Predicting improvement in biofeedback gait training using short-term spectral features from minimum foot clearance data.

Stroke rehabilitation interventions require multiple training sessions and repeated assessments to evaluate the improvements from training. Biofeedback-based treadmill training often involves 10 or more sessions to determine its effectiveness. The training and assessment process incurs time, labor, and cost to determine whether the training produces positive outcomes. Predicting the effectiveness of gait training based on baseline minimum foot clearance (MFC) data would be highly beneficial, potentially saving resources, costs, and patient time. This work proposes novel features using the Short-term Fourier Transform (STFT)-based magnitude spectrum of MFC data to predict the effectiveness of biofeedback training. This approach enables tracking non-stationary dynamics and capturing stride-to-stride MFC value fluctuations, providing a compact representation for efficient processing compared to time-domain analysis alone. The proposed STFT-based features outperform existing wavelet, histogram, and Poincaré-based features with a maximum accuracy of 95%, F1 score of 96%, sensitivity of 93.33% and specificity of 100%. The proposed features are also statistically significant (p < 0.001) compared to the descriptive statistical features extracted from the MFC series and the tone and entropy features extracted from the MFC percentage index series. The study found that short-term spectral components and the windowed mean value (DC value) possess predictive capabilities regarding the success of biofeedback training. The higher spectral amplitude and lower variance in the lower frequency zone indicate lower chances of improvement, while the lower spectral amplitude and higher variance indicate higher chances of improvement.

Integrating Pediatric Universal Behavioral Health Care at Federally Qualified Health Centers.

BACKGROUND: Research supports integrated pediatric behavioral health (BH), but evidence gaps remain in ensuring equitable care for children of all ages. In response, an interdisciplinary team codeveloped a stepped care model that expands BH services at 3 federally qualified health centers (FQHCs). METHODS: FQHCs reported monthly electronic medical record data regarding detection of BH issues, receipt of services, and psychotropic medications. Study staff reviewed charts of children with attention-deficit/hyperactivity disorder (ADHD) before and after implementation. RESULTS: Across 47 437 well-child visits, >80% included a complete BH screen, significantly higher than the state's long-term average (67.5%; P < .001). Primary care providers identified >30% of children as having BH issues. Of these, 11.2% of children <5 years, 53.8% of 5-12 years, and 74.6% >12 years were referred for care. Children seen by BH staff on the day of referral (ie, "warm hand-off") were more likely to complete an additional BH visit than children seen later (hazard ratio = 1.37; P < .0001). There was no change in the proportion of children prescribed psychotropic medications, but polypharmacy declined (from 9.5% to 5.7%; P < .001). After implementation, diagnostic rates for ADHD more than doubled compared with baseline, follow-up with a clinician within 30 days of diagnosis increased (62.9% before vs 78.3% after; P = .03) and prescriptions for psychotropic medication decreased (61.4% before vs 43.9% after; P = .03). CONCLUSIONS: Adding to a growing literature, results demonstrate that integrated BH care can improve services for children of all ages in FQHCs that predominantly serve marginalized populations.

Behavioral Health Integration in a Medicaid Accountable Care Organization: Management Lessons from a Health Center.

Behavioral health integration, including as used in Medicaid Accountable Care Organizations, can improve care and decrease costs. Our model strives to integrate fully its medical, behavioral health, and substance use disorder services into one primary care clinic. Merged management has decreased wait times, improved billing, and enabled several promising innovations.

Oral Health Integration Into a Pediatric Practice and Coordination of Referrals to a Colocated Dental Home at a Federally Qualified Health Center.

We have integrated preventive oral health measures into preventive care visits for children at a federally qualified health center in Boston, Massachusetts. The program, started in 2015, covers 3400 children and has increased universal caries risk screening in primary care to 85%, fluoride varnish application rates to 80%, and referrals to a dental home to 35%. We accomplished this by minimizing pressures on providers' workflow, empowering medical assistants to lead the initiative, and utilizing data-driven improvement strategies, alongside colocated coordinated care.

Lung sound classification using cepstral-based statistical features.

Lung sounds convey useful information related to pulmonary pathology. In this paper, short-term spectral characteristics of lung sounds are studied to characterize the lung sounds for the identification of associated diseases. Motivated by the success of cepstral features in speech signal classification, we evaluate five different cepstral features to recognize three types of lung sounds: normal, wheeze and crackle. Subsequently for fast and efficient classification, we propose a new feature set computed from the statistical properties of cepstral coefficients. Experiments are conducted on a dataset of 30 subjects using the artificial neural network (ANN) as a classifier. Results show that the statistical features extracted from mel-frequency cepstral coefficients (MFCCs) of lung sounds outperform commonly used wavelet-based features as well as standard cepstral coefficients including MFCCs. Further, we experimentally optimize different control parameters of the proposed feature extraction algorithm. Finally, we evaluate the features for noisy lung sound recognition. We have found that our newly investigated features are more robust than existing features and show better recognition accuracy even in low signal-to-noise ratios (SNRs).

Pediatric provider processes for behavioral health screening, decision making, and referral in sites with colocated mental health services.

OBJECTIVE: Validated behavioral health (BH) screens are recommended for use at well-child visits. This study aimed to explore how pediatricians experience and use these screens for subsequent care decisions in primary care. METHODS: The study took place at 4 safety net health centers. Fourteen interviews were conducted with pediatricians who were mandated to use validated BH screens at well-child visits. Interview questions focused on key domains, including clinic BH context, screening processes, assessment of screening scores, and decision making about referral to mental health services. Qualitative analysis used the Framework Approach. RESULTS: A variety of themes emerged: BH screens were well accepted and valued for the way they facilitated discussion of mental health issues. However, screening results were not always used in the way that instrument designers intended. Providers' beliefs about the face validity of the instruments, and their observations about performance of instruments, led to discounting scored results. As a result, clinical decisions were made based on a variety of evidence, including individual item responses, parent or patient concerns, and perceived readiness for treatment. Additionally, providers, although interested in expanding their mental health discussions, perceived a lack of time and of their own skills to be major obstacles in this pursuit. CONCLUSIONS: Screens act as important prompts to stimulate discussion of BH problems, but their actual scored results play a variable role in problem identification and treatment decisions. Modifications to scheduling policies, additional provider training, and enhanced collaboration with mental health professionals could support better BH integration in pediatric primary care.

Provider's perspectives on building research and quality improvement capacity in primary care: a strategy to improve workforce satisfaction.

OBJECTIVES: Safety-net populations are underrepresented in research and quality improvement (QI) studies despite the fact that safety-net providers are uniquely positioned to engage in translational research. This study aimed to understand the current level of interest in, experience with, predicted career satisfaction associated with, and barriers experienced in conducting research and QI among primary care providers (PCPs) at 18 safety-net practices in the Boston, Massachusetts area. METHODS: The Harvard Catalyst Safety-net Infrastructure Initiative partnered with staff at a large academic public hospital system, including 15 primary care sites, to develop and administer an online survey. This survey was then adapted and administered at three other academically affiliated community health centers. RESULTS: Of the 260 providers surveyed, 136 (52%) responded. Nearly 80% reported interest in conducting either QI projects or clinical research and 95% of them believed it would enhance their career satisfaction. However, 63% did not report prior experience or training in research or QI and 93% reported at least one barrier to engagement. CONCLUSION: While supporting safety-net PCPs' engagement in research and/or QI may improve career satisfaction there are numerous barriers that must be addressed to achieve this goal.