IMUs Can Estimate Hip and Knee Range of Motion during Walking Tasks but Are Not Sensitive to Changes in Load or Grade

The ability to estimate lower-extremity mechanics in real-world scenarios may untether biomechanics research from a laboratory environment. This is particularly important for military populations where outdoor ruck marches over variable terrain and the addition of external load are cited as leading causes of musculoskeletal injury As such, this study aimed to examine (1) the validity of a minimal IMU sensor system for quantifying lower-extremity kinematics during treadmill walking and running compared with optical motion capture (OMC) and (2) the sensitivity of this IMU system to kinematic changes induced by load, grade, or a combination of the two. The IMU system was able to estimate hip and knee range of motion (ROM) with moderate accuracy during walking but not running. However, SPM analyses revealed IMU and OMC kinematic waveforms were significantly different at most gait phases. The IMU system was capable of detecting kinematic differences in knee kinematic waveforms that occur with added load but was not sensitive to changes in grade that influence lower-extremity kinematics when measured with OMC. While IMUs may be able to identify hip and knee ROM during gait, they are not suitable for replicating lab-level kinematic waveforms.

Using machine learning probabilities to identify effects of COVID-19

Coronavirus disease 2019 (COVID-19), the disease caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) virus, has had extensive economic, social, and public health impacts in the United States and around the world. To date, there have been more than 600 million reported infections worldwide with more than 6 million reported deaths. Retrospective analysis, which identified comorbidities, risk factors, and treatments, has underpinned the response. As the situation transitions to an endemic, retrospective analyses using electronic health records will be important to identify the long-term effects of COVID-19. However, these analyses can be complicated by incomplete records, which makes it difficult to differentiate visits where the patient had COVID-19. To address this issue, we trained a random Forest classifier to assign a probability of a patient having been diagnosed with COVID-19 during each visit. Using these probabilities, we found that higher COVID-19 probabilities were associated with a future diagnosis of myocardial infarction, urinary tract infection, acute renal failure, and type 2 diabetes.

An Actionable Expert-System Algorithm to Support Nurse-Led Cancer Survivorship Care: Algorithm Development Study

BACKGROUND

Comprehensive models of survivorship care are necessary to improve access to and coordination of care. New models of care provide the opportunity to address the complexity of physical and psychosocial problems and long-term health needs experienced by patients following cancer treatment.

OBJECTIVE

This paper presents our expert-informed, rules-based survivorship algorithm to build a nurse-led model of survivorship care to support men living with prostate cancer (PCa). The algorithm is called No Evidence of Disease (Ned) and supports timelier decision-making, enhanced safety, and continuity of care.

METHODS

An initial rule set was developed and refined through working groups with clinical experts across Canada (eg, nurse experts, physician experts, and scientists; n=20), and patient partners (n=3). Algorithm priorities were defined through a multidisciplinary consensus meeting with clinical nurse specialists, nurse scientists, nurse practitioners, urologic oncologists, urologists, and radiation oncologists (n=17). The system was refined and validated using the nominal group technique.

RESULTS

Four levels of alert classification were established, initiated by responses on the Expanded Prostate Cancer Index Composite for Clinical Practice survey, and mediated by changes in minimal clinically important different alert thresholds, alert history, and clinical urgency with patient autonomy influencing clinical acuity. Patient autonomy was supported through tailored education as a first line of response, and alert escalation depending on a patient-initiated request for a nurse consultation.

CONCLUSIONS

The Ned algorithm is positioned to facilitate PCa nurse-led care models with a high nurse-to-patient ratio. This novel expert-informed PCa survivorship care algorithm contains a defined escalation pathway for clinically urgent symptoms while honoring patient preference. Though further validation is required through a pragmatic trial, we anticipate the Ned algorithm will support timelier decision-making and enhance continuity of care through the automation of more frequent automated checkpoints, while empowering patients to self-manage their symptoms more effectively than standard care.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

RR2-10.1136/bmjopen-2020-045806.

A Minimal Sensor Inertial Measurement Unit System Is Replicable and Capable of Estimating Bilateral Lower-Limb Kinematics in a Stationary Bodyweight Squat and a Countermovement Jump

This study aimed to validate a 7-sensor inertial measurement unit system against optical motion capture to estimate bilateral lower-limb kinematics. Hip, knee, and ankle sagittal plane peak angles and range of motion (ROM) were compared during bodyweight squats and countermovement jumps in 18 participants. In the bodyweight squats, left peak hip flexion (intraclass correlation coefficient [ICC] = .51), knee extension (ICC = .68) and ankle plantar flexion (ICC = .55), and hip (ICC = .63) and knee (ICC = .52) ROM had moderate agreement, and right knee ROM had good agreement (ICC = .77). Relatively higher agreement was observed in the countermovement jumps compared to the bodyweight squats, moderate to good agreement in right peak knee flexion (ICC = .73), and right (ICC = .75) and left (ICC = .83) knee ROM. Moderate agreement was observed for right ankle plantar flexion (ICC = .63) and ROM (ICC = .51). Moderate agreement (ICC > .50) was observed in all variables in the left limb except hip extension, knee flexion, and dorsiflexion. In general, there was poor agreement for peak flexion angles, and at least moderate agreement for joint ROM. Future work will aim to optimize methodologies to increase usability and confidence in data interpretation by minimizing variance in system-based differences and may also benefit from expanding planes of movement.

State-of-the-Art Evidence Retriever for Precision Medicine: Algorithm Development and Validation

BACKGROUND

Under the paradigm of precision medicine (PM), patients with the same disease can receive different personalized therapies according to their clinical and genetic features. These therapies are determined by the totality of all available clinical evidence, including results from case reports, clinical trials, and systematic reviews. However, it is increasingly difficult for physicians to find such evidence from scientific publications, whose size is growing at an unprecedented pace.

OBJECTIVE

In this work, we propose the PM-Search system to facilitate the retrieval of clinical literature that contains critical evidence for or against giving specific therapies to certain cancer patients.

METHODS

The PM-Search system combines a baseline retriever that selects document candidates at a large scale and an evidence reranker that finely reorders the candidates based on their evidence quality. The baseline retriever uses query expansion and keyword matching with the ElasticSearch retrieval engine, and the evidence reranker fits pretrained language models to expert annotations that are derived from an active learning strategy.

RESULTS

The PM-Search system achieved the best performance in the retrieval of high-quality clinical evidence at the Text Retrieval Conference PM Track 2020, outperforming the second-ranking systems by large margins (0.4780 vs 0.4238 for standard normalized discounted cumulative gain at rank 30 and 0.4519 vs 0.4193 for exponential normalized discounted cumulative gain at rank 30).

CONCLUSIONS

We present PM-Search, a state-of-the-art search engine to assist the practicing of evidence-based PM. PM-Search uses a novel Bidirectional Encoder Representations from Transformers for Biomedical Text Mining-based active learning strategy that models evidence quality and improves the model performance. Our analyses show that evidence quality is a distinct aspect from general relevance, and specific modeling of evidence quality beyond general relevance is required for a PM search engine.

Sensor-based outcomes to monitor everyday life motor activities of children and adolescents with neuromotor impairments: A survey with health professionals

In combination with appropriate data processing algorithms, wearable inertial sensors enable the measurement of motor activities in children's and adolescents' habitual environments after rehabilitation. However, existing algorithms were predominantly designed for adult patients, and their outcomes might not be relevant for a pediatric population. In this study, we identified the needs of pediatric rehabilitation to create the basis for developing new algorithms that derive clinically relevant outcomes for children and adolescents with neuromotor impairments. We conducted an international survey with health professionals of pediatric neurorehabilitation centers, provided them a list of 34 outcome measures currently used in the literature, and asked them to rate the clinical relevance of these measures for a pediatric population. The survey was completed by 62 therapists, 16 doctors, and 9 nurses of 16 different pediatric neurorehabilitation centers from Switzerland, Germany, and Austria. They had an average work experience of 13 ± 10 years. The most relevant outcome measures were the duration of lying, sitting, and standing positions; the amount of active self-propulsion during wheeling periods; the hand use laterality; and the duration, distance, and speed of walking periods. The health profession, work experience, and workplace had a minimal impact on the priorities of health professionals. Eventually, we complemented the survey findings with the family priorities of a previous study to provide developers with the clinically most relevant outcomes to monitor everyday life motor activities of children and adolescents with neuromotor impairments.

A Data-Driven Algorithm to Recommend Initial Clinical Workup for Outpatient Specialty Referral: Algorithm Development and Validation Using Electronic Health Record Data and Expert Surveys

BACKGROUND

Millions of people have limited access to specialty care. The problem is exacerbated by ineffective specialty visits due to incomplete prereferral workup, leading to delays in diagnosis and treatment. Existing processes to guide prereferral diagnostic workup are labor-intensive (ie, building a consensus guideline between primary care doctors and specialists) and require the availability of the specialists (ie, electronic consultation).

OBJECTIVE

Using pediatric endocrinology as an example, we develop a recommender algorithm to anticipate patients' initial workup needs at the time of specialty referral and compare it to a reference benchmark using the most common workup orders. We also evaluate the clinical appropriateness of the algorithm recommendations.

METHODS

Electronic health record data were extracted from 3424 pediatric patients with new outpatient endocrinology referrals at an academic institution from 2015 to 2020. Using item co-occurrence statistics, we predicted the initial workup orders that would be entered by specialists and assessed the recommender's performance in a holdout data set based on what the specialists actually ordered. We surveyed endocrinologists to assess the clinical appropriateness of the predicted orders and to understand the initial workup process.

RESULTS

Specialists (n=12) indicated that <50% of new patient referrals arrive with complete initial workup for common referral reasons. The algorithm achieved an area under the receiver operating characteristic curve of 0.95 (95% CI 0.95-0.96). Compared to a reference benchmark using the most common orders, precision and recall improved from 37% to 48% (P<.001) and from 27% to 39% (P<.001) for the top 4 recommendations, respectively. The top 4 recommendations generated for common referral conditions (abnormal thyroid studies, obesity, amenorrhea) were considered clinically appropriate the majority of the time by specialists surveyed and practice guidelines reviewed.

CONCLUSIONS

 An item association-based recommender algorithm can predict appropriate specialists' workup orders with high discriminatory accuracy. This could support future clinical decision support tools to increase effectiveness and access to specialty referrals. Our study demonstrates important first steps toward a data-driven paradigm for outpatient specialty consultation with a tier of automated recommendations that proactively enable initial workup that would otherwise be delayed by awaiting an in-person visit.

A Large-Scale Open Motion Dataset (KFall) and Benchmark Algorithms for Detecting Pre-impact Fall of the Elderly Using Wearable Inertial Sensors

Research on pre-impact fall detection with wearable inertial sensors (detecting fall accidents prior to body-ground impacts) has grown rapidly in the past decade due to its great potential for developing an on-demand fall-related injury prevention system. However, most researchers use their own datasets to develop fall detection algorithms and rarely make these datasets publicly available, which poses a challenge to fairly evaluate the performance of different algorithms on a common basis. Even though some open datasets have been established recently, most of them are impractical for pre-impact fall detection due to the lack of temporal labels for fall time and limited types of motions. In order to overcome these limitations, in this study, we proposed and publicly provided a large-scale motion dataset called “KFall,” which was developed from 32 Korean participants while wearing an inertial sensor on the low back and performing 21 types of activities of daily living and 15 types of simulated falls. In addition, ready-to-use temporal labels of the fall time based on synchronized motion videos were published along with the dataset. Those enhancements make KFall the first public dataset suitable for pre-impact fall detection, not just for post-fall detection. Importantly, we have also developed three different types of latest algorithms (threshold based, support-vector machine, and deep learning), using the KFall dataset for pre-impact fall detection so that researchers and practitioners can flexibly choose the corresponding algorithm. Deep learning algorithm achieved both high overall accuracy and balanced sensitivity (99.32%) and specificity (99.01%) for pre-impact fall detection. Support vector machine also demonstrated a good performance with a sensitivity of 99.77% and specificity of 94.87%. However, the threshold-based algorithm showed relatively poor results, especially the specificity (83.43%) was much lower than the sensitivity (95.50%). The performance of these algorithms could be regarded as a benchmark for further development of better algorithms with this new dataset. This large-scale motion dataset and benchmark algorithms could provide researchers and practitioners with valuable data and references to develop new technologies and strategies for pre-impact fall detection and proactive injury prevention for the elderly.

Estimating the Burden of Alcohol on Ambulance Callouts through Development and Validation of an Algorithm Using Electronic Patient Records

BACKGROUND

Alcohol consumption places a significant burden on emergency services, including ambulance services, which often represent patients' first, and sometimes only, contact with health services. We aimed to (1) improve the assessment of this burden on ambulance services in Scotland using a low-cost and easy to implement algorithm to screen free-text in electronic patient record forms (ePRFs), and (2) present estimates on the burden of alcohol on ambulance callouts in Scotland.

METHODS

Two paramedics manually reviewed 5416 ePRFs to make a professional judgement of whether they were alcohol-related, establishing a gold standard for assessing our algorithm performance. They also extracted all words or phrases relating to alcohol. An automatic algorithm to identify alcohol-related callouts using free-text in EPRs was developed using these extracts.

RESULTS

Our algorithm had a specificity of 0.941 and a sensitivity of 0.996 in detecting alcohol-related callouts. Applying the algorithm to all callout records in Scotland in 2019, we identified 86,780 (16.2%) as alcohol-related. At weekends, this percentage was 18.5%.

CONCLUSIONS

Alcohol-related callouts constitute a significant burden on the Scottish Ambulance Service. Our algorithm is significantly more sensitive than previous methods used to identify alcohol-related ambulance callouts. This approach and the resulting data have potential for the evaluation of alcohol policy interventions as well as for conducting wider epidemiological research.

Quantifying upper limb tremor in people with multiple sclerosis using Fast Fourier Transform based analysis of wrist accelerometer signals

Introduction

Tremor is a disabling symptom of Multiple Sclerosis (MS). The development of objective methods of tremor characterisation to assess intervention efficacy and disease progression is therefore important. The possibility of using a Fast Fourier Transform (FFT) method for tremor detection was explored.

Methods

Acceleration from a wrist-worn device was analysed using FFTs to identify and characterise tremor magnitude and frequency. Processing parameters were explored to provide insight into the optimal algorithm. Participants wore a wrist tri-axial accelerometer during 9 tasks. The FAHN clinical assessment of tremor was used as the reference standard.

Results

Five people with MS and tremor (57.6 ± 15.3 years, 3 F/2M) and ten disease-free controls (42.4 ± 10.9 years, 5 M/5F) took part. Using specific algorithm settings tremor identification was possible (peak frequency 3–15Hz; magnitude greater than 0.06 g; 2 s windows with 50% overlap; using 2 of 3 axes of acceleration), giving sensitivity 0.974 and specificity 0.971 (38 tremor occurrences out of 108 tasks, 1 false positive, 2 false negatives). Tremor had frequency 3.5–13.0 Hz and amplitude 0.07–2.60g.

Conclusions

Upper limb tremor in people with MS can be detected using a FFT approach based on acceleration recorded at the wrist, demonstrating the possibility of using this minimally encumbering technique within clinical practice.

Exhaustive sampling of the fragment space associated to a molecule leading to the generation of conserved fragments

The first step in hit optimization is the identification of the pharmacophore, which is normally achieved by deconstruction of the hit molecule to generate "deletion analogues." In silico fragmentation approaches often focus on the generation of small fragments that do not describe properly the fragment space associated to the deletion analogues. We present significant modifications to the molecular fragmentation programme molBLOCKS, which allows the exhaustive sampling of the fragment space associated with a molecule to generate all possible molecular fragments. This generates larger fragments, by combining the smallest fragments. Additionally, it has been modified to deal with the problem of changing pharmacophoric properties through fragmentation, by highlighting bond cuts. The modified molBLOCKS programme was used on a set of drug compounds, where it generated more unique fragments than standard fragmentation approaches by increasing the number of fragments derived per compound. This fragment set was found to be more diverse than those generated by standard fragmentation programmes and was relevant to drug discovery as it contains the key fragments representing the pharmacophoric elements associated with ligand recognition. The use of dummy atoms to highlight bond cuts further increases the information content of fragments by visualizing their previous bonding pattern.

Remote Sensing of CDOM, CDOM Spectral Slope, and Dissolved Organic Carbon in the Global Ocean

A Global Ocean Carbon Algorithm Database (GOCAD) has been developed from over 500 oceanographic field campaigns conducted worldwide over the past 30 years including in situ reflectances and coincident satellite imagery, multi- and hyperspectral Chromophoric Dissolved Organic Matter (CDOM) absorption coefficients from 245–715 nm, CDOM spectral slopes in eight visible and ultraviolet wavebands, dissolved and particulate organic carbon (DOC and POC, respectively), and inherent optical, physical, and biogeochemical properties. From field optical and radiometric data and satellite measurements, several semi-analytical, empirical, and machine learning algorithms for retrieving global DOC, CDOM, and CDOM slope were developed, optimized for global retrieval, and validated. Global climatologies of satellite-retrieved CDOM absorption coefficient and spectral slope based on the most robust of these algorithms lag seasonal patterns of phytoplankton biomass belying Case 1 assumptions, and track terrestrial runoff on ocean basin scales. Variability in satellite retrievals of CDOM absorption and spectral slope anomalies are tightly coupled to changes in atmospheric and oceanographic conditions associated with El Niño Southern Oscillation (ENSO), strongly covary with the multivariate ENSO index in a large region of the tropical Pacific, and provide insights into the potential evolution and feedbacks related to sea surface dissolved carbon in a warming climate. Further validation of the DOC algorithm developed here is warranted to better characterize its limitations, particularly in mid-ocean gyres and the southern oceans.

Cy-preds: An algorithm and a web service for the analysis and prediction of cysteine reactivity

Cysteine (Cys) is a critically important amino acid, serving a variety of functions within proteins including structural roles, catalysis, and regulation of function through post-translational modifications. Predicting which Cys residues are likely to be reactive is a very sought after feature. Few methods are currently available for the task, either based on evaluation of physicochemical features (e.g., pKa and exposure) or based on similarity with known instances. In this study, we developed an algorithm (named HAL-Cy) which blends previous work with novel implementations to identify reactive Cys from nonreactive. HAL-Cy present two major components: (i) an energy based part, rooted on the evaluation of H-bond network contributions and (ii) a knowledge based part, composed of different profiling approaches (including a newly developed weighting matrix for sequence profiling). In our evaluations, HAL-Cy provided significantly improved performances, as tested in comparisons with existing approaches. We implemented our algorithm in a web service (Cy-preds), the ultimate product of our work; we provided it with a variety of additional features, tools, and options: Cy-preds is capable of performing fully automated calculations for a thorough analysis of Cys reactivity in proteins, ranging from reactivity predictions (e.g., with HAL-Cy) to functional characterization. We believe it represents an original, effective, and very useful addition to the current array of tools available to scientists involved in redox biology, Cys biochemistry, and structural bioinformatics.

An algorithm to predict the connectome of neural microcircuits

Experimentally mapping synaptic connections, in terms of the numbers and locations of their synapses and estimating connection probabilities, is still not a tractable task, even for small volumes of tissue. In fact, the six layers of the neocortex contain thousands of unique types of synaptic connections between the many different types of neurons, of which only a handful have been characterized experimentally. Here we present a theoretical framework and a data-driven algorithmic strategy to digitally reconstruct the complete synaptic connectivity between the different types of neurons in a small well-defined volume of tissue—the micro-scale connectome of a neural microcircuit. By enforcing a set of established principles of synaptic connectivity, and leveraging interdependencies between fundamental properties of neural microcircuits to constrain the reconstructed connectivity, the algorithm yields three parameters per connection type that predict the anatomy of all types of biologically viable synaptic connections. The predictions reproduce a spectrum of experimental data on synaptic connectivity not used by the algorithm. We conclude that an algorithmic approach to the connectome can serve as a tool to accelerate experimental mapping, indicating the minimal dataset required to make useful predictions, identifying the datasets required to improve their accuracy, testing the feasibility of experimental measurements, and making it possible to test hypotheses of synaptic connectivity.

Long-term evaluation of three satellite ocean color algorithms for identifying harmful algal blooms (Karenia brevis) along the west coast of Florida: A matchup assessment

We present a simple algorithm to identify Karenia brevis blooms in the Gulf of Mexico along the west coast of Florida in satellite imagery. It is based on an empirical analysis of collocated matchups of satellite and in situ measurements. The results of this Empirical Approach is compared to those of a Bio-optical Technique - taken from the published literature - and the Operational Method currently implemented by the NOAA Harmful Algal Bloom Forecasting System for K. brevis blooms. These three algorithms are evaluated using a multi-year MODIS data set (from July, 2002 to October, 2006) and a long-term in situ database. Matchup pairs, consisting of remotely-sensed ocean color parameters and near-coincident field measurements of K. brevis concentration, are used to assess the accuracy of the algorithms. Fair evaluation of the algorithms was only possible in the central west Florida shelf (i.e. between 25.75°N and 28.25°N) during the boreal Summer and Fall months (i.e. July to December) due to the availability of valid cloud-free matchups. Even though the predictive values of the three algorithms are similar, the statistical measure of success in red tide identification (defined as cell counts in excess of 1.5 × 10(4) cells L(-1)) varied considerably (sensitivity-Empirical: 86%; Bio-optical: 77%; Operational: 26%), as did their effectiveness in identifying non-bloom cases (specificity-Empirical: 53%; Bio-optical: 65%; Operational: 84%). As the Operational Method had an elevated frequency of false-negative cases (i.e. presented low accuracy in detecting known red tides), and because of the considerable overlap between the optical characteristics of the red tide and non-bloom population, only the other two algorithms underwent a procedure for further inspecting possible detection improvements. Both optimized versions of the Empirical and Bio-optical algorithms performed similarly, being equally specific and sensitive (~70% for both) and showing low levels of uncertainties (i.e. few cases of false-negatives and false-positives: ~30%)-improved positive predictive values (~60%) were also observed along with good negative predictive values (~80%).

Satellite remote sensing of harmful algal blooms: A new multi-algorithm method for detecting the Florida Red Tide (Karenia brevis)

In a continuing effort to develop suitable methods for the surveillance of Harmful Algal Blooms (HABs) of Karenia brevis using satellite radiometers, a new multi-algorithm method was developed to explore whether improvements in the remote sensing detection of the Florida Red Tide was possible. A Hybrid Scheme was introduced that sequentially applies the optimized versions of two pre-existing satellite-based algorithms: an Empirical Approach (using water-leaving radiance as a function of chlorophyll concentration) and a Bio-optical Technique (using particulate backscatter along with chlorophyll concentration). The long-term evaluation of the new multi-algorithm method was performed using a multi-year MODIS dataset (2002 to 2006; during the boreal Summer-Fall periods - July to December) along the Central West Florida Shelf between 25.75°N and 28.25°N. Algorithm validation was done with in situ measurements of the abundances of K. brevis; cell counts ≥1.5×10(4) cells l(-1) defined a detectable HAB. Encouraging statistical results were derived when either or both algorithms correctly flagged known samples. The majority of the valid match-ups were correctly identified (~80% of both HABs and non-blooming conditions) and few false negatives or false positives were produced (~20% of each). Additionally, most of the HAB-positive identifications in the satellite data were indeed HAB samples (positive predictive value: ~70%) and those classified as HAB-negative were almost all non-bloom cases (negative predictive value: ~86%). These results demonstrate an excellent detection capability, on average ~10% more accurate than the individual algorithms used separately. Thus, the new Hybrid Scheme could become a powerful tool for environmental monitoring of K. brevis blooms, with valuable consequences including leading to the more rapid and efficient use of ships to make in situ measurements of HABs.