Development of Various Diabetes Prediction Models Using Machine Learning Techniques.

BACKGROUND: There are many models for predicting diabetes mellitus (DM), but their clinical implication remains vague. Therefore, we aimed to create various DM prediction models using easily accessible health screening test parameters. METHODS: Two sets of variables were used to develop eight DM prediction models. One set comprised 62 easily accessible examination results of commonly used variables from a tertiary university hospital. The second set comprised 27 of the 62 variables included in the national routine health checkups. Gradient boosting and random forest algorithms were used to develop the models. Internal validation was performed using the stratified 10-fold cross-validation method. RESULTS: The area under the receiver operating characteristic curve (ROC-AUC) for the 62-variable DM model making 12-month predictions for subjects without diabetes was the largest (0.928) among those of the eight DM prediction models. The ROC-AUC dropped by more than 0.04 when training with the simplified 27-variable set but still showed fairly good performance with ROC-AUCs between 0.842 and 0.880. The accuracy was up to 11.5% higher (from 0.807 to 0.714) when fasting glucose was included. CONCLUSION: We created easily applicable diabetes prediction models that deliver good performance using parameters commonly assessed during tertiary university hospital and national routine health checkups. We plan to perform prospective external validation, hoping that the developed DM prediction models will be widely used in clinical practice.

Mobile Phone App-Based Pulmonary Rehabilitation for Chemotherapy-Treated Patients With Advanced Lung Cancer: Pilot Study.

BACKGROUND: Advanced lung cancer patients often have chronic lung disease with reduced exercise capacities and various symptoms leading to altered quality of life (QoL). No studies have assessed pulmonary rehabilitation (PR) employing a mobile app and an Internet of Things device in advanced lung cancer patients undergoing chemotherapy. OBJECTIVE: This study aimed to determine the feasibility and efficacy of smartphone app-based PR on exercise capacity, symptom management, and QoL in patients with advanced lung cancer undergoing chemotherapy. METHODS: A total of 100 patients were recruited in a prospective, single-arm intervention study using a smartphone app-based PR program for 12 weeks. Exercise capacity (6-min walking distance, 6MWD), QoL, symptom scale scores, and distress indexes were investigated. RESULTS: A total of 90 patients completed the PR program. The most common cause of drop out was hospitalization because of cancer progression. After PR, there was significant improvement in the 6MWD; 380.1 m (SD 74.1) at baseline, 429.1 m (SD 58.6) at 6 weeks (P<.001), and 448.1 m (SD 50.0) at 12 weeks (P<.001). However, the dyspnea scale score showed no significant improvement in the patients overall, but there was a trend for improvement in those with a stable tumor response (P=.07). Role (P=.02), emotional (P<.001), and social functioning (P=.002) scale scores showed significant improvement after PR. Symptom scale scores for fatigue (P<.001), anorexia (P=.047), and diarrhea (P=.01) also showed significant improvement. There was significant improvement in depression (P=.048) and anxiety (P=.01), whereas there was no significant change in QoL (P=.06) and severity of pain (P=.24). CONCLUSIONS: Smartphone app-based PR represents an effective and feasible program to improve exercise capacity and to manage symptoms and distress in patients with advanced lung cancer who are undergoing chemotherapy.

An mHealth Management Platform for Patients with Chronic Obstructive Pulmonary Disease (efil breath): Randomized Controlled Trial.

BACKGROUND: Chronic obstructive pulmonary disease (COPD) is one of the major morbidities in public health, and the use of mHealth technology for rehabilitation of patients with COPD can help increase physical activity and ameliorate respiratory symptoms. OBJECTIVE: This study aimed to develop a comprehensive rehabilitation management platform to improve physical activity and quality of life in patients with COPD. METHODS: The study comprised the following 2 stages: (1) a pilot stage in which a prototype app was developed; and (2) a fully-fledged platform development stage in which 2 apps and 1 COPD patient monitoring website were developed. We conducted a randomized clinical trial to investigate the efficacy of the apps developed in the second stage of the study. In addition, two 12-week exercise regimens (fixed and fixed-interactive) were tested for the trial. The clinical parameters of the respiratory function and patient global assessment (PGA) of the app were obtained and analyzed. Notably, Android was the chosen operating system for apps. RESULTS: We developed 2 COPD rehabilitation apps and 1 patient monitoring website. For the clinical trial, 85 patients were randomized into the following 3 groups: 57 were allocated to the 2 intervention groups and 28 to the control group. After 6 weeks, the COPD assessment test scores were significantly reduced in the fixed group (P=.01), and signs of improvement were witnessed in the fixed-interactive group. In addition, the PGA score was moderate or high in all aspects of the user experience of the apps in both intervention groups. CONCLUSIONS: A well-designed mobile rehabilitation app for monitoring and managing patients with COPD can supplement or replace traditional center-based rehabilitation programs and achieve improved patient health outcomes. TRIAL REGISTRATION: ClinicalTrials.gov NCT03432117; https://clinicaltrials.gov/ct2/show/NCT03432117 (Archived by WebCite at http://www.webcitation.org/71Yp0P64a).

Infrared probe of spin-phonon coupling in antiferromagnetic honeycomb lattice compound Li2MnO3.

We investigated temperature-dependent infrared-active phonon modes of honeycomb Li2MnO3 which shows an antiferromagnetic transition at T(N) = 36 K. In the far-infrared frequency region, we observed fourteen phonon modes. We obtained the temperature dependence of each phonon mode from the analysis of optical conductivity spectra by using the Lorentz and the Fano-type oscillator models. We found that the resonance frequencies of nine phonon modes showed an anomalous behavior near T(N) that should be attributed to the spin-phonon coupling. We calculated the magnitude of the spin-phonon coupling constant from the shift in the resonance frequencies of the phonon modes below T(N). Our results suggest that Li2MnO3 is weakly frustrated and that spin-phonon coupling plays a role in antiferromagnetic ordering.