Publications
119 results found
Joel Rivas J, Orihuela-Espina F, Enrique Sucar L, et al., 2019, Automatic recognition of multiple affective states in virtual rehabilitation by exploiting the dependency relationships, 8th International Conference on Affective Computing and Intelligent Interaction (ACII), Publisher: IEEE, Pages: 655-661, ISSN: 2156-8103
The automatic recognition of multiple affective states can be enhanced if the underpinning computational models explicitly consider the interactions between the states. This work proposes a computational model that incorporates the dependencies between four states (tiredness, anxiety, pain, and engagement)known to appear in virtual rehabilitation sessions of post-stroke patients, to improve the automatic recognition of the patients' states. A dataset of five stroke patients which includes their fingers' pressure (PRE), hand movements (MOV)and facial expressions (FAE)during ten sessions of virtual rehabilitation was used. Our computational proposal uses the Semi-Naive Bayesian classifier (SNBC)as base classifier in a multiresolution approach to create a multimodal model with the three sensors (PRE, MOV, and FAE)with late fusion using SNBC (FSNB classifier). There is a FSNB classifier for each state, and they are linked in a circular classifier chain (CCC)to exploit the dependency relationships between the states. Results of CCC are over 90% of ROC AUC for the four states. Relationships of mutual exclusion between engagement and all the other states and some co-occurrences between pain and anxiety for the five patients were detected. Virtual rehabilitation platforms that incorporate the automatic recognition of multiple patient's states could leverage intelligent and empathic interactions to promote adherence to rehabilitation exercises.
Modi HN, Singh H, Fiorentino F, et al., 2019, Association of residents' neural signatures with stress resilience during surgery, JAMA Surgery, Vol: 154, ISSN: 2168-6254
Importance: Intraoperative stressors may compound cognitive load, prompting performance decline and threatening patient safety. However, not all surgeons cope equally well with stress, and the disparity between performance stability and decline under high cognitive demand may be characterized by differences in activation within brain areas associated with attention and concentration such as the prefrontal cortex (PFC). Objective: To compare PFC activation between surgeons demonstrating stable performance under temporal stress with those exhibiting stress-related performance decline. Design, Setting, and Participants: Cohort study conducted from July 2015 to September 2016 at the Imperial College Healthcare National Health Service Trust, England. One hundred two surgical residents (postgraduate year 1 and greater) were invited to participate, of which 33 agreed to partake. Exposures: Participants performed a laparoscopic suturing task under 2 conditions: self-paced (SP; without time-per-knot restrictions), and time pressure (TP; 2-minute per knot time restriction). Main Outcomes and Measures: A composite deterioration score was computed based on between-condition differences in task performance metrics (task progression score [arbitrary units], error score [millimeters], leak volume [milliliters], and knot tensile strength [newtons]). Based on the composite score, quartiles were computed reflecting performance stability (quartile 1 [Q1]) and decline (quartile 4 [Q4]). Changes in PFC oxygenated hemoglobin concentration (HbO2) measured at 24 different locations using functional near-infrared spectroscopy were compared between Q1 and Q4. Secondary outcomes included subjective workload (Surgical Task Load Index) and heart rate. Results: Of the 33 participants, the median age was 33 years, the range was 29 to 56 years, and 27 were men (82%). The Q1 residents demonstrated task-induced increases in HbO2 across the bilateral ventrolateral PFC (VLPFC) and right dorsolateral P
Wu K, Farzam P, Sheriff F, et al., 2019, Monitoring cerebral blood flow and critical closing pressure in stroke patients, 29th International Symposium on Cerebral Blood Flow, Metabolism and Function / 14th International Conference on Quantification of Brain Function with PET (BRAIN and BRAIN Pet), Publisher: SAGE Publications, Pages: 258-258, ISSN: 0271-678X
Modi H, Singh H, Fiorentino F, et al., 2019, Neural signatures of resident resilience, JAMA Surgery, ISSN: 2168-6254
Importance: Intraoperative stressors may compound cognitive load, prompting performance decline and threatening patient safety. However, not all surgeons cope equally well with stress, and the disparity between performance stability and decline under high cognitive demand may be characterized by differences in activation within brain areas associated with attention and concentration such as the prefrontal cortex (PFC).Objective: To compare PFC activation between surgeons demonstrating stable performance under temporal stress with those exhibiting stress-related performance decline. The a priori hypothesis being that under temporal demand sustained prefrontal “activation(s)” reflect performance stability, whereas performance decline is manifest as “deactivation(s)”.Design: Cohort study conducted from July 2015 to September 2016. Setting: Single center (Imperial College Healthcare NHS Trust, United Kingdom). Participants: 102 surgical residents (PGY1 and above) were invited to participate, of which 33 agreed to partake (median age [range]: 33 [29-56] years, 27 [82%] males).Exposure: Subjects performed a laparoscopic suturing task under two conditions: ‘self-paced’ (SP; without time per knot restrictions), and ‘time pressure’ (TP; two-minute per knot time restriction). Main Outcomes and Measures: A composite deterioration score was computed based on between-condition differences in task performance metrics [(task progression score (au), error score (mm), leak volume (ml) and knot tensile strength (N)]. Based on the composite score, quartiles were computed reflecting performance stability (Q1) and decline (Q4). Changes in PFC oxygenated haemoglobin concentration (HbO2) measured at 24 different locations using functional near-infrared spectroscopy were compared between Q1 and Q4. Secondary outcomes included subjective workload (Surgical Task Load Index) and heart rate. Results: Q1 residents demonstrated task-induced incr
Joel Rivas J, Orihuela-Espina F, Enrique Sucar L, 2019, Recognition of affective states in virtual rehabilitation using late fusion with semi-naive Bayesian classifier, 13th EAI International Conference on Pervasive Computing Technologies for Healthcare (PervasiveHealth), Publisher: Association for Computing Machinery, Pages: 308-313, ISSN: 2153-1633
Virtual rehabilitation platforms may tailor the rehabilitation tasks to the patients' needs if they could recognize the patient's affective state. Affective states recognition systems can enhance their performance if they receive data coming from different sensors of human behaviour. In this work, we propose a late Fusion using Semi-Naive Bayesian classifier (FSNB) as a multimodal affective states recognition system to infer four states: tiredness, anxiety, pain, and motivation, from observable metrics of fingers pressure, hand movements, and facial expressions of post-stroke patients. Data streams were recorded from 5 post-stroke patients while they attended virtual rehabilitation therapies along 10 sessions over 4 weeks, manifesting the aforementioned states spontaneously. Recognition rates of the FSNB classifier were over 90% (with a standard deviation of around ± 0.06) of AUC for the four states. These results represent contributions for enhancing the development of affective states recognition systems in virtual rehabilitation.
Alejandro Hernandez-Contreras D, Peregrina-Barreto H, De Jesus Rangel-Magdaleno J, et al., 2019, Statistical approximation of plantar temperature distribution on diabetic subjects based on beta mixture model, IEEE Access, Vol: 7, Pages: 28383-28391, ISSN: 2169-3536
A change in plantar temperature distribution can be an indicator of tissue damage, inflammation, or peripheral vascular abnormalities associated with diabetic foot. Despite the efforts to detect these abnormalities through infrared thermography, there are still several problems to be addressed, especially to detect abnormalities on each foot separately. In this paper, a characterization of the plantar temperature distribution based on a probabilistic approach is proposed. The objective is to detect temperature variations on each foot eluding contralateral comparison. A beta mixture model with four components approximates the plantar temperature distributions of diabetic and non-diabetic subjects. Each component represents an area of the plantar region: toes; metatarsal heads; arch; and heel. The approximation was applied to 60 temperature distributions of non-diabetic subjects and 220 of diabetic subjects. The results suggest that it is possible to characterize distribution in terms of the mean of its beta components.
Lami M, Singh H, Dilley JH, et al., 2018, Gaze patterns hold key to unlocking successful search strategies and increasing polyp detection rate in colonoscopy, Endoscopy, Vol: 50, Pages: 701-707, ISSN: 1438-8812
BACKGROUND: The adenoma detection rate (ADR) is an important quality indicator in colonoscopy. The aim of this study was to evaluate the changes in visual gaze patterns (VGPs) with increasing polyp detection rate (PDR), a surrogate marker of ADR. METHODS: 18 endoscopists participated in the study. VGPs were measured using eye-tracking technology during the withdrawal phase of colonoscopy. VGPs were characterized using two analyses - screen and anatomy. Eye-tracking parameters were used to characterize performance, which was further substantiated using hidden Markov model (HMM) analysis. RESULTS: Subjects with higher PDRs spent more time viewing the outer ring of the 3 × 3 grid for both analyses (screen-based: r = 0.56, P = 0.02; anatomy: r = 0.62, P < 0.01). Fixation distribution to the "bottom U" of the screen in screen-based analysis was positively correlated with PDR (r = 0.62, P = 0.01). HMM demarcated the VGPs into three PDR groups. CONCLUSION: This study defined distinct VGPs that are associated with expert behavior. These data may allow introduction of visual gaze training within structured training programs, and have implications for adoption in higher-level assessment.
Montero-Hernandez S, Orihuela-Espina F, Enrique Sucar L, et al., 2018, Estimating functional connectivity symmetry between oxy- and deoxy-haemoglobin: implications for fNIRS connectivity analysis, Algorithms, Vol: 11, ISSN: 1999-4893
Functional Near InfraRed Spectroscopy (fNIRS) connectivity analysis is often performed using the measured oxy-haemoglobin (HbO2) signal, while the deoxy-haemoglobin (HHb) is largely ignored. The in-common information of the connectivity networks of both HbO2 and HHb is not regularly reported, or worse, assumed to be similar. Here we describe a methodology that allows the estimation of the symmetry between the functional connectivity (FC) networks of HbO2 and HHb and propose a differential symmetry index (DSI) indicative of the in-common physiological information. Our hypothesis is that the symmetry between FC networks associated with HbO2 and HHb is above what should be expected from random networks. FC analysis was done in fNIRS data collected from six freely-moving healthy volunteers over 16 locations on the prefrontal cortex during a real-world task in an out-of-the-lab environment. In addition, systemic data including breathing rate (BR) and heart rate (HR) were also synchronously collected and used within the FC analysis. FC networks for HbO2 and HHb were established independently using a Bayesian networks analysis. The DSI between both haemoglobin (Hb) networks with and without systemic influence was calculated. The relationship between the symmetry of HbO2 and HHb networks, including the segregational and integrational characteristics of the networks (modularity and global efficiency respectively) were further described. Consideration of systemic information increases the path lengths of the connectivity networks by 3%. Sparse networks exhibited higher asymmetry than dense networks. Importantly, our experimental connectivity networks symmetry between HbO2 and HHb departs from random (t-test: t(509) = 26.39, p < 0.0001). The DSI distribution suggests a threshold of 0.2 to decide whether both HbO2 and HHb FC networks ought to be studied. For sparse FC networks, analysis of both haemoglobin species is strongly recommended. Our DSI can provide a quantifiable g
Herrera-Vega J, Orihuela-Espina F, Ibarguengoytia PH, et al., 2018, A local multiscale probabilistic graphical model for data validation and reconstruction, and its application in industry, Engineering Applications of Artificial Intelligence, Vol: 70, Pages: 1-15, ISSN: 0952-1976
The detection and subsequent reconstruction of incongruent data in time series by means of observation of statistically related information is a recurrent issue in data validation. Unlike outliers, incongruent observations are not necessarily confined to the extremes of the data distribution. Instead, these rogue observations are unlikely values in the light of statistically related information. This paper proposes a multiresolution Bayesian network model for the detection of rogue values and posterior reconstruction of the erroneous sample for non-stationary time-series. Our method builds local Bayesian Network models that best fit to segments of data in order to achieve a finer discretization and hence improve data reconstruction. Our local multiscale approach is compared against its single-scale global predecessor (assumed as our gold standard) in the predictive power and of this, both error detection capabilities and error reconstruction capabilities are assessed. This parameterization and verification of the model are evaluated over three synthetic data source topologies. The virtues of the algorithm are then further tested in real data from the steel industry where the aforementioned problem characteristics are met but for which the ground truth is unknown. The proposed local multiscale approach was found to dealt better with increasing complexities in data topologies.
Orihuela-Espina F, Sucar LE, 2018, Adaptation and customization in virtual rehabilitation, Virtual and Augmented Reality: Concepts, Methodologies, Tools, and Applications, Pages: 826-849, ISBN: 9781522554691
Background. Adaptation and customization are two related but distinct concepts that are central to virtual rehabilitation if this motor therapy modality is to succeed in alleviating the demand for expert supervision. These two elements of the therapy are required to exploit the flexibility of virtual environments to enhance motor training and boost therapy outcome. Aim. The chapter provides a non-systematic overview of the state of the art regarding the evolving manipulation of virtual rehabilitation environments to optimize therapy outcome manifested through customization and adaptation mechanisms. Methods. Both concepts will be defined, aspects guiding their implementation reviewed, and available literature suggesting different solutions discussed. We present "Gesture Therapy", a platform realizing our contributions to the field and we present results of the adaptation techniques integrated into it. Less explored additional dimensions such as liability and privacy issues affecting their implementation are briefly discussed. Results. Solutions to implement decision-making on how to manipulate the environment are varied. They range from predefined system configurations to sophisticated artificial intelligence (AI) models. Challenge maintenance and feedback personalization is the most common driving force for their incorporation to virtual rehabilitation platforms. Conclusions. Customization and adaptation are the main mechanisms responsible for the full exploitation of the potential of virtual rehabilitation environments, and the potential benefits are worth pursuing. Despite encouraging evidence of the many solutions proposed thus far in literature, none has yet proven to substantially alter the therapy outcome. In consequence, research is still on going to equip virtual rehabilitation solutions with efficacious tailoring elements.
Soto-Perez de Celis E, Abraham Baez-Bagattela J, Lira-Huerta E, et al., 2018, Sensor-based mobile system for the promotion and real-time monitoring of physical activity, Salud Pública de Mexico, Vol: 60, Pages: 119-120, ISSN: 0036-3634
Joel Rivas J, Palafox L, Hernandez-Franco J, et al., 2018, Automatic Recognition of Pain, Anxiety, Engagement and Tiredness for Virtual Rehabilitation from Stroke: A Marginalization Approach, 7th International Conference on Affective Computing and Intelligent Interaction Workshops and Demos (ACIIW), Publisher: IEEE, Pages: 159-164, ISSN: 2156-8103
Virtual rehabilitation taps affective computing to personalize therapy. States of anxiety, pain and engagement (affective) and tiredness (physical or psychological) were studied to be inferable from metrics of 3D hand location-proxy of hand movement- and fingers' pressure relevant for upper limb motor recovery. Features from the data streams characterized the motor dynamics of 2 stroke patients attending 10 sessions of motor virtual rehabilitation. Experts tagged states manifestations from videos. We aid classification contributing with a marginalization mechanism whereby absent input is reconstructed. With the hand movement information absent, marginalization statistically outperformed a base model where such input is ignored. Marginalized classification performance was (Area below ROC curve: μ ± σ) 0.880 ± 0.173 and 0.738 ± 0.177 for each patient. Marginalization aid classification sustaining performance under input failure or permitting different sensing settings.
Montero-Hernandez S, Orihuela-Espina F, Sucar LE, 2018, Intervals of Causal Effects for Learning Causal Graphical Models, Pages: 296-307
Structure learning algorithms aim to retrieve the true causal structure from a set of observations. Most times only an equivalence class can be recovered and a unique model cannot be singled out. We hypothesized that casual directions could be inferred from the assessment of the strength of potential causal effects and such assessment can be computed by intervals comparison strategies. We introduce SLICE (Structural Learning with Intervals of Causal Effects), a new algorithm to decide on unresolved relations, which taps on the computation of causal effects and an acceptability index; a strategy for intervals comparison. For validation purposes, synthetic datasets were generated varying the graph size and density with samples drawn from Gaussian and non-Gaussian distributions. Comparison against LiNGAM is made to establish the performance of SLICE over 1440 scenarios using the normalised structural Hamming distance (SHD). The retrieved structures with SLICE showed smaller SHD values in the Gaussian case, improving the structure of the retrieved causal model in terms of correctly found directions. The acceptability index is a good predictor of the true causal effects (R2 = 0.62). The proposed strategy represents a new tool for discovering unravelled causal relations in the presence of observational data only.
Rivas JJ, Orihuela-Espina F, Sucar LE, 2018, Circular Chain Classifiers, Pages: 392-403
Chain Classifiers (CC) are an alternative for multi-label classification that is efficient and provides, in general, good results. However, it is not clear how to define the order of the chain. Different orders tend to produce different outcomes. We propose an extension to chain classifiers called “Circular Chain Classifiers” (CCC), in which the propagation of the classes of the previous binary classifiers is done iteratively in a circular way. After the first cycle, the predictions from the base classifiers are entered as additional attributes to the first one in the chain. This process continues for all the classifiers in the chain, and it is repeated for a prefixed number of cycles or until convergence. Using two datasets, we empirically established that CCC: (i) converges in few iterations (in general, 3 or 4), (ii) the initial order of the chain does not have a significant impact on the results. CCC performance was also compared against binary relevance and chain classifiers producing statistically superior results. The main contribution of CCC is its independence from the preestablished order of the chain, outperforming CC.
Orihuela-Espina F, Leff DR, James DRC, et al., 2018, Imperial College near infrared spectroscopy neuroimaging analysis framework., Neurophotonics, Vol: 5, ISSN: 2329-423X
This paper describes the Imperial College near infrared spectroscopy neuroimaging analysis (ICNNA) software tool for functional near infrared spectroscopy neuroimaging data. ICNNA is a MATLAB-based object-oriented framework encompassing an application programming interface and a graphical user interface. ICNNA incorporates reconstruction based on the modified Beer-Lambert law and basic processing and data validation capabilities. Emphasis is placed on the full experiment rather than individual neuroimages as the central element of analysis. The software offers three types of analyses including classical statistical methods based on comparison of changes in relative concentrations of hemoglobin between the task and baseline periods, graph theory-based metrics of connectivity and, distinctively, an analysis approach based on manifold embedding. This paper presents the different capabilities of ICNNA in its current version.
Herrera-Vega J, Montero-Hernandez S, Tachtsidis I, et al., 2017, Modelling and validation of diffuse reflectance of the adult human head for fNIRS: scalp sub-layers definition, 13th International Conference on Medical Information Processing and Analysis, Publisher: Society of Photo-Optical Instrumentation Engineers (SPIE), ISSN: 0277-786X
Accurate estimation of brain haemodynamics parameters such as cerebral blood flow and volume as well as oxygen consumption i.e. metabolic rate of oxygen, with funcional near infrared spectroscopy (fNIRS) requires precise characterization of light propagation through head tissues. An anatomically realistic forward model of the human adult head with unprecedented detailed specification of the 5 scalp sublayers to account for blood irrigation in the connective tissue layer is introduced. The full model consists of 9 layers, accounts for optical properties ranging from 750nm to 950nm and has a voxel size of 0.5mm. The whole model is validated comparing the predicted remitted spectra, using Monte Carlo simulations of radiation propagation with 108 photons, against continuous wave (CW) broadband fNIRS experimental data. As the true oxy- and deoxy-hemoglobin concentrations during acquisition are unknown, a genetic algorithm searched for the vector of parameters that generates a modelled spectrum that optimally fits the experimental spectrum. Differences between experimental and model predicted spectra was quantified using the Root mean square error (RMSE). RMSE was 0.071 ± 0.004, 0.108 ± 0.018 and 0.235±0.015 at 1, 2 and 3cm interoptode distance respectively. The parameter vector of absolute concentrations of haemoglobin species in scalp and cortex retrieved with the genetic algorithm was within histologically plausible ranges. The new model capability to estimate the contribution of the scalp blood flow shall permit incorporating this information to the regularization of the inverse problem for a cleaner reconstruction of brain hemodynamics.
Heyer P, Castrejon LR, Orihuela-Espina F, et al., 2017, Automation of motor dexterity assessment, International Conference on Rehabilitation Robotics (ICORR), Publisher: IEEE, Pages: 521-526, ISSN: 1945-7898
Motor dexterity assessment is regularly performed in rehabilitation wards to establish patient status and automatization for such routinary task is sought. A system for automatizing the assessment of motor dexterity based on the Fugl-Meyer scale and with loose restrictions on sensing technologies is presented. The system consists of two main elements: 1) A data representation that abstracts the low level information obtained from a variety of sensors, into a highly separable low dimensionality encoding employing t-distributed Stochastic Neighbourhood Embedding, and, 2) central to this communication, a multi-label classifier that boosts classification rates by exploiting the fact that the classes corresponding to the individual exercises are naturally organized as a network. Depending on the targeted therapeutic movement class labels i.e. exercises scores, are highly correlated-patients who perform well in one, tends to perform well in related exercises-; and critically no node can be used as proxy of others - an exercise does not encode the information of other exercises. Over data from a cohort of 20 patients, the novel classifier outperforms classical Naive Bayes, random forest and variants of support vector machines (ANOVA: p <; 0.001). The novel multi-label classification strategy fulfills an automatic system for motor dexterity assessment, with implications for lessening therapist's workloads, reducing healthcare costs and providing support for home-based virtual rehabilitation and telerehabilitation alternatives.
Hernandez-Contreras D, Peregrina-Barreto H, Rangel-Magdaleno J, et al., 2017, Measuring changes in the plantar temperature distribution in diabetic patients, IEEE International Instrumentation and Measurement Technology Conference (I2MTC), Publisher: IEEE, Pages: 272-277, ISSN: 1091-5281
Temperature distribution in the sole is an indicator of peripheral vascular abnormalities associated with the diabetic foot. This paper presents a criterion to identify changes in the plantar temperature distribution that can be related to diabetic foot complications. This criterion, based on Kullback-Leibler and Jensen-Shannon divergences, allows identification of changes in the plantar temperature distribution by comparing the samples with a reference distribution from healthy subjects. A 82% of 200 samples of diabetic patients presented a significant change in the temperature distribution which can be a precursor of any complication. These results suggest that with this method, it is possible to detect changes in the plantar temperature distribution. Potentially, this method can be exploited for medical diagnostic support.
Herrera-Vega J, Treviño-Palacios CG, Orihuela-Espina F, 2017, Neuroimaging with functional near infrared spectroscopy: From formation to interpretation, Infrared Physics and Technology, Vol: 85, Pages: 225-237, ISSN: 1350-4495
Functional Near Infrared Spectroscopy (fNIRS) is gaining momentum as a functional neuroimaging modality to investigate the cerebral hemodynamics subsequent to neural metabolism. As other neuroimaging modalities, it is neuroscience's tool to understand brain systems functions at behaviour and cognitive levels. To extract useful knowledge from functional neuroimages it is critical to understand the series of transformations applied during the process of the information retrieval and how they bound the interpretation. This process starts with the irradiation of the head tissues with infrared light to obtain the raw neuroimage and proceeds with computational and statistical analysis revealing hidden associations between pixels intensities and neural activity encoded to end up with the explanation of some particular aspect regarding brain function.To comprehend the overall process involved in fNIRS there is extensive literature addressing each individual step separately. This paper overviews the complete transformation sequence through image formation, reconstruction and analysis to provide an insight of the final functional interpretation.
Modi HN, SIngh H, Orihuela-Espina F, et al., 2017, Temporal stress in the operating room: brain engagement promotes "coping" and disengagement prompts "choking", Annals of Surgery, Vol: 267, Pages: 683-691, ISSN: 1528-1140
Objective:To investigate the impact of time pressure (TP) on prefrontalactivation and technical performance in surgical residents during a laparo-scopic suturing task.Background:Neural mechanisms enabling surgeons to maintain perform-ance and cope with operative stressors are unclear. The prefrontal cortex(PFC) is implicated due to its role in attention, concentration, and perform-ance monitoring.Methods:A total of 33 residents [Postgraduate Year (PGY)1 – 2¼15,PGY3– 4¼8, and PGY5¼10] performed a laparoscopic suturing taskunder ‘‘self-paced’’ (SP) and ‘‘TP’’ conditions (TP¼maximum 2 minutes perknot). Subjective workload was quantified using the Surgical Task LoadIndex. PFC activation was inferred using optical neuroimaging. Technicalskill was assessed using progression scores (au), error scores (mm), leakvolumes (mL), and knot tensile strengths (N).Results:TP led to greater perceived workload amongst all residents (meanSurgical Task Load Index score SD: PGY1 – 2: SP¼160.3 24.8 vs TP¼202.1 45.4,P<0.001; PGY3 – 4: SP¼123.0 52.0 vs TP¼172.5 43.1,P<0.01; PGY5: SP¼105.8 55.3 vs TP¼159.1 63.1,P<0.05).Amongst PGY1– 2 and PGY3– 4, deterioration in task progression, errorscores and knot tensile strength (P<0.05), and diminished PFC activationwas observed under TP. In PGY5, TP resulted in inferior task progression anderror scores (P<0.05), but preservation of knot tensile strength. Furthermore,PGY5 exhibited less attenuation of PFC activation under TP, and greateractivation than either PGY1 – 2 or PGY3 – 4 under both experimental con-ditions (P<0.05).Conclusions:Senior residents cope better with temporal demands and exhibitgreater technical performance stability under pressure, possibly due to
Leff DR, Yongue G, Vlaev I, et al., 2017, "Contemplating the next maneuver": functional neuroimaging reveals intraoperative decision-making strategies, Annals of Surgery, Vol: 265, Pages: 320-330, ISSN: 1528-1140
OBJECTIVE: To investigate differences in the quality, confidence, and consistency of intraoperative surgical decision making (DM) and using functional neuroimaging expose decision systems that operators use. SUMMARY BACKGROUND DATA: Novices are hypothesized to use conscious analysis (effortful DM) leading to activation across the dorsolateral prefrontal cortex, whereas experts are expected to use unconscious automation (habitual DM) in which decisions are recognition-primed and prefrontal cortex independent. METHODS: A total of 22 subjects (10 medical student novices, 7 residents, and 5 attendings) reviewed simulated laparoscopic cholecystectomy videos, determined the next safest operative maneuver upon video termination (10 s), and reported decision confidence. Video paradigms either declared ("primed") or withheld ("unprimed") the next operative maneuver. Simultaneously, changes in cortical oxygenated hemoglobin and deoxygenated hemoglobin inferring prefrontal activation were recorded using Optical Topography. Decision confidence, consistency (primed vs unprimed), and quality (script concordance) were assessed. RESULTS: Attendings and residents were significantly more certain (P < 0.001), and decision quality was superior (script concordance: attendings = 90%, residents = 78.3%, and novices = 53.3%). Decision consistency was significantly superior in experts (P < 0.001) and residents (P < 0.05) than novices (P = 0.183). During unprimed DM, novices showed significant activation of the dorsolateral prefrontal cortex, whereas this activation pattern was not observed among residents and attendings. During primed DM, significant activation was not observed in any group. CONCLUSIONS: Expert DM is characterized by improved quality, consistency, and confidence. The findings imply attendings use a habitual decision system, whereas novices use an effortful approach under uncertainty. In the presence of operative cues (primes), novices disengage
Morales-Vargas E, Reyes-García CA, Peregrina-Barreto H, et al., 2017, Facial expression recognition with fuzzy explainable models, Pages: 51-54
The performance of current algorithms of facial expressions recognition are still insufficient for certain applications such as facial rehabilitation. We aim at alleviating some current limitations of these algorithms by exploiting explainable fuzzy models over sequences of frontal face images. In this work, facial expressions are characterized in terms of action units. Fuzzy models maintain a semantic relation between the facial muscle appearance and the fuzzily associated facial expression. First, heuristic guided affine transformations align facial landmarks of the neutral and target expression. Second, features are extracted describing face movements in terms of changes in orientation (angle and magnitude) of distinctive facial areas. Third, the full featured representation is embedded into a compact one by means of pooling. Finally, a Sugeno-type adaptive neuro fuzzy inference system is used for each action unit to generate a description of the movements in the face that identifies the facial expression present in an image sequence. The proposed model discriminates facial expressions with mean accuracy of 89.04±0.91% with a maximum accuracy of 91.41±28%. Further, distinctly to current solutions the model can also describe why is reaching such decision. The current solution brings application in facial rehabilitation a step closer.
Heyer P, Orihuela-Espina F, Castrejon LR, et al., 2017, Sensor Abstracted Extremity Representation for Automatic Fugl-Meyer Assessment, International 360 Degree Summit on Applications for Future Internet (AFI360), Publisher: SPRINGER INTERNATIONAL PUBLISHING AG, Pages: 152-163, ISSN: 1867-8211
Orihuela-Espina F, Roldán GF, Sánchez Villavicencio I, et al., 2016, Response to “Letter to the editor: Robot training for hand motor recovery in subacute stroke patients: A randomized controlled trial”, Journal of Hand Therapy, Vol: 29, Pages: e13-e14, ISSN: 0894-1130
Modi HN, Singh H, Orihuela-Espina F, et al., 2016, Cortical haemodynamic changes associated with high and low cognitive demand in surgeons, 22nd Annual Meeting of the Organisation for Human Brain Mapping, Publisher: Organization for Human Brain Mapping
Cuervo-Soto B, Herrera-Vega J, Garces-Baez JADC, et al., 2016, Mocarts: a lightweight radiation transport simulator for easy handling of complex sensing geometries, IEEE 13th International Symposium on Biomedical Imaging (ISBI), Publisher: IEEE, Pages: 377-380, ISSN: 1945-7928
In functional neuroimaging (fNIRS), elaborated sensing geometries pairing multiple light sources and detectors arranged over the tissue surface are needed. A variety of software tools for probing forward models of radiation transport in tissue exist, but their handling of sensing geometries and specification of complex tissue architectures is, most times, cumbersome. In this work, we introduce a lightweight simulator, Monte Carlo Radiation Transport Simulator (MOCARTS) that attends these demands for simplifying specification of tissue architectures and complex sensing geometries. An object-oriented architecture facilitates such goal. The simulator core is evolved from the Monte Carlo Multi-Layer (mcml) tool but extended to support multi-channel simulations. Verification against mcml yields negligible error (RMSE~4-10e-9) over a photon trajectory. Full simulations show concurrent validity of the proposed tool. Finally, the ability of the new software to simulate multi-channel sensing geometries and to define biological tissue models in an intuitive nested-hierarchy way are exemplified.
Shetty K, Leff DR, Orihuela-Espina F, et al., 2016, Persistent Prefrontal Engagement Despite Improvements in Laparoscopic Technical Skill, JAMA Surgery, Vol: 151, Pages: 682-684, ISSN: 2168-6262
Teaching and assessment of laparoscopic skills are currently essential components of surgical training. The Fundamentals of Laparoscopic Surgery (FLS) is a widely adopted training program based on expert-derived benchmarks; technical skills are assessed and completion is a mandatory criterion for general surgery board certification in the United States.1 However, is attainment of technical proficiency synonymous with being a safe surgeon? Intraoperative errors persist and are thought to be related to errors in cognition2 as opposed to technical failure per se. The prefrontal cortex (PFC) is a brain region associated with attention and executive function serving as a scaffold to support novel task demands during effortful unrefined performance.3 Studies examining cortical correlates of technical skills acquisition have observed predictable attenuation in PFC response alongside improvement in technical performance4,5; however, this has not been adequately tested for challenging laparoscopic skills.
Orihuela-Espina F, Femat Roldan G, Sanchez-Villavicencio I, et al., 2016, Robot training for hand motor recovery in subacute stroke patients: a randomized controlled trial, Journal of Hand Therapy, Vol: 29, Pages: 51-57, ISSN: 1545-004X
BackgroundEvidence of superiority of robot training for the hand over classical therapies in stroke patients remains controversial. During the subacute stage, hand training is likely to be the most useful.AimTo establish whether robot active assisted therapies provides any additional motor recovery for the hand when administered during the subacute stage (<4 months from event) in a Mexican adult population diagnosed with stroke.HypothesisCompared to classical occupational therapy, robot based therapies for hand recovery will show significant differences at subacute stages.Trial designA randomized clinical trial.MethodsA between subjects randomized controlled trial was carried out on subacute stroke patients (n = 17) comparing robot active assisted therapy (RT) with a classical occupational therapy (OT). Both groups received 40 sessions ensuring at least 300 repetitions per session. Treatment duration was (mean ± std) 2.18 ± 1.25 months for the control group and 2.44 ± 0.88 months for the study group. The primary outcome was motor dexterity changes assessed with the Fugl-Meyer (FMA) and the Motricity Index (MI).ResultsBoth groups (OT: n = 8; RT: n = 9) exhibited significant improvements over time (Non-parametric Cliff's delta-within effect sizes: dwOT-FMA = 0.5, dwOT-MI = 0.5, dwRT-FMA = 1, dwRT-MI = 1). Regarding differences between the therapies; the Fugl-Meyer score indicated a significant advantage for the hand training with the robot (FMA hand: WRS: W = 8, p <0.01), whilst the Motricity index suggested a greater improvement (size effect) in hand prehension for RT with respect to OT but failed to reach significance (MI prehension: W = 17.5, p = 0.080). No harm occurred.ConclusionsRobotic therapies may be useful during the subacute stages of stroke – both endpoints (FM hand and MI prehension) showed the expected trend with bigger effect size for the robotic intervention. Additional benefit of the robotic therapy over the control th
Montero-Hernández SA, Orihuela-Espina F, Herrera-Vega J, et al., 2016, Causal probabilistic graphical models for decoding effective connectivity in functional near infrared spectroscopy, Pages: 686-689
Uncovering effective relations from non-invasive functional neuroimaging data remains challenging because the physical truth does not match the modelling assumptions often made by causal models. Here, we explore the use of causal Probabilistic Graphical Models for decoding the effective connectivity from functional optical neuroimaging. Our hypothesis is that directions of arcs of the connectivity network left undecided by existing learning algorithms can be resolved by exploiting prior structural knowledge from the human connec-tome. A variant of the fast causal inference algorithm, seeded FCI, is proposed to handle prior information. For evaluation, we used an existing dataset from prefrontal cortical activity of a cohort of 62 surgeons of varying expertise whilst knot-tying was monitored using fNIRS. Seeded FCI is used to built the prefrontal effective networks across expertise groups to reveal expertise-dependent differences. As hypothesized, the incorporation of prior information from the connectome reduces the set of undecided links. Good nomological validity is achieved when data is retrospectively compared to the findings in the original publication of the dataset. We contribute to the analysis of effective connectivity in fNIRS with the incorportation of structural information, and contribute to the field of causal PGMs with a new structure learning algorithm capable of exploiting existing knowledge to reduce the number of links remaining undecided when only information from observations is used. This work has implications thus for both, the AI and the neuroscience communities.
Leff DR, James D, Orihuela-Espina F, et al., 2015, The impact of expert visual guidance on trainee visual search strategy, visual attention and motor skills, Frontiers in Human Neuroscience, Vol: 9, ISSN: 1662-5161
Minimally invasive and robotic surgery changes the capacity for surgical mentors to guide their trainees with the control customary to open surgery. This neuroergonomic study aims to assess a “Collaborative Gaze Channel” (CGC); which detects trainer gaze-behaviour and displays the point of regard to the trainee. A randomised crossover study was conducted in which twenty subjects performed a simulated robotic surgical task necessitating collaboration either with verbal (control condition) or visual guidance with CGC (study condition). Trainee occipito-parietal (O-P) cortical function was assessed with optical topography (OT) and gaze-behaviour was evaluated using video-oculography. Performance during gaze-assistance was significantly superior [biopsy number: (mean ± SD): control=5·6±1·8 vs. CGC=6·6±2·0; p< 0.05] and was associated with significantly lower O-P cortical activity [∆HbO2 mMol x cm [median (IQR)] control = 2.5 (12.0) vs. CGC 0.63 (11.2), p < 0.001]. A random effect model confirmed the association between guidance mode and O-P excitation. Network cost and global efficiency and global efficiency were not significantly influenced by guidance mode. A gaze channel enhances performance, modulates visual search, and alleviates the burden in brain centres subserving visual attention and does not induce changes in the trainee's O-P functional network observable with the current OT technique. The results imply that through visual guidance, attentional resources may be liberated, potentially improving the capability trainees to attend to other safety critical events during the procedure.
This data is extracted from the Web of Science and reproduced under a licence from Thomson Reuters. You may not copy or re-distribute this data in whole or in part without the written consent of the Science business of Thomson Reuters.