Development of AI-generated medical responses using the ChatGPT for cancer patients.

BACKGROUND AND OBJECTIVE: To develop a healthcare chatbot service (AI-guided bot) that conducts real-time conversations using large language models to provide accurate health information to patients. METHODS: To provide accurate and specialized medical responses, we integrated several cancer practice guidelines. The size of the integrated meta-dataset was 1.17 million tokens. The integrated and classified metadata were extracted, transformed into text, segmented to specific character lengths, and vectorized using the embedding model. The AI-guide bot was implemented using Python 3.9. To enhance the scalability and incorporate the integrated dataset, we combined the AI-guide bot with OpenAI and the LangChain framework. To generate user-friendly conversations, a language model was developed based on Chat-Generative Pretrained Transformer (ChatGPT), an interactive conversational chatbot powered by GPT-3.5. The AI-guide bot was implemented using ChatGPT3.5 from Sep. 2023 to Jan. 2024. RESULTS: The AI-guide bot allowed users to select their desired cancer type and language for conversational interactions. The AI-guided bot was designed to expand its capabilities to encompass multiple major cancer types. The performance of the AI-guide bot responses was 90.98 ± 4.02 (obtained by summing up the Likert scores). CONCLUSIONS: The AI-guide bot can provide medical information quickly and accurately to patients with cancer who are concerned about their health.

Facile and Scalable Preparation of a MoS2/Carbon Nanotube Nanocomposite Anode for High-Performance Lithium-Ion Batteries: Effects of Carbon Nanotube Content.

To investigate the effects of carbon nanotube content on the electrochemical performance in MoS2/CNT nanocomposite, a simple high-energy mechanical milling method was employed to prepare nanocomposites from MoS2 and CNT. Prepared with a one-step, 24-h ball-milling method, the MoS2/CNT nanocomposite showed improved performance in terms of specific capacity after 70 cycles when compared to pure MoS2. In addition, upon studying the effects of the weight ratio between MoS2 and the CNTs at (1:2), (1:1), and (2:1), we found the MoS2/CNT-(1:2) showed the highest specific capacity (~765 mAh g-1) after 70 cycles and the best rate capability due to increased conductivity. Overall, the results suggested that the addition of conductive CNTs in MoS2 not only improves the cycling stability, but also leads to an increase in the specific capacity of MoS2/CNTs, which suggests our MoS2/CNT nanocomposite as a new and promising anode material for lithium-ion batteries (LIBs).

Comparative Study of Mechanically Milled MoS2 and MoSe2 in Graphite Matrix as Anode Materials for High-Performance Lithium-Ion Batteries.

Nanocomposites of MoS2/graphite and MoSe2/graphite were formed from two-dimensional materials (MoS2 and MoSe2) and graphite using a one-step ball-milling method (high energy mechanical milling, HEMM). As anode materials for lithium-ion batteries (LIBs), these nanocomposites showed higher specific capacity and greater stability during long cyclic operation compared to their pure counterparts (MoS2 and MoSe2). X-ray diffraction and transmission electron microscopy revealed that graphite nanoflakes were effectively exfoliated and covered MoS2 or MoSe2 layers to form homogeneous nanostructures via HEMM. As a result, the electrochemical performances of both MoS2/graphite and MoSe2/graphite were excellent; the specific capacities were as high as 684.8 (MoS2/graphite) and 787.3 mAh g-1 (MoSe2/graphite) after 100 cycles. Also, when compared with MoS2/graphite, the MoSe2/graphite nanocomposite showed higher specific capacity and better rate capability performance due to larger interlayer spacing, leading to fast and facile movement of Liions. Overall, we demonstrate that homogeneous nanocomposites between similar layered materials (MoS2, MoSe2 and graphite) can be easily synthesized via one-step HEMM, which can be used as excellent anode materials for LIBs.

The detection of p53 gene via fluorescence quenching of quantum dot in microfluidic chip.

Recently, quantum dot (QD) has been used widely in the field of bio assay including cell imaging, biomarker, and fluorescence resonance energy transfer (FRET) sensor. The DNA assay without labeling process has several advantages including low cost, short time, and simplicity. Microbeads of agarose, glass, and polystyrene have been used as a solid support in microfluidic devices to trace molecules. The main advantages of microfluidics include high throughput, short analysis time, small sample volume, and high sensitivity. PDMS based microfluidic chips were prepared for the detection of p53 gene by using QD-DNA conjugate. The microfluidic chip has a weir in the channel to trap microbeads to which QD-DNA probes bind. Carboxylated CdSe/ZnS QDs (wavelength of emission: 605 nm) could bind to microbeads of polystyrene/divinyl benzene via EDC/NHS crosslinking reaction. The target gene and DNA intercalating dye (TOTO-3) were loaded into the micro-channel. Fluorescence quenching from QDs by intercalating dye was observed after hybridization of DNA at the weir in the channel of microfluidic chip. The fluorescence quenching from QDs by TOTO-3 was dependent on the concentration of target gene. This experiment shows the possibility of rapid detection of DNA via bead-QD complex on microfluidic chip.

Production of lactic acid from food wastes.

Conversion of food wastes into lactic acid by simultaneous saccharification and fermentation (SSF) was investigated. The process involves saccharification of the starch component in food wastes by a commercial amylolytic enzyme preparation (a mixture of amyloglucosidase, alpha-amylase, and protease) and fermentation by Lactobacillus delbrueckii. The highest observed overall yield of lactic acid in the SSF was 91% of theoretical. Lactic acid concentration as high as 80 g/L was attainable in 48 h of the SSF. The optimum operating conditions for the maximum productivity were found to be 42 degrees C and pH 6.0. Without supplementation of nitrogen-containing nutrients, the lactic acid yield in the SSF decreased to 60%: 27 g/L of lactic acid from 60 g/L of food waste. The overall performance of the SSF, however, was not significantly affected by the elimination of mineral supplements.