A machine learning approach for predicting treatment response of hyponatremia.

Hyponatremia leads to severe central nervous system disorders and requires immediate treatment in some cases. However, a rapid increase in serum sodium (s-Na) concentration could cause osmotic demyelination syndrome. To achieve a safety hyponatremia treatment, we develop a prediction model of s-Na concentration using a machine learning. Among the 341 and 47 patients admitted to two tertiary hospitals for hyponatremia treatment (s-Na <130 mEq/L), those who were admitted to the general unit with urine sodium <20 mEq/L or treated with desmopressin were excluded. Ultimately, 74 and 15 patients (342 and 146 6-hourly datasets) were included in the learning and validation data, respectively. We trained the prediction model using three regression algorithms for shallow machine learning to predict s-Na every 6 h during treatment with the data of patients with hyponatremia (median s-Na: 112.5 mEq/L; range: 110.0-116.8 mEq/L) from one hospital. The model was validated externally using the data of patients with hyponatremia (median s-Na: 117.0 mEq/L; range: 112.9-120.0 mEq/L) from another hospital. Using 5-7 predictors (water intake, sodium intake, potassium intake, urine volume, s-Na concentration, serum potassium concentration, serum chloride concentration), the support vector regression model showed the best performance overall (root mean square error = 0.05396; R2 = 0.92), followed by the linear regression and regression tree models. The predicted s-Na levels, using explainable machine learning algorithms and clinically accessible parameters, correlated well with the actual levels. Thus, our model could be applied to the treatment of hyponatremia in clinical practice.

Artificial intelligence in a prediction model for postendoscopic retrograde cholangiopancreatography pancreatitis.

OBJECTIVES: In this study we aimed to develop an artificial intelligence-based model for predicting postendoscopic retrograde cholangiopancreatography (ERCP) pancreatitis (PEP). METHODS: We retrospectively reviewed ERCP patients at Nagoya University Hospital (NUH) and Toyota Memorial Hospital (TMH). We constructed two prediction models, a random forest (RF), one of the machine-learning algorithms, and a logistic regression (LR) model. First, we selected features of each model from 40 possible features. Then the models were trained and validated using three fold cross-validation in the NUH cohort and tested in the TMH cohort. The area under the receiver operating characteristic curve (AUROC) was used to assess model performance. Finally, using the output parameters of the RF model, we classified the patients into low-, medium-, and high-risk groups. RESULTS: A total of 615 patients at NUH and 544 patients at TMH were enrolled. Ten features were selected for the RF model, including albumin, creatinine, biliary tract cancer, pancreatic cancer, bile duct stone, total procedure time, pancreatic duct injection, pancreatic guidewire-assisted technique without a pancreatic stent, intraductal ultrasonography, and bile duct biopsy. In the three fold cross-validation, the RF model showed better predictive ability than the LR model (AUROC 0.821 vs. 0.660). In the test, the RF model also showed better performance (AUROC 0.770 vs. 0.663, P = 0.002). Based on the RF model, we classified the patients according to the incidence of PEP (2.9%, 10.0%, and 23.9%). CONCLUSION: We developed an RF model. Machine-learning algorithms could be powerful tools to develop accurate prediction models.

A comprehensible machine learning tool to differentially diagnose idiopathic pulmonary fibrosis from other chronic interstitial lung diseases.

BACKGROUND AND OBJECTIVE: Idiopathic pulmonary fibrosis (IPF) has poor prognosis, and the multidisciplinary diagnostic agreement is low. Moreover, surgical lung biopsies pose comorbidity risks. Therefore, using data from non-invasive tests usually employed to assess interstitial lung diseases (ILDs), we aimed to develop an automated algorithm combining deep learning and machine learning that would be capable of detecting and differentiating IPF from other ILDs. METHODS: We retrospectively analysed consecutive patients presenting with ILD between April 2007 and July 2017. Deep learning was used for semantic image segmentation of HRCT based on the corresponding labelled images. A diagnostic algorithm was then trained using the semantic results and non-invasive findings. Diagnostic accuracy was assessed using five-fold cross-validation. RESULTS: In total, 646,800 HRCT images and the corresponding labelled images were acquired from 1068 patients with ILD, of whom 42.7% had IPF. The average segmentation accuracy was 96.1%. The machine learning algorithm had an average diagnostic accuracy of 83.6%, with high sensitivity, specificity and kappa coefficient values (80.7%, 85.8% and 0.665, respectively). Using Cox hazard analysis, IPF diagnosed using this algorithm was a significant prognostic factor (hazard ratio, 2.593; 95% CI, 2.069-3.250; p < 0.001). Diagnostic accuracy was good even in patients with usual interstitial pneumonia patterns on HRCT and those with surgical lung biopsies. CONCLUSION: Using data from non-invasive examinations, the combined deep learning and machine learning algorithm accurately, easily and quickly diagnosed IPF in a population with various ILDs.

Development and validation of machine learning models to predict postoperative infarction in moyamoya disease.

OBJECTIVE: Cerebral infarction is a common complication in patients undergoing revascularization surgery for moyamoya disease (MMD). Although previous statistical evaluations have identified several risk factors for postoperative brain ischemia, the ability to predict its occurrence based on these limited predictors remains inadequately explored. This study aimed to assess the feasibility of machine learning algorithms for predicting cerebral infarction after revascularization surgery in patients with MMD. METHODS: This retrospective study was conducted across two centers and harnessed data from 512 patients with MMD who had undergone revascularization surgery. The patient cohort was partitioned into internal and external datasets. Using perioperative clinical data from the internal cohort, three distinct machine learning algorithms-namely the support vector machine, random forest, and light gradient-boosting machine models-were trained and cross-validated to predict the occurrence of postoperative cerebral infarction. Predictive performance validity was subsequently assessed using an external dataset. Shapley additive explanations (SHAP) analysis was conducted to augment the prediction model's transparency and to quantify the impact of each input variable on shaping both the aggregate and individual patient predictions. RESULTS: In the cohort of 512 patients, 33 (6.4%) experienced postrevascularization cerebral infarction. The cross-validation outcomes revealed that, among the three models, the support vector machine model achieved the largest area under the receiver operating characteristic curve (ROC-AUC) at mean ± SD 0.785 ± 0.052. Notably, during external validation, the light gradient-boosting machine model exhibited the highest accuracy at 0.903 and the largest ROC-AUC at 0.710. The top-performing prediction model utilized five input variables: postoperative serum gamma-glutamyl transpeptidase value, positive posterior cerebral artery (PCA) involvement on preoperative MRA, infarction as the rationale for surgery, presence of an infarction scar on preoperative MRI, and preoperative modified Rankin Scale score. Furthermore, the SHAP analysis identified presence of PCA involvement, infarction as the rationale for surgery, and presence of an infarction scar on preoperative MRI as positive influences on postoperative cerebral infarction. CONCLUSIONS: This study indicates the usefulness of employing machine learning techniques with routine perioperative data to predict the occurrence of cerebral infarction after revascularization procedures in patients with MMD.

Intra-Articular Ultrasonography Probe for Minimally Invasive Upper Extremity Arthroscopic Surgery: A Phantom Study.

BACKGROUND: Upper extremity arthroscopic surgery is a highly technique-dependent procedure that requires the surgeon to assess difficult cartilage conditions and manage the risk of iatrogenic damage to nerves and vessels adjacent to the joint capsule in a confined joint space, and a device that can safely assist in this procedure has been in demand. METHODS: In this study, we developed a small intra-articular ultrasound (AUS) probe for upper extremity joint surgery, evaluated its safety using underwater sound field measurement, and tested its visualization with a phantom in which nerves and blood vessels were embedded. RESULTS: Sound field measurement experiments confirmed the biological safety of the AUS probe's output, while confirming that sufficient output power level performance was obtained as an ultrasound measurement probe. In addition, images of blood vessels and nerves were reconstructed discriminatively using A-mode imaging of the agar phantom. CONCLUSIONS: This study provides proof-of-concept of the AUS probe in upper extremity surgery. Further studies are needed to obtain approval for use in future medical devices.

Prognostic Factors for Covid-19 on Admission Profile and Air Pollutants.

It has been reported that the severity and lethality of Covid-19 are associated with coexisting underlying diseases (hypertension, diabetes, etc.) and cardiovascular diseases (coronary artery disease, atrial fibrillation, heart failure, etc.) that increase with age, but environmental exposure such as air pollutants may also be a risk factor for mortality. In this study, we investigated patient characteristics at admission and prognostic factors of air pollutants in Covid-19 patients using a machine learning (random forest) prediction model. Age, Photochemical oxidant concentration one month prior to admission, and level of care required were shown to be highly important for the characteristics, while the cumulative concentrations of air pollutants SPM, NO2, and PM2.5 one year prior to admission were the most important characteristics for patients aged 65 years and older, suggesting the influence of long-term exposure.

In-Hospital Cancer Mortality Prediction by Multimodal Learning of Non-English Clinical Texts.

Predicting important outcomes in patients with complex medical conditions using multimodal electronic medical records remains challenge. We trained a machine learning model to predict the inpatient prognosis of cancer patients using EMR data with Japanese clinical text records, which has been considered difficult due to its high context. We confirmed high accuracy of the mortality prediction model using clinical text in addition to other clinical data, suggesting applicability of this method to cancer.

Telerehabilitation Based on Markerless Motion Capture and IMT-2020 (5G) Networks.

Eldercare programs such as health consultations and physiotherapy that improve the well-being and extend the life expectancy of people in rural or sparsely populated areas is a socially important though costly problem. We ran a pilot project to test the effectiveness potential of telerehabilitation using markerless motion capture technology integrated in a fast and low-latency IMT-2020 (5G) mobile network. Accelerating technological innovations and the surge in advances of telehealth will greatly impact conventional home visit or outpatient rehabilitation services, working in concert with or even supplanting them, given the potential lower cost and better utilization of time.

Demonstration experiment of telemedicine using ultrasonography and telerehabilitation with 5G communication system in aging and depopulated mountainous area.

Objective: The challenges of an aging population worldwide are the increased number of people needing medical and nursing care and inadequate medical resources. Information and communication technologies have progressed remarkably, leading to innovations in various areas. 5G communication systems are capable of high-capacity, high-speed communication with low latency and are expected to transform medicine. We aimed to report a demonstration experiment of telerehabilitation and telemedicine using a mobile ultrasound system in a depopulated area in a mountainous terrain, where 32% of the population are 65 years or older. Methods: At the core hospital, a physician or physical therapist remotely performed ultrasonography or rehabilitation on a subject in a clinic. Five general residents participated in the telerehabilitation as subjects. The delay time and video quality transmitted with 5G and long-term evolution (LTE) communication systems were compared. The physician or physical therapist subjectively evaluated the quality and delay of the transmitted images and subject acceptability. Results: Of seven physical therapists, six and three responded that the video quality was "good" for telerehabilitation with 5G/4K resolution and LTE, respectively. Five physical therapists and one physical therapist reported that the delay time was "acceptable" with 5G/4K resolution and LTE, respectively. For telemedicine using a mobile ultrasound system, the responses for 5G were "the delay was acceptable" and "rather acceptable." In contrast, both respondents' responses for LTE were "not acceptable." Conclusions: Multiple high-definition images can be transmitted with lower latency in telerehabilitation and telemedicine using mobile ultrasound imaging systems with a 5G communication system. These differences affected the subjective evaluation of the doctors and physical therapists.

Experimental pilot study for augmented reality-enhanced elbow arthroscopy.

The purpose of this study was to develop and evaluate a novel elbow arthroscopy system with superimposed bone and nerve visualization using preoperative computed tomography (CT) and magnetic resonance imaging (MRI) data. We obtained bone and nerve segmentation data by CT and MRI, respectively, of the elbow of a healthy human volunteer and cadaveric Japanese monkey. A life size 3-dimensional (3D) model of human organs and frame was constructed using a stereo-lithographic 3D printer. Elbow arthroscopy was performed using the elbow of a cadaveric Japanese monkey. The augmented reality (AR) range of error during rotation of arthroscopy was examined at 20 mm scope-object distances. We successfully performed AR arthroscopy using the life-size 3D elbow model and the elbow of the cadaveric Japanese monkey by making anteromedial and posterior portals. The target registration error was 1.63 ± 0.49 mm (range 1-2.7 mm) with respect to the rotation angle of the lens cylinder from 40° to - 40°. We attained reasonable accuracy and demonstrated the operation of the designed system. Given the multiple applications of AR-enhanced arthroscopic visualization, it has the potential to be a next-generation technology for arthroscopy. This technique will contribute to the reduction of serious complications associated with elbow arthroscopy.

Smart hospital infrastructure: geomagnetic in-hospital medical worker tracking.

PURPOSE: Location visualization is essential for locating people/objects, improving efficiency, and preventing accidents. In hospitals, Wi-Fi, Bluetooth low energy (BLE) Beacon, indoor messaging system, and similar methods have generally been used for tracking, with Wi-Fi and BLE being the most common. Recently, nurses are increasingly using mobile devices, such as smartphones and tablets, while shifting. The accuracy when using Wi-Fi or BLE may be affected by interference or multipath propagation. In this research, we evaluated the positioning accuracy of geomagnetic indoor positioning in hospitals. MATERIALS AND METHODS: We compared the position measurement accuracy of a geomagnetic method alone, Wi-Fi alone, BLE beacons alone, geomagnetic plus Wi-Fi, and geomagnetic plus BLE in a general inpatient ward, using a geomagnetic positioning algorithm by GiPStech. The existing Wi-Fi infrastructure was used, and 20 additional BLE beacons were installed. Our first experiment compared these methods' accuracy for 8 test routes, while the second experiment verified a combined geomagnetic/BLE beacon method using 3 routes based on actual daily activities. RESULTS: The experimental results demonstrated that the most accurate method was geomagnetic/BLE, followed by geomagnetic/Wi-Fi, and then geomagnetic alone. DISCUSSION: The geomagnetic method's positioning accuracy varied widely, but combining it with BLE beacons reduced the average position error to approximately 1.2 m, and the positioning accuracy could be improved further. We believe this could effectively target humans (patients) where errors of up to 3 m can generally be tolerated. CONCLUSION: In conjunction with BLE beacons, geomagnetic positioning could be sufficiently effective for many in-hospital localization tasks.

Electroencephalographic Functional Connectivity With the Tacit Learning System Prosthetic Hand: A Case Series Using Motor Imagery.

We previously created a prosthetic hand with a tacit learning system (TLS) that automatically supports the control of forearm pronosupination. This myoelectric prosthetic hand enables sensory feedback and flexible motor output, which allows users to move efficiently with minimal burden. In this study, we investigated whether electroencephalography can be used to analyze the influence of the auxiliary function of the TLS on brain function. Three male participants who had sustained below-elbow amputations and were myoelectric prosthesis users performed a series of physical movement trials with the TLS inactivated and activated. Trials were video recorded and a sequence of videos was prepared to represent each individual's own use while the system was inactivated and activated. In a subsequent motor imagery phase during which electroencephalography (EEG) signals were collected, each participant was asked to watch both videos of themself while actively imagining the physical movement depicted. Differences in mean cortical current and amplitude envelope correlation (AEC) values between supplementary motor areas (SMA) and each vertex were calculated. For all participants, there were differences in the mean cortical current generated by the motor imagery tasks when the TLS inactivated and activated conditions were compared. The AEC values were higher during the movement imagery task with TLS activation, although their distribution on the cortex varied between the three individuals. In both S1 and other brain areas, AEC values increased in conditions with the TLS activated. Evidence from this case series indicates that, in addition to motor control, TLS may change sensory stimulus recognition.

Magnetoencephalographic evaluation for the myoelectric hand prosthesis with tacit learning system.

BACKGROUND: The effect of tacit learning systems (TLSs) on brain plasticity are as of yet unknown. We developed a myoelectric hand prosthesis equipped with a TLS to auto-regulate forearm rotation in response to upper extremity movement patterns. OBJECTIVE: To evaluate the effects of tacit learning on the central nervous system during a prosthesis control exercise. METHODS: The experienced prosthetic user performed a series of simple mechanical tasks with the TLS inactivated (the baseline condition) and then with it activated (the enhanced, experimental condition). The process was video recorded. Subsequently, the participant viewed video recordings of each condition (baseline and experimental) during magnetoencephalography and electroencephalography recordings. RESULTS: Stronger connections between the motor area and other cortical areas were observed, as indicated by a significant increase in coherence values. CONCLUSIONS: Integration and interoperability may underlie tacit learning and promote motor function-related adaptive neuroplasticity.

Use of in-Hospital Geomagnetic Fingerprinting Localization.

Recently, visualizing location of people and things in a hospital has become an issue particularly for improving work efficiency and incident prevention. Although radio frequency waves such as Wi-Fi and Bluetooth are commonly used in indoor positioning, they have several limitations owing to their physical characteristics. We proposed in-hospital hybrid positioning technique, involving a combination of radio waves and geomagnetic fingerprinting techniques. We compared accuracy of proposed technique with that of Wi-Fi- and BLE-based techniques.

Biomechanical Reconstruction Using the Tacit Learning System: Intuitive Control of Prosthetic Hand Rotation.

Background: For mechanically reconstructing human biomechanical function, intuitive proportional control, and robustness to unexpected situations are required. Particularly, creating a functional hand prosthesis is a typical challenge in the reconstruction of lost biomechanical function. Nevertheless, currently available control algorithms are in the development phase. The most advanced algorithms for controlling multifunctional prosthesis are machine learning and pattern recognition of myoelectric signals. Despite the increase in computational speed, these methods cannot avoid the requirement of user consciousness and classified separation errors. "Tacit Learning System" is a simple but novel adaptive control strategy that can self-adapt its posture to environment changes. We introduced the strategy in the prosthesis rotation control to achieve compensatory reduction, as well as evaluated the system and its effects on the user. Methods: We conducted a non-randomized study involving eight prosthesis users to perform a bar relocation task with/without Tacit Learning System support. Hand piece and body motions were recorded continuously with goniometers, videos, and a motion-capture system. Findings: Reduction in the participants' upper extremity rotatory compensation motion was monitored during the relocation task in all participants. The estimated profile of total body energy consumption improved in five out of six participants. Interpretation: Our system rapidly accomplished nearly natural motion without unexpected errors. The Tacit Learning System not only adapts human motions but also enhances the human ability to adapt to the system quickly, while the system amplifies compensation generated by the residual limb. The concept can be extended to various situations for reconstructing lost functions that can be compensated.