Pole balancing on the fingertip: model-motivated machine learning forecasting of falls

Introduction: There is increasing interest in developing mathematical and computational models to forecast adverse events in physiological systems. Examples include falls, the onset of fatal cardiac arrhythmias, and adverse surgical outcomes. However, the dynamics of physiological systems are known to be exceedingly complex and perhaps even chaotic. Since no model can be perfect, it becomes important to understand how forecasting can be improved, especially when training data is limited. An adverse event that can be readily studied in the laboratory is the occurrence of stick falls when humans attempt to balance a stick on their fingertips. Over the last 20 years, this task has been extensively investigated experimentally, and presently detailed mathematical models are available. Methods: Here we use a long short-term memory (LTSM) deep learning network to forecast stick falls. We train this model to forecast stick falls in three ways: 1) using only data generated by the mathematical model (synthetic data), 2) using only stick balancing recordings of stick falls measured using high-speed motion capture measurements (human data), and 3) using transfer learning which combines a model trained using synthetic data plus a small amount of human balancing data. Results: We observe that the LTSM model is much more successful in forecasting a fall using synthetic data than it is in forecasting falls for models trained with limited available human data. However, with transfer learning, i.e., the LTSM model pre-trained with synthetic data and re-trained with a small amount of real human balancing data, the ability to forecast impending falls in human data is vastly improved. Indeed, it becomes possible to correctly forecast 60%-70% of real human stick falls up to 2.35 s in advance. Conclusion: These observations support the use of model-generated data and transfer learning techniques to improve the ability of computational models to forecast adverse physiological events.

Controlling stick balancing on a linear track: Delayed state feedback or delay-compensating predictor feedback?

A planar stick balancing task was investigated using stabilometry parameters (SP); a concept initially developed to assess the stability of human postural sway. Two subject groups were investigated: 6 subjects (MD) with many days of balancing a 90 cm stick on a linear track and 25 subjects (OD) with only one day of balancing experience. The underlying mechanical model is a pendulum-cart system. Two control force models were investigated by means of numerical simulations: (1) delayed state feedback (DSF); and (2) delay-compensating predictor feedback (PF). Both models require an internal model and are subject to certainty thresholds with delayed switching. Measured and simulated time histories were compared quantitatively using a cost function in terms of some essential SPs for all subjects. Minimization of the cost function showed that the control strategy of both OD and MD subjects can better be described by DSF. The control mechanism for the MD subjects was superior in two aspects: (1) they devoted less energy to controlling the cart's position; and (2) their perception threshold for the stick's angular velocity was found to be smaller. Findings support the concept that when sufficient sensory information is readily available, a delay-compensating PF strategy is not necessary.

Predictor feedback models for stick balancing with delay mismatch and sensory dead zones

Human stick balancing is investigated in terms of reaction time delay and sensory dead zones for position and velocity perception using a special combination of delayed state feedback and mismatched predictor feedback as a control model. The corresponding mathematical model is a delay-differential equation with event-driven switching in the control action. Due to the sensory dead zones, initial conditions of the actual state cannot always be provided for an internal-model-based prediction, which indicates that (1) perfect prediction is not possible and (2) the delay in the switching condition cannot be compensated. The imperfection of the predictor is described by the delay mismatch, which is treated as a lumped parameter that creates a transition between perfect predictor feedback (zero delay mismatch) and delayed state feedback (mismatch equal to switching delay). The maximum admissible switching delay (critical delay) is determined numerically based on a practical stabilizability concept. This critical delay is compared to a realistic reference value of 230 ms in order to assess the possible regions of the threshold values for position and velocity perception. The ratio of the angular position and angular velocity for 44 successful balancing trials by 8 human subjects was used to validate the numerical results. Comparison of actual human stick balancing data and numerical simulations based on the mismatched predictor feedback model provided a plausible range of parameters: position detection threshold 1°, velocity detection threshold between 4.24 and 9.35°/s, and delay mismatch around 100-150 ms.

Intravenous ketorolac and subarachnoid opioid analgesia in the management of acute postoperative pain

BACKGROUND AND OBJECTIVES

Ketorolac is a parenteral nonsteroidal anti-inflammatory drug that provides analgesia through a peripheral mechanism. The purpose of this study was to evaluate whether the scheduled administration of intravenous ketorolac improves the analgesia provided by subarachnoid opioids after surgery.

METHODS

Patients undergoing major urologic surgery were enrolled in a randomized, placebo-controlled, double-blinded study and received one of two analgesic regimens. All patients were given subarachnoid opioid analgesia consisting of morphine (range, 0.55-0.8 mg) plus fentanyl (25 micrograms) at the completion of surgery just prior to awakening. In addition to subarachnoid opioids, patients received four doses of either intravenous placebo (group 1, n = 21) or ketorolac (group 2, n = 17) administered 30 minutes before the anticipated completion of surgery and at 6, 12, and 18 hours after surgery. Patients in group 2 who were 65 years old or older received 30 mg ketorolac initially, with subsequent doses of 15 mg. Those younger than 65 years of age received 60 mg ketorolac initially, with subsequent doses of 30 mg. Pain scores were assessed by a blinded observer using a 10-cm visual analog scale (VAS) at 1, 8, and 24 hours after the operation. Intravenous morphine requirements while in the postanesthesia care unit (PACU) and during the following 24 hours, as well as the incidence of pruritus, nausea, naloxone usage, and bleeding were also recorded. Results were analyzed using the Wilcoxon rank-sum, Fischer's exact, chi-square, and Student's t tests.

RESULTS

Patients receiving intravenous ketorolac (group 2) in addition to subarachnoid opioids had significantly lower pain scores 1 hour after surgery, and required less supplementary intravenous morphine within the first 24 postoperative hours (P < .05). The percentage of patients requiring no analgesic intervention while in the PACU was significantly higher for those receiving ketorolac (P = .01). The incidence of opioid-related side effects was similar between groups, and no perioperative bleeding was observed.

CONCLUSIONS

When used in conjunction with subarachnoid opioids, the scheduled administration of intravenous ketorolac during the first 24 hours after major urologic surgery significantly enhances analgesia and reduces the need for supplemental intravenous opioids without affecting the incidence of side effects. Intravenous ketorolac is a safe and useful adjuvant to subarachnoid opioids in the management of acute postoperative pain.