Machine Learning Models for Parkinson Disease: Systematic Review.

Background: With the increasing availability of data, computing resources, and easier-to-use software libraries, machine learning (ML) is increasingly used in disease detection and prediction, including for Parkinson disease (PD). Despite the large number of studies published every year, very few ML systems have been adopted for real-world use. In particular, a lack of external validity may result in poor performance of these systems in clinical practice. Additional methodological issues in ML design and reporting can also hinder clinical adoption, even for applications that would benefit from such data-driven systems. Objective: To sample the current ML practices in PD applications, we conducted a systematic review of studies published in 2020 and 2021 that used ML models to diagnose PD or track PD progression. Methods: We conducted a systematic literature review in accordance with PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines in PubMed between January 2020 and April 2021, using the following exact string: "Parkinson's" AND ("ML" OR "prediction" OR "classification" OR "detection" or "artificial intelligence" OR "AI"). The search resulted in 1085 publications. After a search query and review, we found 113 publications that used ML for the classification or regression-based prediction of PD or PD-related symptoms. Results: Only 65.5% (74/113) of studies used a holdout test set to avoid potentially inflated accuracies, and approximately half (25/46, 54%) of the studies without a holdout test set did not state this as a potential concern. Surprisingly, 38.9% (44/113) of studies did not report on how or if models were tuned, and an additional 27.4% (31/113) used ad hoc model tuning, which is generally frowned upon in ML model optimization. Only 15% (17/113) of studies performed direct comparisons of results with other models, severely limiting the interpretation of results. Conclusions: This review highlights the notable limitations of current ML systems and techniques that may contribute to a gap between reported performance in research and the real-life applicability of ML models aiming to detect and predict diseases such as PD.

Creating an autoencoder single summary metric to assess gait quality to compare surgical outcomes in children with cerebral palsy: The Shriners Gait Index (SGI).

Gait for individuals with movement disorders varies widely and the variability makes it difficult to assess outcomes of surgical and therapeutic interventions. Although specific joints can be assessed by fewer individual measures, gait depends on multiple parameters making an overall assessment metric difficult to determine. A holistic, summary measure can permit a standard comparison of progress throughout treatments and interventions, and permit more straightforward comparison across varied subjects. We propose a single summary metric (the Shriners Gait Index (SGI)) to represent the quality of gait using a deep learning autoencoder model, which helps to capture the nonlinear statistical relationships among a number of disparate gait metrics. We utilized gait data of 412 individuals under the age of 18 collected from the Motion Analysis Center (MAC) at the Shriners Children's - Chicago. The gait data includes a total of 114 features: temporo-spatial parameters (7), lower extremity kinematics (64), and lower extremity kinetics (43) which were min-max normalized. The developed SGI score captured more than 89% variance of all 144 features using subject-wise cross-validation. Such summary metrics holistically quantify an individual's gait which can then be used to assess the impact of therapeutic interventions. The machine learning approach utilized can be leveraged to create such metrics in a variety of contexts depending on the data available. We also utilized the SGI to compare overall changes to gait after surgery with the goal of improving mobility for individuals with gait disabilities such as Cerebral Palsy.

AI-organoid integrated systems for biomedical studies and applications.

In this review, we explore the growing role of artificial intelligence (AI) in advancing the biomedical applications of human pluripotent stem cell (hPSC)-derived organoids. Stem cell-derived organoids, these miniature organ replicas, have become essential tools for disease modeling, drug discovery, and regenerative medicine. However, analyzing the vast and intricate datasets generated from these organoids can be inefficient and error-prone. AI techniques offer a promising solution to efficiently extract insights and make predictions from diverse data types generated from microscopy images, transcriptomics, metabolomics, and proteomics. This review offers a brief overview of organoid characterization and fundamental concepts in AI while focusing on a comprehensive exploration of AI applications in organoid-based disease modeling and drug evaluation. It provides insights into the future possibilities of AI in enhancing the quality control of organoid fabrication, label-free organoid recognition, and three-dimensional image reconstruction of complex organoid structures. This review presents the challenges and potential solutions in AI-organoid integration, focusing on the establishment of reliable AI model decision-making processes and the standardization of organoid research.

Feasibility of PROMIS using computerized adaptive testing during inpatient rehabilitation.

BACKGROUND: There has been an increased significance on patient-reported outcomes in clinical settings. We aimed to evaluate the feasibility of administering patient-reported outcome measures by computerized adaptive testing (CAT) using a tablet computer with rehabilitation inpatients, assess workload demands on staff, and estimate the extent to which rehabilitation inpatients have elevated T-scores on six Patient Reported Outcomes Measurement Information System® (PROMIS®) measures. METHODS: Patients (N = 108) with stroke, spinal cord injury, traumatic brain injury, and other neurological disorders participated in this study. PROMIS computerized adaptive tests (CAT) were administered via a web-based platform. Summary scores were calculated for six measures: Pain Interference, Sleep Disruption, Anxiety, Depression, Illness Impact Positive, and Illness Impact Negative. We calculated the percent of patients with T-scores equivalent to 2 standard deviations or greater above the mean. RESULTS: During the first phase, we collected data from 19 of 49 patients; of the remainder, 61% were not available or had cognitive or expressive language impairments. In the second phase of the study, 40 of 59 patients participated to complete the assessment. The mean PROMIS T-scores were in the low 50 s, indicating an average symptom level, but 19-31% of patients had elevated T-scores where the patients needed clinical action. CONCLUSIONS: The study demonstrated that PROMIS assessment using a CAT administration during an inpatient rehabilitation setting is feasible with the presence of a research staff member to complete PROMIS assessment.

A Low-Power Wireless System for Predicting Early Signs of Sudden Cardiac Arrest Incorporating an Optimized CNN Model Implemented on NVIDIA Jetson.

The survival rate for sudden cardiac arrest (SCA) is low, and patients with long-term risks of SCA are not adequately alerted. Understanding SCA's characteristics will be key to developing preventive strategies. Many lives could be saved if SCA's early onset could be detected or predicted. Monitoring heart signals continuously is essential for diagnosing sporadic cardiac dysfunction. An electrocardiogram (ECG) can be used to continuously monitor heart function without having to go to the hospital. A zeolite-based dry electrode can provide safe on-skin ECG acquisition while the subject is out-of-hospital and facilitate long-term monitoring. To the ECG signal, a low-power 1 µW read-out circuit was designed and implemented in our prior work. However, having long-term ECG monitoring outside the hospital, i.e., high battery life, and low power consumption while transmission and reception of ECG signal are crucial. This paper proposes a prototype with a 10-bit resolution ADC and nRF24L01 transceivers placed 5 m apart. The system uses the 2.4 GHz worldwide ISM frequency band with GFSK modulation to wirelessly transmit digitized ECG bits at 250 kbps data rate to a physician's computer (or similar) for continuous monitoring of ECG signals; the power consumption is only 11.2 mW and 4.62 mW during transmission and reception, respectively, with a low bit error rate of ≤0.1%. Additionally, a subject-wise cross-validated, three-fold, optimized convolutional neural network (CNN) model using the Physionet-SCA dataset was implemented on NVIDIA Jetson to identify the irregular heartbeats yielding an accuracy of 89% with a run time of 5.31 s. Normal beat classification has an F1 score of 0.94 and a ROC score of 0.886. Thus, this paper integrates the ECG acquisition and processing unit with low-power wireless transmission and CNN model to detect irregular heartbeats.

An LSTM-based Gesture-to-Speech Recognition System.

Fast and flexible communication options are limited for speech-impaired people. Hand gestures coupled with fast, generated speech can enable a more natural social dynamic for those individuals - particularly individuals without the fine motor skills to type on a keyboard or tablet reliably. We created a mobile phone application prototype that generates audible responses associated with trained hand movements and collects and organizes the accelerometer data for rapid training to allow tailored models for individuals who may not be able to perform standard movements such as sign language. Six participants performed 11 distinct gestures to produce the dataset. A mobile application was developed that integrated a bidirectional LSTM network architecture which was trained from this data. After evaluation using nested subject-wise cross-validation, our integrated bidirectional LSTM model demonstrates an overall recall of 91.8% in recognition of these pre-selected 11 hand gestures, with recall at 95.8% when two commonly confused gestures were not assessed. This prototype is a step in creating a mobile phone system capable of capturing new gestures and developing tailored gesture recognition models for individuals in speech-impaired populations. Further refinement of this prototype can enable fast and efficient communication with the goal of further improving social interaction for individuals unable to speak.

Autoencoder Composite Scoring to Evaluate Prosthetic Performance in Individuals with Lower Limb Amputation.

We created an overall assessment metric using a deep learning autoencoder to directly compare clinical outcomes in a comparison of lower limb amputees using two different prosthetic devices­a mechanical knee and a microprocessor-controlled knee. Eight clinical outcomes were distilled into a single metric using a seven-layer deep autoencoder, with the developed metric compared to similar results from principal component analysis (PCA). The proposed methods were used on data collected from ten participants with a dysvascular transfemoral amputation recruited for a prosthetics research study. This single summary metric permitted a cross-validated reconstruction of all eight scores, accounting for 83.29% of the variance. The derived score is also linked to the overall functional ability in this limited trial population, as improvements in each base clinical score led to increases in this developed metric. There was a highly significant increase in this autoencoder-based metric when the subjects used the microprocessor-controlled knee (p < 0.001, repeated measures ANOVA). A traditional PCA metric led to a similar interpretation but captured only 67.3% of the variance. The autoencoder composite score represents a single-valued, succinct summary that can be useful for the holistic assessment of highly variable, individual scores in limited clinical datasets.

Wearable airbag technology and machine learned models to mitigate falls after stroke.

BACKGROUND: Falls are a common complication experienced after a stroke and can cause serious detriments to physical health and social mobility, necessitating a dire need for intervention. Among recent advancements, wearable airbag technology has been designed to detect and mitigate fall impact. However, these devices have not been designed nor validated for the stroke population and thus, may inadequately detect falls in individuals with stroke-related motor impairments. To address this gap, we investigated whether population-specific training data and modeling parameters are required to pre-detect falls in a chronic stroke population. METHODS: We collected data from a wearable airbag's inertial measurement units (IMUs) from individuals with (n = 20 stroke) and without (n = 15 control) history of stroke while performing a series of falls (842 falls total) and non-falls (961 non-falls total) in a laboratory setting. A leave-one-subject-out crossvalidation was used to compare the performance of two identical machine learned models (adaptive boosting classifier) trained on cohort-dependent data (control or stroke) to pre-detect falls in the stroke cohort. RESULTS: The average performance of the model trained on stroke data (recall = 0.905, precision = 0.900) had statistically significantly better recall (P = 0.0035) than the model trained on control data (recall = 0.800, precision = 0.944), while precision was not statistically significantly different. Stratifying models trained on specific fall types revealed differences in pre-detecting anterior-posterior (AP) falls (stroke-trained model's F1-score was 35% higher, P = 0.019). Using activities of daily living as non-falls training data (compared to near-falls) significantly increased the AUC (Area under the receiver operating characteristic) for classifying AP falls for both models (P < 0.04). Preliminary analysis suggests that users with more severe stroke impairments benefit further from a stroke-trained model. The optimal lead time (time interval pre-impact to detect falls) differed between control- and stroke-trained models. CONCLUSIONS: These results demonstrate the importance of population sensitivity, non-falls data, and optimal lead time for machine learned pre-impact fall detection specific to stroke. Existing fall mitigation technologies should be challenged to include data of neurologically impaired individuals in model development to adequately detect falls in other high fall risk populations. Trial registration https://clinicaltrials.gov/ct2/show/NCT05076565 ; Unique Identifier: NCT05076565. Retrospectively registered on 13 October 2021.

Predicting UPDRS Motor Symptoms in Individuals With Parkinson's Disease From Force Plates Using Machine Learning.

Parkinson's disease (PD) is a neurodegenerative disease that affects motor abilities with increasing severity as the disease progresses. Traditional methods for diagnosing PD include a section where a trained specialist scores qualitative symptoms using the motor subscale of the Unified Parkinson's Disease Rating Scale (UPDRS-III). The aim of this feasibility study was twofold. First, to evaluate quiet standing as an additional, out-of-clinic, objective feature to predict UPDRS-III subscores related to motor symptom severity; and second, to use quiet standing to detect the presence of motor symptoms. Force plate data were collected from 42 PD patients and 43 healthy controls during quiet standing (a task involving standing still with eyes open and closed) as a feasible task in clinics. Predicting each subscore of the UPDRS-III could aid in identifying progression of PD and provide specialists additional tools to make an informed diagnosis. Random Forest feature importance indicated that features correlated with range of center of pressure (i.e., the medial-lateral and anterior-posterior sway) were most useful in the prediction of the top PD prediction subscores of postural stability (r = 0.599; p = 0.014), hand tremor of the left hand (r = 0.650; p = 0.015), and tremor at rest of the left upper extremity (r = 0.703; p = 0.016). Quiet standing can detect body bradykinesia (AUC-ROC = 0.924) and postural stability (AUC-ROC = 0.967) with high predictability. Although there are limited data, these results should be used as a feasibility study that evaluates the predictability of individual UPDRS-III subscores using quiet standing data.

Variable abnormality of the melanopsin-derived portion of the pupillary light reflex (PLR) in patients with Parkinson's disease (PD) and parkinsonism features.

OBJECTIVES: Ascertain and quantify abnormality of the melanopsin-derived portion of the pupillary light reflex (PLR) in patients with Parkinson's disease (PD) and parkinsonism features based on a statistical predictive modeling strategy for PLR classification. METHODS: Exploratory cohort analysis of pupillary kinetics in non-disease controls, PD subjects, and subjects with parkinsonism features using chromatic pupillometry. Receiver operating characteristic (ROC) curve interpretation of pupillary changes consistent with abnormality of intrinsically photosensitive retinal ganglion cells (ipRGCs) was employed using a thresholding algorithm to discriminate pupillary abnormality between study groups. RESULTS: Twenty-eight subjects were enrolled, including 17 PD subjects (age range 64-85, mean 70.65) and nine controls (age range 48-95, mean 63.89). Two subjects were described as demonstrating parkinsonism symptoms due to presumed Lewy body dementia and motor system atrophy (MSA) respectively. On aggregate analysis, PD subjects demonstrated abnormal but variable pupillary dynamics suggestive of ipRGC abnormality. Subjects with parkinsonism features did not demonstrate pupillary changes consistent with ipRGC abnormality. There was no relationship between levodopa equivalent dosage or PD severity and ipRGC abnormality. The pupillary test sensitivity in predicting PD was 0.75 and likelihood ratio was 1.2. CONCLUSIONS: ipRGC deficit is demonstrated in PD subjects; however, the degree and constancy of abnormality appear variable.

On the Role of LGN/V1 Spontaneous Activity as an Innate Learning Pattern for Visual Development.

Correlated, spontaneous neural activity is known to play a necessary role in visual development, but the higher-order statistical structure of these coherent, amorphous patterns has only begun to emerge in the past decade. Several computational studies have demonstrated how this endogenous activity can be used to train a developing visual system. Models that generate spontaneous activity analogous to retinal waves have shown that these waves can serve as stimuli for efficient coding models of V1. This general strategy in development has one clear advantage: The same learning algorithm can be used both before and after eye-opening. This same insight can be applied to understanding LGN/V1 spontaneous activity. Although lateral geniculate nucleus (LGN) activity has been less discussed in the literature than retinal waves, here we argue that the waves found in the LGN have a number of properties that fill the role of a training pattern. We make the case that the role of "innate learning" with spontaneous activity is not only possible, but likely in later stages of visual development, and worth pursuing further using an efficient coding paradigm.

A smartphone-based online system for fall detection with alert notifications and contextual information of real-life falls.

BACKGROUND: Falls are a leading cause of accidental deaths and injuries worldwide. The risk of falling is especially high for individuals suffering from balance impairments. Retrospective surveys and studies of simulated falling in lab conditions are frequently used and are informative, but prospective information about real-life falls remains sparse. Such data are essential to address fall risks and develop fall detection and alert systems. Here we present the results of a prospective study investigating a proof-of-concept, smartphone-based, online system for fall detection and notification. METHODS: The system uses the smartphone's accelerometer and gyroscope to monitor the participants' motion, and falls are detected using a regularized logistic regression. Data on falls and near-fall events (i.e., stumbles) is stored in a cloud server and fall-related variables are logged onto a web portal developed for data exploration, including the event time and weather, fall probability, and the faller's location and activity before the fall. RESULTS: In total, 23 individuals with an elevated risk of falling carried the phones for 2070 days in which the model classified 14,904,000 events. The system detected 27 of the 37 falls that occurred (sensitivity = 73.0 %) and resulted in one false alarm every 46 days (specificity > 99.9 %, precision = 37.5 %). 42.2 % of the events falsely classified as falls were validated as stumbles. CONCLUSIONS: The system's performance shows the potential of using smartphones for fall detection and notification in real-life. Apart from functioning as a practical fall monitoring instrument, this system may serve as a valuable research tool, enable future studies to scale their ability to capture fall-related data, and help researchers and clinicians to investigate real-falls.

Using a microprocessor knee (C-Leg) with appropriate foot transitioned individuals with dysvascular transfemoral amputations to higher performance levels: a longitudinal randomized clinical trial.

BACKGROUND: Individuals with transfemoral amputations who are considered to be limited community ambulators are classified as Medicare functional classification (MFCL) level K2. These individuals are usually prescribed a non-microprocessor controlled knee (NMPK) with an appropriate foot for simple walking functions. However, existing research suggests that these individuals can benefit from using a microprocessor controlled knee (MPK) and appropriate foot for their ambulation, but cannot obtain one due to insurance policy restrictions. With a steady increase in older adults with amputations due to vascular conditions, it is critical to evaluate whether advanced prostheses can provide better safety and performance capabilities to maintain and improve quality of life in individuals who are predominantly designated MFCL level K2. To decipher this we conducted a 13 month longitudinal clinical trial to determine the benefits of using a C-Leg and 1M10 foot in individuals at K2 level with transfemoral amputation due to vascular disease. This longitudinal clinical trial incorporated recommendations prescribed by the lower limb prosthesis workgroup to design a study that can add evidence to improve reimbursement policy through clinical outcomes using an MPK in K2 level individuals with transfemoral amputation who were using an NMPK for everyday use. METHODS: Ten individuals (mean age: 63 ± 9 years) with unilateral transfemoral amputation due to vascular conditions designated as MFCL K2 participated in this longitudinal crossover randomized clinical trial. Baseline outcomes were collected with their current prosthesis. Participants were then randomized to one of two groups, either an intervention with the MPK with a standardized 1M10 foot or their predicate NMPK with a standardized 1M10 foot. On completion of the first intervention, participants crossed over to the next group to complete the study. Each intervention lasted for 6 months (3 months of acclimation and 3 months of take-home trial to monitor home use). At the end of each intervention, clinical outcomes and self-reported outcomes were collected to compare with their baseline performance. A generalized linear model ANOVA was used to compare the performance of each intervention with respect to their own baseline. RESULTS: Statistically significant and clinically meaningful improvements were observed in gait performance, safety, and participant-reported measures when using the MPK C-Leg + 1M10 foot. Most participants were able to achieve higher clinical scores in gait speed, balance, self-reported mobility, and fall safety, while using the MPK + 1M10 combination. The improvement in scores were within range of scores achieved by individuals with K3 functional level as reported in previous studies. CONCLUSIONS: Individuals with transfemoral amputation from dysvascular conditions designated MFCL level K2 benefited from using an MPK + appropriate foot. The inference and evidence from this longitudinal clinical trial will add to the knowledgebase related to reimbursement policy-making. Trial registration This study is registered on clinical trials.gov with the study title "Functional outcomes in dysvascular transfemoral amputees" and the associated ClinicalTrials.gov Identifier: NCT01537211. The trial was retroactively registered on February 7, 2012 after the first participant was enrolled.

Detection of Parkinson's Disease Through Automated Pupil Tracking of the Post-illumination Pupillary Response.

Parkinson's disease (PD) is one of the most common neurodegenerative disorders, but it is often diagnosed after the majority of dopaminergic cells are already damaged. It is critical to develop biomarkers to identify the disease as early as possible for early intervention. PD patients appear to have an altered pupillary response consistent with an abnormality in photoreceptive retinal ganglion cells. Tracking the pupil size manually is a tedious process and offline automated systems can be prone to errors that may require intervention; for this reason in this work we describe a system for pupil size estimation with a user interface to allow rapid adjustment of parameters and extraction of pupil parameters of interest for the present study. We implemented a user-friendly system designed for clinicians to automate the process of tracking the pupil diameter to measure the post-illumination pupillary response (PIPR), permit manual corrections when needed, and continue automation after correction. Tracking was automated using a Kalman filter estimating the pupil center and diameter over time. The resulting system was tested on a PD classification task in which PD subjects are known to have similar responses for two wavelengths of light. The pupillary response is measured in the contralateral eye to two different light stimuli (470 and 610 nm) for 19 PD and 10 control subjects. The measured Net PIPR indicating different responsiveness to the wavelengths was 0.13 mm for PD subjects and 0.61 mm for control subjects, demonstrating a highly significant difference (p < 0.001). Net PIPR has the potential to be a biomarker for PD, suggesting further study to determine clinical validity.

Accelerometer-Based Automated Counting of Ten Exercises without Exercise-Specific Training or Tuning.

Measuring physical activity using wearable sensors is essential for quantifying adherence to exercise regiments in clinical research and motivating individuals to continue exercising. An important aspect of wearable activity tracking is counting particular movements. One limitation of many previous models is the need to design the counting for a specific exercise. However, during physical therapy, some movements are unique to the patient and also valuable to track. To address this, we create an automatic repetition counting system that is flexible enough to measure multiple distinct and repeating movements during physical therapy without being trained on the specific motion. Accelerometers, using smartphones, were attached to the body or held by participants to track repetitive motions during different exercises. 18 participants completed a series of 10 exercises for 30 seconds, including arm circles, bicep curls, bridges, sit-ups, elbow extensions, leg lifts, lunges, push-ups, squats, and upper trunk rotations. To count the repetitions of each exercise, we apply three analysis techniques: (a) threshold crossing, (b) threshold crossing with a low-pass filter, and (c) Fourier transform. The results demonstrate that arm circles and push-ups can be tracked well, while less periodic and irregular motions such as upper trunk rotations are more difficult. Overall, threshold crossing with low-pass filtering achieves the best performance among these methods. We conclude that the proposed automatic counting system is capable of tracking exercise repetition without prior training and development for that activity.

Hidden Markov model-based activity recognition for toddlers.

OBJECTIVE: Physical activity has been shown to impact future health outcomes in adults, but little is known about the long-term impact of physical activity in toddlers. Accurately measuring the specific types and amounts of physical activity in toddlers will help us to understand, predict, and better affect their future health outcomes. Although activity recognition has been extensively developed for adults as well as older children, toddlers move in ways that are significantly different from older children, indicating the need for a more tailored approach. APPROACH: In this study, 22 toddlers wore Actigraph waist-worn accelerometers which recorded their movements during guided play. The toddlers were videotaped and their activities were later annotated for the following eight distinct activity classes: lying down, being carried, riding in a stroller, sitting, standing, running/walking, crawling, and climbing up/down. Accelerometer data were extracted in 2 s signal windows and paired with the activities the toddlers were performing during that time interval. MAIN RESULTS: A variety of classifiers were tuned to a validation set. A random forest classifier was found to achieve the highest accuracy of 63.8% in a test set. To improve the accuracy, a hidden Markov model (HMM) was applied by providing the predictions of the static classifiers as observations. The HMM was able to improve the accuracy to 64.8% with all five classifiers increasing the accuracy an average of 1.3% points (95% confidence interval = 0.7-1.9, p  < 0.01). When the three most misclassified activities (sitting, standing, and riding in a stroller) were collapsed together, the accuracy increased to 79.3%. SIGNIFICANCE: Further refinement of the toddler activity recognition classifier will enable more accurate measurements of toddler activity and improve future health outcomes of toddlers.

Hip and Wrist-Worn Accelerometer Data Analysis for Toddler Activities.

Although accelerometry data are widely utilized to estimate physical activity and sedentary behavior among children age 3 years or older, for toddlers age 1 and 2 year(s), accelerometry data recorded during such behaviors have been far less examined. In particular, toddler's unique behaviors, such as riding in a stroller or being carried by an adult, have not yet been examined. The objective of this study was to describe accelerometry signal outputs recorded during participation in nine types of behaviors (i.e., running, walking, climbing up/down, crawling, riding a ride-on toy, standing, sitting, riding in a stroller/wagon, and being carried by an adult) among toddlers. Twenty-four toddlers aged 13 to 35 months (50% girls) performed various prescribed behaviors during free play in a commercial indoor playroom while wearing ActiGraph wGT3X-BT accelerometers on a hip and a wrist. Participants' performances were video-recorded. Based on the video data, accelerometer data were annotated with behavior labels to examine accelerometry signal outputs while performing the nine types of behaviors. Accelerometer data collected during 664 behavior assessments from the 21 participants were used for analysis. Hip vertical axis counts for walking were low (median = 49 counts/5 s). They were significantly lower than those recorded while a toddler was "carried" by an adult (median = 144 counts/5 s; p < 0.01). While standing, sitting, and riding in a stroller, very low hip vertical axis counts were registered (median ≤ 5 counts/5 s). Although wrist vertical axis and vector magnitude counts for "carried" were not higher than those for walking, they were higher than the cut-points for sedentary behaviors. Using various accelerometry signal features, machine learning techniques showed 89% accuracy to differentiate the "carried" behavior from ambulatory movements such as running, walking, crawling, and climbing. In conclusion, hip vertical axis counts alone may be unable to capture walking as physical activity and "carried" as sedentary behavior among toddlers. Machine learning techniques that utilize additional accelerometry signal features could help to recognize behavior types, especially to differentiate being "carried" from ambulatory movements.

Addendum of: Fall Detection in Individuals With Lower Limb Amputations Using Mobile Phones: Machine Learning Enhances Robustness for Real-World Applications.

[This corrects the article DOI: 10.2196/mhealth.8201.].

Fall Detection in Individuals With Lower Limb Amputations Using Mobile Phones: Machine Learning Enhances Robustness for Real-World Applications.

BACKGROUND: Automatically detecting falls with mobile phones provides an opportunity for rapid response to injuries and better knowledge of what precipitated the fall and its consequences. This is beneficial for populations that are prone to falling, such as people with lower limb amputations. Prior studies have focused on fall detection in able-bodied individuals using data from a laboratory setting. Such approaches may provide a limited ability to detect falls in amputees and in real-world scenarios. OBJECTIVE: The aim was to develop a classifier that uses data from able-bodied individuals to detect falls in individuals with a lower limb amputation, while they freely carry the mobile phone in different locations and during free-living. METHODS: We obtained 861 simulated indoor and outdoor falls from 10 young control (non-amputee) individuals and 6 individuals with a lower limb amputation. In addition, we recorded a broad database of activities of daily living, including data from three participants' free-living routines. Sensor readings (accelerometer and gyroscope) from a mobile phone were recorded as participants freely carried it in three common locations-on the waist, in a pocket, and in the hand. A set of 40 features were computed from the sensors data and four classifiers were trained and combined through stacking to detect falls. We compared the performance of two population-specific models, trained and tested on either able-bodied or amputee participants, with that of a model trained on able-bodied participants and tested on amputees. A simple threshold-based classifier was used to benchmark our machine-learning classifier. RESULTS: The accuracy of fall detection in amputees for a model trained on control individuals (sensitivity: mean 0.989, 1.96*standard error of the mean [SEM] 0.017; specificity: mean 0.968, SEM 0.025) was not statistically different (P=.69) from that of a model trained on the amputee population (sensitivity: mean 0.984, SEM 0.016; specificity: mean 0.965, SEM 0.022). Detection of falls in control individuals yielded similar results (sensitivity: mean 0.979, SEM 0.022; specificity: mean 0.991, SEM 0.012). A mean 2.2 (SD 1.7) false alarms per day were obtained when evaluating the model (vs mean 122.1, SD 166.1 based on thresholds) on data recorded as participants carried the phone during their daily routine for two or more days. Machine-learning classifiers outperformed the threshold-based one (P<.001). CONCLUSIONS: A mobile phone-based fall detection model can use data from non-amputee individuals to detect falls in individuals walking with a prosthesis. We successfully detected falls when the mobile phone was carried across multiple locations and without a predetermined orientation. Furthermore, the number of false alarms yielded by the model over a longer period of time was reasonably low. This moves the application of mobile phone-based fall detection systems closer to a real-world use case scenario.

In-lab versus at-home activity recognition in ambulatory subjects with incomplete spinal cord injury.

BACKGROUND: Although commercially available activity trackers can aid in tracking therapy and recovery of patients, most devices perform poorly for patients with irregular movement patterns. Standard machine learning techniques can be applied on recorded accelerometer signals in order to classify the activities of ambulatory subjects with incomplete spinal cord injury in a way that is specific to this population and the location of the recording-at home or in the clinic. METHODS: Subjects were instructed to perform a standardized set of movements while wearing a waist-worn accelerometer in the clinic and at-home. Activities included lying, sitting, standing, walking, wheeling, and stair climbing. Multiple classifiers and validation methods were used to quantify the ability of the machine learning techniques to distinguish the activities recorded in-lab or at-home. RESULTS: In the lab, classifiers trained and tested using within-subject cross-validation provided an accuracy of 91.6%. When the classifier was trained on data collected in the lab but tested on at home data, the accuracy fell to 54.6% indicating distinct movement patterns between locations. However, the accuracy of the at-home classifications, when training the classifier with at-home data, improved to 85.9%. CONCLUSION: Individuals with unique movement patterns can benefit from using tailored activity recognition algorithms easily implemented using modern machine learning methods on collected movement data.