Machine learning forecasting for COVID-19 pandemic-associated effects on paediatric respiratory infections.

OBJECTIVE: The COVID-19 pandemic and subsequent government restrictions have had a major impact on healthcare services and disease transmission, particularly those associated with acute respiratory infection. This study examined non-identifiable routine electronic patient record data from a specialist children's hospital in England, UK, examining the effect of pandemic mitigation measures on seasonal respiratory infection rates compared with forecasts based on open-source, transferable machine learning models. METHODS: We performed a retrospective longitudinal study of respiratory disorder diagnoses between January 2010 and February 2022. All diagnoses were extracted from routine healthcare activity data and diagnosis rates were calculated for several diagnosis groups. To study changes in diagnoses, seasonal forecast models were fit to prerestriction period data and extrapolated. RESULTS: Based on 144 704 diagnoses from 31 002 patients, all but two diagnosis groups saw a marked reduction in diagnosis rates during restrictions. We observed 91%, 89%, 72% and 63% reductions in peak diagnoses of 'respiratory syncytial virus', 'influenza', 'acute nasopharyngitis' and 'acute bronchiolitis', respectively. The machine learning predictive model calculated that total diagnoses were reduced by up to 73% (z-score: -26) versus expected during restrictions and increased by up to 27% (z-score: 8) postrestrictions. CONCLUSIONS: We demonstrate the association between COVID-19 related restrictions and significant reductions in paediatric seasonal respiratory infections. Moreover, while many infection rates have returned to expected levels postrestrictions, others remain supressed or followed atypical winter trends. This study further demonstrates the applicability and efficacy of routine electronic record data and cross-domain time-series forecasting to model, monitor, analyse and address clinically important issues.

Classification Performance of Neural Networks Versus Logistic Regression Models: Evidence From Healthcare Practice.

Machine learning encompasses statistical approaches such as logistic regression (LR) through to more computationally complex models such as neural networks (NN). The aim of this study is to review current published evidence for performance from studies directly comparing logistic regression, and neural network classification approaches in medicine. A literature review was carried out to identify primary research studies which provided information regarding comparative area under the curve (AUC) values for the overall performance of both LR and NN for a defined clinical healthcare-related problem. Following an initial search, articles were reviewed to remove those that did not meet the criteria and performance metrics were extracted from the included articles. Teh initial search revealed 114 articles; 21 studies were included in the study. In 13/21 (62%) of cases, NN had a greater AUC compared to LR, but in most the difference was small and unlikely to be of clinical significance; (unweighted mean difference in AUC 0.03 (95% CI 0-0.06) in favour of NN versus LR. In the majority of cases examined across a range of clinical settings, LR models provide reasonable performance that is only marginally improved using more complex methods such as NN. In many circumstances, the use of a relatively simple LR model is likely to be adequate for real-world needs but in specific circumstances in which large amounts of data are available, and where even small increases in performance would provide significant management value, the application of advanced analytic tools such as NNs may be indicated.

Accuracy and usability of AcuPebble SA100 for automated diagnosis of obstructive sleep apnoea in the home environment setting: an evaluation study.

OBJECTIVES: Obstructive sleep apnoea (OSA) is a heavily underdiagnosed condition, which can lead to significant multimorbidity. Underdiagnosis is often secondary to limitations in existing diagnostic methods. We conducted a diagnostic accuracy and usability study, to evaluate the efficacy of a novel, low-cost, small, wearable medical device, AcuPebble_SA100, for automated diagnosis of OSA in the home environment. SETTINGS: Patients were recruited to a standard OSA diagnostic pathway in an UK hospital. They were trained on the use of type-III-cardiorespiratory polygraphy, which they took to use at home. They were also given AcuPebble_SA100; but they were not trained on how to use it. PARTICIPANTS: 182 consecutive patients had been referred for OSA diagnosis in which 150 successfully completed the study. PRIMARY OUTCOME MEASURES: Efficacy of AcuPebble_SA100 for automated diagnosis of moderate-severe-OSA against cardiorespiratory polygraphy (sensitivity/specificity/likelihood ratios/predictive values) and validation of usability by patients themselves in their home environment. RESULTS: After returning the systems, two expert clinicians, blinded to AcuPebble_SA100's output, manually scored the cardiorespiratory polygraphy signals to reach a diagnosis. AcuPebble_SA100 generated automated diagnosis corresponding to four, typically followed, diagnostic criteria: Apnoea Hypopnoea Index (AHI) using 3% as criteria for oxygen desaturation; Oxygen Desaturation Index (ODI) for 3% and 4% desaturation criteria and AHI using 4% as desaturation criteria. In all cases, AcuPebble_SA100 matched the experts' diagnosis with positive and negative likelihood ratios over 10 and below 0.1, respectively. Comparing against the current American Academy of Sleep Medicine's AHI-based criteria demonstrated 95.33% accuracy (95% CI (90·62% to 98·10%)), 96.84% specificity (95% CI (91·05% to 99·34%)), 92.73% sensitivity (95% CI (82·41% to 97·98%)), 94.4% positive-predictive value (95% CI (84·78% to 98·11%)) and 95.83% negative-predictive value (95% CI (89·94% to 98·34%)). All patients used AcuPebble_SA100 correctly. Over 97% reported a strong preference for AcuPebble_SA100 over cardiorespiratory polygraphy. CONCLUSIONS: These results validate the efficacy of AcuPebble_SA100 as an automated diagnosis alternative to cardiorespiratory polygraphy; also demonstrating that AcuPebble_SA100 can be used by patients without requiring human training/assistance. This opens the doors for more efficient patient pathways for OSA diagnosis. TRIAL REGISTRATION NUMBER: NCT03544086; ClinicalTrials.gov.

Stereoscopic Near-Infrared Fluorescence Imaging: A Proof of Concept Toward Real-Time Depth Perception in Surgical Robotics.

The increasing use of surgical robotics has provoked the necessity for new medical imaging methods. Many assistive surgical robotic systems influence the surgeon's movements based on a model of constraints and boundaries driven by anatomy. This study aims to demonstrate that Near-Infrared Fluorescence (NIRF) imaging could be applied in surgical applications to provide subsurface mapping of capillaries beneath soft tissue as a method for imaging active constraints. The manufacture of a system for imaging in the near-infrared wavelength range is presented, followed by a description of computational methods for stereo-post-processing and data acquisition and testing used to demonstrate that the proposed methods are viable. The results demonstrate that it is possible to use NIRF for the imaging of a capillary submersed up to 11 mm below a soft tissue phantom, over a range of angles from 0° through 45°. Phantom depth has been measured to an accuracy of ±3 mm and phantom angle to a constant accuracy of ±1.6°. These findings suggest that NIRF could be used for the next generation of medical imaging in surgical robotics and provide a basis for future research into real-time depth perception in the mapping of active constraints.

TaiNi: Maximizing research output whilst improving animals' welfare in neurophysiology experiments.

Understanding brain function at the cell and circuit level requires representation of neuronal activity through multiple recording sites and at high sampling rates. Traditional tethered recording systems restrict movement and limit the environments suitable for testing, while existing wireless technology is still too heavy for extended recording in mice. Here we tested TaiNi, a novel ultra-lightweight (<2 g) low power wireless system allowing 72-hours of recording from 16 channels sampled at ~19.5 KHz (9.7 KHz bandwidth). We captured local field potentials and action-potentials while mice engaged in unrestricted behaviour in a variety of environments and while performing tasks. Data was synchronized to behaviour with sub-second precision. Comparisons with a state-of-the-art wireless system demonstrated a significant improvement in behaviour owing to reduced weight. Parallel recordings with a tethered system revealed similar spike detection and clustering. TaiNi represents a significant advance in both animal welfare in electrophysiological experiments, and the scope for continuously recording large amounts of data from small animals.

Automatic adventitious respiratory sound analysis: A systematic review.

BACKGROUND: Automatic detection or classification of adventitious sounds is useful to assist physicians in diagnosing or monitoring diseases such as asthma, Chronic Obstructive Pulmonary Disease (COPD), and pneumonia. While computerised respiratory sound analysis, specifically for the detection or classification of adventitious sounds, has recently been the focus of an increasing number of studies, a standardised approach and comparison has not been well established. OBJECTIVE: To provide a review of existing algorithms for the detection or classification of adventitious respiratory sounds. This systematic review provides a complete summary of methods used in the literature to give a baseline for future works. DATA SOURCES: A systematic review of English articles published between 1938 and 2016, searched using the Scopus (1938-2016) and IEEExplore (1984-2016) databases. Additional articles were further obtained by references listed in the articles found. Search terms included adventitious sound detection, adventitious sound classification, abnormal respiratory sound detection, abnormal respiratory sound classification, wheeze detection, wheeze classification, crackle detection, crackle classification, rhonchi detection, rhonchi classification, stridor detection, stridor classification, pleural rub detection, pleural rub classification, squawk detection, and squawk classification. STUDY SELECTION: Only articles were included that focused on adventitious sound detection or classification, based on respiratory sounds, with performance reported and sufficient information provided to be approximately repeated. DATA EXTRACTION: Investigators extracted data about the adventitious sound type analysed, approach and level of analysis, instrumentation or data source, location of sensor, amount of data obtained, data management, features, methods, and performance achieved. DATA SYNTHESIS: A total of 77 reports from the literature were included in this review. 55 (71.43%) of the studies focused on wheeze, 40 (51.95%) on crackle, 9 (11.69%) on stridor, 9 (11.69%) on rhonchi, and 18 (23.38%) on other sounds such as pleural rub, squawk, as well as the pathology. Instrumentation used to collect data included microphones, stethoscopes, and accelerometers. Several references obtained data from online repositories or book audio CD companions. Detection or classification methods used varied from empirically determined thresholds to more complex machine learning techniques. Performance reported in the surveyed works were converted to accuracy measures for data synthesis. LIMITATIONS: Direct comparison of the performance of surveyed works cannot be performed as the input data used by each was different. A standard validation method has not been established, resulting in different works using different methods and performance measure definitions. CONCLUSION: A review of the literature was performed to summarise different analysis approaches, features, and methods used for the analysis. The performance of recent studies showed a high agreement with conventional non-automatic identification. This suggests that automated adventitious sound detection or classification is a promising solution to overcome the limitations of conventional auscultation and to assist in the monitoring of relevant diseases.

An algorithm for automatic detection of drowsiness for use in wearable EEG systems.

Lack of proper restorative sleep can induce sleepiness at odd hours making a person drowsy. This onset of drowsiness can be detrimental for the individual in a number of ways if it happens at an unwanted time. For example, drowsiness while driving a vehicle or operating heavy machinery poses a threat to the safety and wellbeing of individuals as well as those around them. Timely detection of drowsiness can prevent the occurrence of unfortunate accidents thereby improving road and work environment safety. In this paper, by analyzing the electroencephalographic (EEG) signals of human subjects in the frequency domain, several features across different EEG channels are explored. Of these, three features are identified to have a strong correlation with drowsiness. A weighted sum of these defining features, extracted from a single EEG channel, is then used with a simple classifier to automatically separate the state of wakefulness from drowsiness. The proposed algorithm resulted in drowsiness detection sensitivity of 85% and specificity of 93%.

Low-complexity prediction of frequency-rich biosignals for lossless compression in wearable technologies.

Wearable technologies that store, monitor and analyse a range of biosignals are an area of significant growth and interest for both industry and academia. The rate of data generation in these devices poses a considerable challenge with regards to the bandwidths of wireless transmission protocols, local storage capacities and the on-board power consumption requirements. This issue is particularly acute for frequency-rich biosignals containing significant higher frequency components that are un-served by conventional compression techniques. This paper proposes a low-complexity predictor, based on a low-order infinite impulse response bandpass filter, to accurately predict such biosignals for use in lossless compression. Experimental evaluation of the method demonstrates that it outperforms conventional predictors with an average 25 % reduction in predictor residual standard deviation. The predictor described here enables high-bandwidth wearable sensors that can be employed in systems with reduced power consumption for transmission, storage and compression leading to considerable improvements in user experience by reducing device mass and increasing battery life.

Deformation invariant bounding spheres for dynamic active constraints in surgery.

Active constraints are collaborative robot control strategies, which can be used to guide a surgeon or protect delicate tissue structures during robot-assisted surgery. Tissue structures of interest often move and deform throughout a surgical intervention, and therefore, dynamic active constraints, which adapt and conform to these changes, are required. A fundamental element of an active constraint controller is the computation of the geometric relationship between the constraint geometry and the surgical instrument. For a static active constraint, there are a variety of computationally efficient methods for computing this relative configuration; however, for a dynamic active constraint, it becomes significantly more challenging. Deformation invariant bounding spheres are a novel bounding volume formulation, which can be used within a hierarchy to allow efficient proximity queries within dynamic active constraints. These bounding spheres are constructed in such a way that as the surface deforms, they do not require time-consuming rebuilds or updates, rather they are implicitly updated and continue to represent the underlying geometry as it changes. Experimental results show that performing proximity queries with deformation invariant bounding sphere hierarchies is faster than common methods from the literature when the deformation rate is within the range expected from conventional imaging systems.