile application for collecting movement and audio data during a battery of mood induction tasks and an open-source platform for extracting digital biomarkers. As proof of principle, we present ChAMP System data from 101 children 4-8 years old, with and without diagnosed mental health disorders. Machine learning models trained on these data detect the presence of specific disorders with 70-73% balanced accuracy, with similar results to clinical thresholds on established parent-report measures (63-82% balanced accuracy). Features favored in model architectures are described using Shapley Additive Explanations (SHAP). Canonical Correlation Analysis reveals moderate to strong associations between predictors of each disorder and associated symptom severity (r = .51-.83). The open-source ChAMP System provides clinically-relevant digital biomarkers that may later complement parent-report measures of emotional and behavioral health for detecting kids with underlying mental health conditions and lowers the barrier to entry for researchers interested in exploring digital phenotyping of childhood mental health.

Chest-Based Wearables and Individualized Distributions for Assessing Postural Sway in Persons With Multiple Sclerosis.

Typical assessments of balance impairment are subjective or require data from cumbersome and expensive force platforms. Researchers have utilized lower back (sacrum) accelerometers to enable more accessible, objective measurement of postural sway for use in balance assessment. However, new sensor patches are broadly being deployed on the chest for cardiac monitoring, opening a need to determine if measurements from these devices can similarly inform balance assessment. Our aim in this work is to validate postural sway measurements from a chest accelerometer. To establish concurrent validity, we considered data from 16 persons with multiple sclerosis (PwMS) asked to stand on a force platform while also wearing sensor patches on the sacrum and chest. We found five of 15 postural sway features derived from the chest and sacrum were significantly correlated with force platform-derived features, which is in line with prior sacrum-derived findings. Clinical significance was established using a sample of 39 PwMS who performed eyes-open, eyes-closed, and tandem standing tasks. This cohort was stratified by fall status and completed several patient-reported measures (PRM) of balance and mobility impairment. We also compared sway features derived from a single 30-second period to those derived from a one-minute period with a sliding window to create individualized distributions of each postural sway feature (ID method). We find traditional computation of sway features from the chest is sensitive to changes in PRMs and task differences. Distribution characteristics from the ID method establish additional relationships with PRMs, detect differences in more tasks, and distinguish between fall status groups. Overall, the chest was found to be a valid location to monitor postural sway and we recommend utilizing the ID method over single-observation analyses.

Digital Phenotypes of Instability and Fatigue Derived From Daily Standing Transitions in Persons With Multiple Sclerosis.

Impairment in persons with multiple sclerosis (PwMS) can often be attributed to symptoms of motor instability and fatigue. Symptom monitoring and queued interventions often target these symptoms. Clinical metrics are currently limited to objective physician assessments or subjective patient reported measures. Recent research has turned to wearables for improving the objectivity and temporal resolution of assessment. Our group has previously observed wearable assessment of supervised and unsupervised standing transitions to be predictive of fall-risk in PwMS. Here we extend the application of standing transition quantification to longitudinal home monitoring of symptoms. Subjects (N=23) with varying degrees of MS impairment were recruited and monitored with accelerometry for a total of  âˆ¼  6 weeks each. These data were processed using a preexisting framework, applying a deep learning activity classifier to isolate periods of standing transition from which descriptive features were extracted for analysis. Participants completed daily and biweekly assessments describing their symptoms. From these data, Canonical Correlation Analysis was used to derive digital phenotypes of MS instability and fatigue. We find these phenotypes capable of distinguishing fallers from non-fallers, and further that they demonstrate a capacity to characterize symptoms at both daily and sub-daily resolutions. These results represent promising support for future applications of wearables, which may soon augment or replace current metrics in longitudinal monitoring of PwMS.

Preterm Preeclampsia Risk Modelling: Examining Hemodynamic, Biochemical, and Biophysical Markers Prior to Pregnancy.

Preeclampsia (PE) is a leading cause of maternal and perinatal death globally and can lead to unplanned preterm birth. Predicting risk for preterm or early-onset PE, has been investigated primarily after conception, and particularly in the early and mid-gestational periods. However, there is a distinct clinical advantage in identifying individuals at risk for PE prior to conception, when a wider array of preventive interventions are available. In this work, we leverage machine learning techniques to identify potential pre-pregnancy biomarkers of PE in a sample of 80 women, 10 of whom were diagnosed with preterm preeclampsia during their subsequent pregnancy. We explore biomarkers derived from hemodynamic, biophysical, and biochemical measurements and several modeling approaches. A support vector machine (SVM) optimized with stochastic gradient descent yields the highest overall performance with ROC AUC and detection rates up to .88 and .70, respectively on subject-wise cross validation. The best performing models leverage biophysical and hemodynamic biomarkers. While preliminary, these results indicate the promise of a machine learning based approach for detecting individuals who are at risk for developing preterm PE before they become pregnant. These efforts may inform gestational planning and care, reducing risk for adverse PE-related outcomes.

Perinodular Parenchymal Features Improve Indeterminate Lung Nodule Classification.

BACKGROUND: Radiomics, defined as quantitative features extracted from images, provide a non-invasive means of assessing malignant versus benign pulmonary nodules. In this study, we evaluate the consistency with which perinodular radiomics extracted from low-dose computed tomography images serve to identify malignant pulmonary nodules. MATERIALS AND METHODS: Using the National Lung Screening Trial (NLST), we selected individuals with pulmonary nodules between 4mm to 20mm in diameter. Nodules were segmented to generate four distinct datasets; 1) a Tumor dataset containing tumor-specific features, 2) a 10 mm Band dataset containing parenchymal features between the segmented nodule boundary and 10mm out from the boundary, 3) a 15mm Band dataset, and 4) a Tumor Size dataset containing the maximum nodule diameter. Models to predict malignancy were constructed using support-vector machine (SVM), random forest (RF), and least absolute shrinkage and selection operator (LASSO) approaches. Ten-fold cross validation with 10 repetitions per fold was used to evaluate the performance of each approach applied to each dataset. RESULTS: With respect to the RF, the Tumor, 10mm Band, and 15mm Band datasets achieved areas under the receiver-operator curve (AUC) of 84.44%, 84.09%, and 81.57%, respectively. Significant differences in performance were observed between the Tumor and 15mm Band datasets (adj. p-value <0.001). However, when combining tumor-specific features with perinodular features, the 10mm Band + Tumor and 15mm Band + Tumor datasets (AUC 87.87% and 86.75%, respectively) performed significantly better than the Tumor Size dataset (66.76%) or the Tumor dataset. Similarly, the AUCs from the SVM and LASSO were 84.71% and 88.91%, respectively, for the 10mm Band + Tumor. CONCLUSIONS: The combined 10mm Band + Tumor dataset improved the differentiation between benign and malignant lung nodules compared to the Tumor datasets across all methodologies. This demonstrates that parenchymal features capture novel diagnostic information beyond that present in the nodule itself. (data agreement: NLST-163).

A machine learning approach to predicting early and late postoperative reintubation.

Accurate estimation of surgical risks is important for informing the process of shared decision making and informed consent. Postoperative reintubation (POR) is a severe complication that is associated with postoperative morbidity. Previous studies have divided POR into early POR (within 72 h of surgery) and late POR (within 30 days of surgery). Using data provided by American College of Surgeons (ACS) National Surgical Quality Improvement Program (NSQIP), machine learning classification models (logistic regression, random forest classification, and gradient boosting classification) were utilized to develop scoring systems for the prediction of combined, early, and late POR. The risk factors included in each scoring system were narrowed down from a set of 37 pre and perioperative factors. The scoring systems developed from the logistic regression models demonstrated strong performance in terms of both accuracy and discrimination across the different POR outcomes (Average Brier score, 0.172; Average c-statistic, 0.852). These results were only marginally worse than prediction using the full set of risk variables (Average Brier score, 0.145; Average c-statistic, 0.870). While more work needs to be done to identify clinically relevant differences between the early and late POR outcomes, the scoring systems provided here can be used by surgeons and patients to improve the quality of care overall.

UVM KID Study: Identifying Multimodal Features and Optimizing Wearable Instrumentation to Detect Child Anxiety.

Anxiety and depression, collectively known as internalizing disorders, begin as early as the preschool years and impact nearly 1 out of every 5 children. Left undiagnosed and untreated, childhood internalizing disorders predict later health problems including substance abuse, development of comorbid psychopathology, increased risk for suicide, and substantial functional impairment. Current diagnostic procedures require access to clinical experts, take considerable time to complete, and inherently assume that child symptoms are observable by caregivers. Multi-modal wearable sensors may enable development of rapid point-of-care diagnostics that address these challenges. Building on our prior work, here we present an assessment battery for the development of a digital phenotype for internalizing disorders in young children and an early feasibility case study of multi-modal wearable sensor data from two participants, one of whom has been clinically diagnosed with an internalizing disorder. Results lend support that sacral movement responses and R-R interval during a short stress-induction task may facilitate child diagnosis. Multi-modal sensors measuring movement and surface biopotentials of the chest and trapezius are also shown to have significant redundancy, introducing the potential for sensor optimization moving forward. Future work aims to further optimize sensor placement, signals, features, and assessments to enable deployment in clinical practice. Clinical Relevance- This work considers the development and optimization of technologies for improving the identification of children with internalizing disorders.

How Much Data Is Enough? A Reliable Methodology to Examine Long-Term Wearable Data Acquisition in Gait and Postural Sway.

Wearable sensors facilitate the evaluation of gait and balance impairment in the free-living environment, often with observation periods spanning weeks, months, and even years. Data supporting the minimal duration of sensor wear, which is necessary to capture representative variability in impairment measures, are needed to balance patient burden, data quality, and study cost. Prior investigations have examined the duration required for resolving a variety of movement variables (e.g., gait speed, sit-to-stand tests), but these studies use differing methodologies and have only examined a small subset of potential measures of gait and balance impairment. Notably, postural sway measures have not yet been considered in these analyses. Here, we propose a three-level framework for examining this problem. Difference testing and intra-class correlations (ICC) are used to examine the agreement in features computed from potential wear durations (levels one and two). The association between features and established patient reported outcomes at each wear duration is also considered (level three) for determining the necessary wear duration. Utilizing wearable accelerometer data continuously collected from 22 persons with multiple sclerosis (PwMS) for 6 weeks, this framework suggests that 2 to 3 days of monitoring may be sufficient to capture most of the variability in gait and sway; however, longer periods (e.g., 3 to 6 days) may be needed to establish strong correlations to patient-reported clinical measures. Regression analysis indicates that the required wear duration depends on both the observation frequency and variability of the measure being considered. This approach provides a framework for evaluating wear duration as one aspect of the comprehensive assessment, which is necessary to ensure that wearable sensor-based methods for capturing gait and balance impairment in the free-living environment are fit for purpose.

Connecting livestock disease dynamics to human learning and biosecurity decisions.

The acceleration of animal disease spread worldwide due to increased animal, feed, and human movement has driven a growing body of epidemiological research as well as a deeper interest in human behavioral studies aimed at understanding their interconnectedness. Biosecurity measures can reduce the risk of infection, but human risk tolerance can hinder biosecurity investments and compliance. Humans may learn from hardship and become more risk averse, but sometimes they instead become more risk tolerant because they forget negative experiences happened in the past or because they come to believe they are immune. We represent the complexity of the hog production system with disease threats, human decision making, and human risk attitude using an agent-based model. Our objective is to explore the role of risk tolerant behaviors and the consequences of delayed biosecurity investments. We set up experiment with Monte Carlo simulations of scenarios designed with different risk tolerance amongst the swine producers and we derive distributions and trends of biosecurity and porcine epidemic diarrhea virus (PEDv) incidence emerging in the system. The output data allowed us to examine interactions between modes of risk tolerance and timings of biosecurity response discussing consequences for disease protection in the production system. The results show that hasty and delayed biosecurity responses or slow shifts toward a biosecure culture do not guarantee control of contamination when the disease has already spread in the system. In an effort to support effective disease prevention, our model results can inform policy making to move toward more resilient and healthy production systems. The modeled dynamics of risk attitude have also the potential to improve communication strategies for nudging and establishing risk averse behaviors thereby equipping the production system in case of foreign disease incursions.

Open-source dataset reveals relationship between walking bout duration and fall risk classification performance in persons with multiple sclerosis.

Falls are frequent and associated with morbidity in persons with multiple sclerosis (PwMS). Symptoms of MS fluctuate, and standard biannual clinical visits cannot capture these fluctuations. Remote monitoring techniques that leverage wearable sensors have recently emerged as an approach sensitive to disease variability. Previous research has shown that fall risk can be identified from walking data collected by wearable sensors in controlled laboratory conditions however this data may not be generalizable to variable home environments. To investigate fall risk and daily activity performance from remote data, we introduce a new open-source dataset featuring data collected from 38 PwMS, 21 of whom are identified as fallers and 17 as non-fallers based on their six-month fall history. This dataset contains inertial-measurement-unit data from eleven body locations collected in the laboratory, patient-reported surveys and neurological assessments, and two days of free-living sensor data from the chest and right thigh. Six-month (n = 28) and one-year repeat assessment (n = 15) data are also available for some patients. To demonstrate the utility of these data, we explore the use of free-living walking bouts for characterizing fall risk in PwMS, compare these data to those collected in controlled environments, and examine the impact of bout duration on gait parameters and fall risk estimates. Both gait parameters and fall risk classification performance were found to change with bout duration. Deep learning models outperformed feature-based models using home data; the best performance was observed with all bouts for deep-learning and short bouts for feature-based models when evaluating performance on individual bouts. Overall, short duration free-living walking bouts were found to be the least similar to laboratory walking, longer duration free-living walking bouts provided more significant differences between fallers and non-fallers, and an aggregation of all free-living walking bouts yields the best performance in fall risk classification.

Understanding the factors that affect the appropriateness of rheumatology referrals.

BACKGROUND: Reducing inappropriate referrals to specialists is a challenge for the healthcare system as it seeks to transition from volume to value-based healthcare. Given the projection of a severe shortage of rheumatologists in the near future, innovative strategies to decrease demand for rheumatology services may prove more fruitful than increasing the supply of rheumatologists. Efforts to increase appropriate utilization through reductions in capacity may have the unintended consequence of reducing appropriate care as well. This highlights the challenges in increasing the appropriate use of high cost services as the health system transitions to value based care. The objective of this study was to analyze factors affecting appropriateness of rheumatology services. METHODS: This was a cross-sectional study of patients receiving Rheumatology services between November 2013 and October 2019. We used a proxy for "appropriateness": whether or not there was any follow-up care after the first appointment. Results from regression analysis and physicians' chart reviews were compared using an inter-rater reliability measure (kappa). Data was drawn from the EHR 2013-2019. RESULTS: We found that inappropriate referrals increased 14.3% when a new rheumatologist was hired, which increased to 14.8% after wash-out period of 6 months; 15.7% after 12 months; 15.5% after 18 months and 16.7% after 18 months. Other factors influencing appropriateness of referrals included severity of disease, gender and insurance type, but not specialty of referring provider. CONCLUSIONS: Given the projection of a severe shortage of rheumatologists in the near future, innovative strategies to decrease demand for rheumatology services may prove more fruitful than increasing the supply of rheumatologists. Innovative strategies to decrease demand for rheumatology services may prove more fruitful than increasing the supply of rheumatologists. These findings may apply to other specialties as well. This study is relevant for health care systems that are implementing value-based payment models aimed at reducing inappropriate care.

Recurrence of Hallux Valgus After Modified Lapidus Procedure With Successful Fusion of the Intermetatarsal and Intercuneiform Joints.

Background The Lapidus procedure has become a popular procedure in correcting hallux valgus deformities and has undergone several modifications in an effort to improve the efficacy of the procedure. The senior author modifies this procedure with the addition of an intermetatarsal and intercuneiform fusion. Our hypothesis is that this will improve the procedure outcomes and decrease deformity recurrence. Methods We reviewed patient charts who underwent the procedure between 2014 and 2017 performed by the senior author. This yielded 47 reviewable cases, with 34 meeting study criteria. The cases were analyzed for standard hallux valgus measurements (intermetatarsal angle [IMA], hallux valgus angle [HVA]) and fusion on X-ray. Results The results of the study showed partial intermetatarsal and intercuneiform fusion failure in seven (20%) cases, and one case where the great toe fell into varus. These cases were excluded. In the remaining cases, there was a statistically significant improvement in the HVA and IMA between the preoperative X-ray and first postoperative X-ray. Additionally, there was no significant difference between HVA and IMA between first and final postoperative radiographs. There was a significant increase in IMA for the fusion failure cases (p=0.001). Conclusion Clinically, our findings demonstrate that successful union is possible with low recurrence and complication rates when using this modification of the Lapidus procedure in patients with hallux valgus deformity.

Wearables and Deep Learning Classify Fall Risk From Gait in Multiple Sclerosis.

Falls are a significant problem for persons with multiple sclerosis (PwMS). Yet fall prevention interventions are not often prescribed until after a fall has been reported to a healthcare provider. While still nascent, objective fall risk assessments could help in prescribing preventative interventions. To this end, retrospective fall status classification commonly serves as an intermediate step in developing prospective fall risk assessments. Previous research has identified measures of gait biomechanics that differ between PwMS who have fallen and those who have not, but these biomechanical indices have not yet been leveraged to detect PwMS who have fallen. Moreover, they require the use of laboratory-based measurement technologies, which prevent clinical deployment. Here we demonstrate that a bidirectional long short-term (BiLSTM) memory deep neural network was able to identify PwMS who have recently fallen with good performance (AUC of 0.88) based on accelerometer data recorded from two wearable sensors during a one-minute walking task. These results provide substantial improvements over machine learning models trained on spatiotemporal gait parameters (21% improvement in AUC), statistical features from the wearable sensor data (16%), and patient-reported (19%) and neurologist-administered (24%) measures in this sample. The success and simplicity (two wearable sensors, only one-minute of walking) of this approach indicates the promise of inexpensive wearable sensors for capturing fall risk in PwMS.

The Surprising Creativity of Digital Evolution: A Collection of Anecdotes from the Evolutionary Computation and Artificial Life Research Communities.

Evolution provides a creative fount of complex and subtle adaptations that often surprise the scientists who discover them. However, the creativity of evolution is not limited to the natural world: Artificial organisms evolving in computational environments have also elicited surprise and wonder from the researchers studying them. The process of evolution is an algorithmic process that transcends the substrate in which it occurs. Indeed, many researchers in the field of digital evolution can provide examples of how their evolving algorithms and organisms have creatively subverted their expectations or intentions, exposed unrecognized bugs in their code, produced unexpectedly adaptations, or engaged in behaviors and outcomes, uncannily convergent with ones found in nature. Such stories routinely reveal surprise and creativity by evolution in these digital worlds, but they rarely fit into the standard scientific narrative. Instead they are often treated as mere obstacles to be overcome, rather than results that warrant study in their own right. Bugs are fixed, experiments are refocused, and one-off surprises are collapsed into a single data point. The stories themselves are traded among researchers through oral tradition, but that mode of information transmission is inefficient and prone to error and outright loss. Moreover, the fact that these stories tend to be shared only among practitioners means that many natural scientists do not realize how interesting and lifelike digital organisms are and how natural their evolution can be. To our knowledge, no collection of such anecdotes has been published before. This article is the crowd-sourced product of researchers in the fields of artificial life and evolutionary computation who have provided first-hand accounts of such cases. It thus serves as a written, fact-checked collection of scientifically important and even entertaining stories. In doing so we also present here substantial evidence that the existence and importance of evolutionary surprises extends beyond the natural world, and may indeed be a universal property of all complex evolving systems.

Estimating Biomechanical Time-Series with Wearable Sensors: A Systematic Review of Machine Learning Techniques.

Wearable sensors have the potential to enable comprehensive patient characterization and optimized clinical intervention. Critical to realizing this vision is accurate estimation of biomechanical time-series in daily-life, including joint, segment, and muscle kinetics and kinematics, from wearable sensor data. The use of physical models for estimation of these quantities often requires many wearable devices making practical implementation more difficult. However, regression techniques may provide a viable alternative by allowing the use of a reduced number of sensors for estimating biomechanical time-series. Herein, we review 46 articles that used regression algorithms to estimate joint, segment, and muscle kinematics and kinetics. We present a high-level comparison of the many different techniques identified and discuss the implications of our findings concerning practical implementation and further improving estimation accuracy. In particular, we found that several studies report the incorporation of domain knowledge often yielded superior performance. Further, most models were trained on small datasets in which case nonparametric regression often performed best. No models were open-sourced, and most were subject-specific and not validated on impaired populations. Future research should focus on developing open-source algorithms using complementary physics-based and machine learning techniques that are validated in clinically impaired populations. This approach may further improve estimation performance and reduce barriers to clinical adoption.