Select Field
Select Ministry
10 results
Cardiovascular disease is one of the major health concerns in Taiwan and worldwide. The number of patients with cardiovascular disease has drama tically increased over the years, with coronary artery disease (CAD) being t he most significant condition. Traditional diagnostic methods for CAD are expensive and resource-intensive. However, this technology utilizes artific ial intelligence (AI)-enhanced electrocardiography (ECG) to improve the d etection of CAD thereby enabling more accurate detection of asymptomat ic coronary artery stenosis.This AI-based technology is a SaMD (software as medical device). Three p atents are applied: (1) Method for selecting feature of ECG; (2) Method for predicting blockage of coronary artery; (3) Method for diagnosing heart s tate based on ECG. Moreover, we expand the output format to PDF vector files, enhancing its commercial potential. Regarding signal processing, it includes wavelet transform, statistical indic ators, and personalized heartbeat intervals. Regarding feature engineerin g, it includes various time intervals, slopes, and height differences betwee n heartbeats to capture subtle abnormalities. Regarding model predictio n, it utilizes a combination of deep learning and machine learning method s, ensuring stability and accuracy. In terms of product application, both XML and PDF files are applicable as i nput. The interpretability of features aids clinicians in identifying abnorma l locations on ECG. Finally, the performance was validated in two hospitals. The results revealed that our AI technology has a superiorly better perfor mance. Traditional resting ECG achieves to 50%-60% accuracy, and exercis e ECG achieves to 70% accuracy. Remarkably, our AI algorithm achieves an 84%-90% accuracy of AUC. Currently, CAD cannot be easily detected in high-risk asymptomatic patie nts. Our AI algorithm can identify 80%-90% of asymptomatic patients wit h normal ECG but actually having stenosis, thus enhancing the accuracy fo r detecting
Future Tech | Biotechnology ＆ Medical careEstablish high-accuracy AI governance technology to produce a local path ogen-themed database. 1.Cooperate with the National Health Insurance (NHI) Administration to a pply natural language processing (NLP) technology to develop a set of me thods for managing pathogen data, which can automatically standardize t he data format, and combine the expertise of infectious disease physician s to make the standardized data meet the needs of professional fields. 2.Using NLP technology, the data uploaded from the hospital to the infor mation system of the NHI Administration, it will automatically collects the strain name, antibiotic name, antibiotic susceptibility and resistance value. The data collection process includes the following steps: (1)Data classification: Classify the uploaded data into two types: complete and incomplete; (2)Word tokenization: Use Regular Expression to separate the string of co mpleted data into individual words or symbols; (3)Extract key data: From the comparison results of the tokenized data, ext ract the strain name, antibiotic name, antibiotic susceptibility and resistan ce values; (4) Look for the law of data: look for the law of pathogen resistance data, e.g., [antibiotic name][abbreviation of antibiotic][antibiotic susceptibili ty][resistance value]; (5) Compiling data: according to the law of key data, compile data sequen tially; (6) Data integration: output the pattern data and the aggregated data in d ifferent Excel files. Results: 1.High accuracy: Develop AI models to rectify pathogen-themed database s. The correct rate of data compilation can reach 93.88%. 2.Save manpower-time: (1)Non-blood bacterial data: It only takes about 65 hours to collect 240,00 0 pieces of data using this technology. It would take about 1,000 working days to sort out these materials manually. (2)Blood bacteria data: It only takes about 25 hours to collect 60,000 piece s of data using this technology. It would take about 250 working days to s ort out these m
Future Tech | Information ＆ Communications/Machinery ＆ SystemIn Taiwan, drowning remains one of the top three causes of accidental inju ry-related deaths among children and adolescents. The swimming industr y faces practical challenges in terms of economics and safety measures. At NHRI, our team has partnered with the safety management sector to d evelop the AI Smart Pool Automated Drowning Prevention and Early Warn ing System. Traditionally, video equipment has been used as passive post- accident evidence to meet legal requirements. In contrast, the AI Smart Po ol Automated Drowning Prevention and Early Warning System actively an alyzes swimmer activities and pre-drowning characteristics to assess safet y status and trigger automatic alerts. The system offers the following func tions and advantages. Adaptability to various pool sizes: The system demonstrates flexibility by i ntegrating standard monitoring systems and employing computational m odels for water surface observation. By considering multiple angles, lighti ng conditions, and color variations, the system achieves highly adaptable AI monitoring and early warning capabilities. Assisting lifeguards in maintaining attention and improving judgment effi ciency: High-resolution images of the entire pool area are captured, overc oming limitations associated with human visual observation, such as a lim ited field of view, attention span, and blind spots. The system enables prol onged observation and indicates specific areas that require judgment, ser ving as an efficient and accurate reinforcement system. Prediction of swimming patterns: The AI algorithm employed in the syste m utilizes various swimming postures, data quantification, calculation, an d domain knowledge of the swimming process to establish an intelligent mechanism for pre-drowning, mid-drowning, and post-drowning stages. The system achieves a recognition accuracy of over 90% in identifying swi mming patterns, providing real-time and accurate safety monitoring assis tance.
Future Tech | Biotechnology ＆ Medical care/Life ApplicationThis project integrates resources from industry, government, and academi a to establish 5G infrastructure in rural areas. Using 5G technology, we up grade medical image transmission, enhancing healthcare applications and quality. The National Health Institute collaborates with telecom providers and medical center/regional hospital to create a 5G telemedicine experim ental field. Our aim is a multi-faceted healthcare model. Model One: "Doct ors Stationary, Patients Mobile". Patients visit local clinics for remote cons ultations, reducing travel distances. It involves collaborative diagnosis and treatment between local and remote doctors, integrating specialized hosp ital capabilities with local physicians' care. Model Two: "Doctors Mobile, Patients Stationary". Home-based telemedicine is established, providing r emote diagnosis and treatment. Specialized medical teams support home -based physicians through real-time guidance and access to medical imag es. This ensures quality care for patients in their homes, including those wi th complex conditions. Through 5G-enabled telemedicine, we overcome d istance and time limitations, meeting social needs, utilizing healthcare res ources effectively, and reducing healthcare disparities. The project also est ablishes a healthcare information industry alliance, extending services to home and community settings, implementing medical diversion, and ena bling local physicians to acquire specialized skills through remote consult ations. Information security technologies safeguard data transmission. Re search outcomes and recommendations will guide future government pol icies in remote healthcare services.
Future Tech | Information ＆ Communications/Machinery ＆ SystemPaclitaxel is a first-line taxane-based chemotherapeutic agent for various malignancies such as breast, ovarian, and non-small cell lung cancers. Unf ortunately, approximately 60-70% patients develop chemotherapy-induce d peripheral neuropathy (CIPN) after receiving it, not only diminishing life quality but even making patients quit therapy. Thus, development of a ne uroprotective agent to prevent or alleviate paclitaxel-induced CIPN is an u rgent unmet medical need. Combining a unique image-based high-conte nt screening platform with a novel phenotypic nerve assay system newly d eveloped by our drug-discovery team, medicinal chemists have well estab lished structure-activity relationships (SAR), leading to the identification o f a neuroprotective drug candidate DBPR168, which has completed the proof-of-concept in two behavioral mouse models, including tail immersion and von Frey filaments. In brief, pretreatment with DBPR168 administered intravenously before receiving paclitaxel was able to alleviate both paclita xel-induced thermal hypesthesia and mechanical allodynia effectively. Me chanistically, DBPR168 could significantly inhibit paclitaxel-induced inflam matory responses and the infiltration of immune cells into sensory neuron s. DBPR168 not only showed a high safety dose (MTD = 500 mg/kg, IV), b ut also a low minimum efficacy dose (MED = 10 mg/kg, IV) in mice. Based on a high therapeutic index (50) and excellent pharmacological profiles, it is anticipated that DBPR168 might have great potential to become the firs t-in-class neuroprotective agent to prevent chemotherapy-induced periph eral neuropathy (CIPN).
Future Tech | Biotechnology ＆ Medical careWe have developed compartmental disease transmission models to provi de policymakers timely simulations of the pandemic's progression. Ther efore, policymakers utilized the information to take preemptive actions, w hich included efficiently formulating mitigation policies before an outbrea k and comprehensively assessing their effectiveness. By integrating data on multi-dimensional parameters gathered at various stages of the pande mic, our model can also reveal the associated risks it poses to different ag e groups. The timely implementation of accurate and dynamic prediction models based on data sourced from various countries can provide efficien t allocation of resources according to demand. We have also developed an agent-based disease transmission model at an individual level, integrating population mobility data to accurately reprod uce the mobility of people in public areas and individuals' activities. Base d on a geographic model, various types of buildings such as companies, sc hools, restaurants, and residential areas are realistically represented in the ir locations and distributions. This enables the simulation of gatherings in daily life for different age groups and fixed interactions between different communities or random contacts between strangers. Furthermore, we hav e developed a dynamic mathematical model with multiple adjustable para meters and a user-friendly interface. We investigated the mediation effects of government non-pharmaceutica l interventions (NPIs), such as social distancing measures, and the actual l evels of various types of activities by the population (e.g., indoor dining a nd outdoor activities) on the transmission and containment of the epidem ic. The results of this study are expected to contribute to the understandin g of different patterns of transmission and socio-cultural differences by co mparing the analysis of over the past three years, and how the activity pat terns of the population can influence the development of t
Future Tech | Information ＆ Communications/Machinery ＆ SystemMagnetic resonance imaging (MRI) is a radiation-free, non-invasive, preci se, and safe medical imaging modality. By utilizing a strong magnetic fiel d, MRI can detect the small signal from the protons in the human body aft er the excitation by radiofrequency waves. MRI offers multi-angle scannin g and high-contrast imaging, improving diagnostic accuracy. However, M RI images are susceptible to motion artifacts caused by subject movemen t or physiological motion during scans. Diffusion-weighted MRI, in particu lar, is highly sensitive to even slight subject motion or positional changes due to respiration or heartbeat, leading to significant image artifacts whic h can hinder the image interpretation and clinical diagnosis. Current methods to mitigate motion artifacts in MRI include the navigator echo method and the multi-channel signal correction. The navigator echo method requires the modification of pulse sequence to acquire additional signals for the correction of phase error due to subject motion. Multi-chan nel signal correction requires a phase array coil for multi-channel data acq uisition to correct the motion artifact. However, the present invention offe rs a method that does not require modifying existing MRI pulse sequence s and is not limited by MRI hardware. If subject motion happens during sc ans, inconsistent phase errors occur in each data acquisition. The present i nvention utilizes an iterative algorithm to compensate the phase errors caused by subject motion with automated segmentation of MRI images. Thi s method can automatic correct motion artifacts in MRI images without m odifying existing sequences or being limited by hardware. It provides mor e accurate and precise medical images for clinical use.
Future Tech | Biotechnology ＆ Medical careAXL and MERTK are members of TAM (TYRO3, AXL and MERTK) receptor t yrosine kinases and play important roles in tumor progression, metastasis, drug resistance and immune evasion. Thus, dual inhibition of AXL and ME RTK in the tumor and tumor immune microenvironment would enhance a nti-tumor efficacy and boost anti-tumor immune responses. Utilizing our proprietary small molecule tyrosine kinase inhibitors compound library an d structure-based drug design by protein crystallography approach, we h ave identified an orally bioavailable AXL and MERTK dual kinase inhibitor BPR5K230 with potent AXL and MERTK inhibitory activities and selectivity over TYRO3. BPR5K230 demonstrated in vivo anti-tumor efficacy and imm unomodulatory activities; the anti-tumor effect of BPR5K230 was more efficacious than that of the current Phase II clinical trial agent Ono-7475. The current invention is intended to use in late stage triple negative breast can cer, lung cancer and liver cancer.
Future Tech | Biotechnology ＆ Medical careThe Precision Medicine Public-Private Partnership Alliance (PPP) coordinates with the clinical study platform (e.g., TCOG) to provide high-quality patient recruitment/data collection support to conduct the Collaborative Precision Medicine Research Program initiated and invested by the industrial partners. In this program, the LDTs certified NGS-based genetic tests are performed, with results applied to treatments and follow-up data collected. Also, patient consents to submit data to the National Biobank Consortium are obtained for future data use. Thus, the PPP project successfully links industrial, medical, academic, and government resources to achieve its four major goals: acceleration of clinical studies for new drug developments, enhancing cancer therapy developments to benefit patients, establishing cancer precision medicine databases conducive for R&D using RWD/RWE, and to facilitate evidence-based assessment for genetic tests insurance coverage policies.
Future Tech | Biotechnology ＆ Medical careThrough the cooperation of all biobanks in Taiwan, with consistent quality standards and clinical data content, a large and comprehensive human bi obank network can be quickly established. As a result, National Biobank C onsortium of Taiwan (NBCT) was established. The goal of NBCT is to prom ote the biomedical science in Taiwan and the demand of biotechnology in dustries. A Central office of NBCT was set up to manage all of the administ ration work and to play a role as one stop service with good efficiency. Ad equate and consistent clinical data will also be established under well info rmation security management. Since the contents of the biobanks from different institute are quite differ ent, NBCT is able to quickly establish a large and comprehensive biobank network. Currently NBCT already successfully invited 33 biobanks to join a nd has more than 836 thousand participants with various kinds of biosam ples available for applicants. So far, NBCT already received 158 application s, including 24 from industries. One of them is an international collaborati on project and application from Roche. The number of specimens in the N BCT is very large, coupled with large medical data, it is already Taiwan's l argest biomedical industry treasure. The future plan is to expand informat ion security and compliance with biobank regulations, so that applicants c an analyze and use data online, which will help promote international coo peration and continue to expand the results and benefits of the integrated platform , becoming the most important resource for Taiwan's biotechnology and pharmaceutical industry. It can also attract the interest of foreig n research institutions or industries, and help establish cooperative relatio ns with international academic institutions or biotechnology industries.
Future Tech | Biotechnology ＆ Medical careComing soon!
