Tracking financing for global common goods for health: A machine learning approach using natural language processing techniques.

Objective: Tracking global health funding is a crucial but time consuming and labor-intensive process. This study aimed to develop a framework to automate the tracking of global health spending using natural language processing (NLP) and machine learning (ML) algorithms. We used the global common goods for health (CGH) categories developed by Schäferhoff et al. to design and evaluate ML models. Methods: We used data curated by Schäferhoff et al., which tracked the official development assistance (ODA) disbursements to global CGH for 2013, 2015, and 2017, for training and validating the ML models. To process raw text, we implemented different NLP techniques, such as removing stop words, lemmatization, and creation of synthetic text, to balance the dataset. We used four supervised learning ML algorithms-random forest (RF), XGBOOST, support vector machine (SVM), and multinomial naïve Bayes (MNB) (see Glossary)-to train and test the pre-coded dataset, and applied the best model on dataset that hasn't been manually coded to predict the financing for CGH in 2019. Results: After we trained the machine on the training dataset (n = 10,534), the weighted average F1-scores (a measure of a ML model's performance) on the testing dataset (n = 2,634) ranked 0.79-0.83 among four models, and the RF model had the best performance (F1-score = 0.83). The predicted total donor support for CGH projects by the RF model was $2.24 billion across 3 years, which was very close to the finding of $2.25 billion derived from coding and classification by humans. By applying the trained RF model on the 2019 dataset, we predicted that the total funding for global CGH was about $2.7 billion for 730 CGH projects. Conclusion: We have demonstrated that NLP and ML can be a feasible and efficient way to classify health projects into different global CGH categories, and thus track health funding for CGH routinely using data from publicly available databases.

Validation of the Decision model of the Burden of Hearing loss Across the Lifespan (DeciBHAL) in Chile, India, and Nigeria.

Background: There is no published decision model for informing hearing health care resource allocation across the lifespan in low- and middle-income countries. We sought to validate the Decision model of the Burden of Hearing loss Across the Lifespan International (DeciBHAL-I) in Chile, India, and Nigeria. Methods: DeciBHAL-I simulates bilateral sensorineural hearing loss (SNHL) and conductive hearing loss (CHL) acquisition, SNHL progression, and hearing loss treatment. To inform model inputs, we identified setting-specific estimates including SNHL prevalence from the Global Burden of Disease (GBD) studies, acute otitis media (AOM) incidence and prevalence of otitis-media related CHL from a systematic review, and setting-specific pediatric and adult hearing aid use prevalence. We considered a coefficient of variance root mean square error (CV-RMSE) of ≤15% to indicate good model fit. Findings: The model-estimated prevalence of bilateral SNHL closely matched GBD estimates, (CV-RMSEs: 3.2-7.4%). Age-specific AOM incidences from DeciBHAL-I also achieved good fit (CV-RMSEs=5.0-7.5%). Model-projected chronic suppurative otitis media prevalence (1.5% in Chile, 4.9% in India, and 3.4% in Nigeria) was consistent with setting-specific estimates, and the incidence of otitis media-related CHL was calibrated to attain adequate model fit. DeciBHAL-projected adult hearing aid use in Chile (3.2-19.7% ages 65-85 years) was within the 95% confidence intervals of published estimates. Adult hearing aid prevalence from the model in India was 1.4-2.3%, and 1.1-1.3% in Nigeria, consistent with literature-based and expert estimates. Interpretation: DeciBHAL-I reasonably simulates hearing loss natural history, detection, and treatment in Chile, India, and Nigeria. Future cost-effectiveness analyses might use DeciBHAL-I to inform global hearing health policy. Funding: National Institutes of Health (3UL1-TR002553-03S3 and F30 DC019846).

Who benefits from tuberculosis outpatient services in Enugu state, Nigeria? A benefit incidence analysis.

OBJECTIVES: Nigeria is one of the 30 high-burden countries for TB and currently, recurrent costs of TB treatment services are largely dependent on donor-funding, with government providing the health facilities. This study aims to assess the benefit incidence of TB treatment services so as to determine if the poor and rural dwellers preferentially benefit from such services that were subsidized by government and donors. METHODS: A survey of patients (n = 202) accessing TB treatment services was conducted between 2019 and 2020 in five purposively selected rural and urban health facilities in Enugu state. Socio-economic status (SES) was estimated using household assets ownership. Benefits of TB services were measured by multiplying the unit cost of utilization of different services while the net benefit was calculated by subtracting out-of-pocket (OOP) payments incurred from the benefits. We estimated the benefit for 1 month and the benefit for the whole TB treatment course (6 months). Concentration index was used to determine the level of equity in spending across the socio-economic quintiles. RESULTS: 56.4% of the respondents were from urban facilities. 100% had used TB drugs in the past months, 73% had undergone a Gene-Xpert test, and 67% had had a consultation. All patients received TB drugs without OOP payment, but 90% paid for X-ray. Urban respondents captured a disproportionally higher share of benefit from TB services. The concentration index was -0.025 for net benefit from TB services across different quintiles, indicating the pro-poor distribution of TB services in Nigeria. CONCLUSIONS: The benefit from TB services had a pro-poor distribution, but urban respondents obtained a disproportionally higher share of gross and net benefit from TB services. Funding for TB services needs to be secured to promote the equitable access to TB services.

Effect of Alcohol and Tea on Solubility of Soft-liner and Polymethyl Methacrylate Resin: An In Vitro Study.

AIM: To evaluate solubility of soft denture liner material and acrylic denture base resin when stored in 8% and 50% concentration of alcohol and tea(with milk and green tea) at an interval of 4,7,11 and 15 days. MATERIALS AND METHODS: An in vitro study wasdone on 75 standardized samples in disk form (15 mm × 2 mm), each for soft-liner and acrylic denture base resin. Samples were divided into 5 groups (15 per group/per material) and stored in distilled water (A), 8% alcohol (B), 50% alcohol (C), tea with milk (D) and green tea (E). Solubility was determined at each time interval by dividing difference of weight (taken after drying the sample in a desiccator) from day 1 divided by surface area of the specimen. For each day (i.e., 4, 7, 11 and 15),one-way analysis of variance (ANOVA) test was used to determine if the distribution of mean solubility was similar in five groups followed by post-hoc Tukey's test for pair-wise comparisons. RESULTS: Mean solubility of soft-liner was the highest tea with milk (D) followed by green tea (E), then 50% and 8 % alcohol (C and B) and was least in group A at each time of measurement. Mean solubility of an acrylic resin was highest for 8% alcohol (B) and all other groups it was similar. CONCLUSION: This study shows increased solubility for soft-liners when immersed in tea with milk, green tea, and alcohol at 8% and 50% concentration. The solubility of acrylic resin also increases at 8% alcohol concentration. CLINICAL SIGNIFICANCE: Drinks/beverages used in our study are commonly consumed, the results of this study caution for restricting the frequency of intake. However, this needs to be confirmed by in-vivo studies designed to prove the association of denture life with the consumption pattern of these drinks/ beverages.

Outcome of a "modified brief intervention" program delivered at work place for a population with hazardous alcohol use.

INTRODUCTION: At the population level, screening and brief intervention (BI) is the most cost-effective method to reduce the burden of disease due to hazardous alcohol use. In delivering BI at individual level, trained workforce as well as time is a limiting factor. Hence, a study was conducted to assess the outcome of a "modified brief intervention" program delivered at workplace in a group setting for the participants identified with hazardous alcohol use pattern, as a secondary prevention measure. MATERIALS AND METHODS: Study was a pre- and post-intervention study without a control group. Following an educational lecture, conducted by a mental health team including a psychiatrist, participants were screened using the WHO ASSIST questionnaire, V3.0 version. Those screened positive for hazardous alcohol use were given "modified brief intervention" in a group setting at their workplace which consisted of two semi-structured sessions of 1-h duration each. The sessions were spaced in a month. First session was based on motivation enhancement measures along with gathering of current alcohol use details and second session focused on relapse prevention. Three months later, the outcomes were assessed using a semistructured questionnaire and ASSIST was reapplied. The analysis was done using the R-commander from R-software. RESULTS: No significant difficulty was experienced in conducting the interventions. Fifty (55.6%) participants stayed alcohol abstinent following second session and another 22 (24.44%) had reduced both the quantity and frequency of use. Paired t-tests revealed statistically significant reduction in all secondary outcome parameters (ASSIST scores, usual dose in one sitting, maximum dose, and number of days of use in month). Eighty (88.89%) participants reported the program to be effective. Only 3 months of observation is a limitation. CONCLUSION: The study provides an efficient secondary prevention model to reduce hazardous drinking at the population level needing less workforce, cost, and time.

Social Support and Treatment Outcome in Alcohol Dependence Syndrome in Armed Forces.

INTRODUCTION: Social factors play vital role in unfolding of alcohol use disorders in any given population. Several factors beyond the confines of treatment settings influence treatment outcome in alcohol dependence syndrome. Social support has positive effect in treatment outcome of alcohol dependence syndrome. This has not been much studied in India in past. Therefore we decided to study the perception of social support in cases of alcohol dependence syndrome admitted in a busy hospital in armed forces. AIM: The aim was to study the perception of social support across relapsed and abstinent group and see if it reached any statistical proportion and also to see if any socio-demographic variables also affected perception of social support. MATERIALS AND METHODS: Fifty five consecutive male patients of alcohol dependent syndrome without a co-morbid neurological/psychiatric diagnosis were assessed for their perception of social support after taking informed consent. They were explained the procedure and their alcoholic milestones were recorded in specially designed pro-forma. Subjects were then divided in abstinent and relapsed group. Subsequently they were assessed for their perception of social support by administering Social provision scale and Social support questionnaire. STATISTICAL ANALYSIS: Data were tabulated and statistically analysed by using chi square test, Mann Whitney U-Test and Rank ANOVA test where applicable p-value <.05 was taken as significant. RESULTS: Results indicated that perception of social support across abstinent (n=18) and relapsed (n= 37) group reached significant statistical proportion as measured by social provision scale and social support questionnaire. Duration of use, dependence and family history of alcoholism did not influence perception of social support across patient population. There was inverse relationship between patients with alcohol related problem and their perception of social support. Professional and qualified soldiers perceived higher social support than soldiers and lesser qualified individuals. CONCLUSION: Abstinent group perceived better social support than relapsed group and soldiers in upper socio-occupational status and less alcohol related problems perceived more social support than soldiers with lower socioeconomic status and more alcohol related problems. Psychosocial therapy must be incorporated in management of Alcohol dependence syndrome.

A Rare Case of Myxedema Coma with Neuroleptic Malignant Syndrome (NMS).

Myxedema coma or hypothyroid crisis is an endocrine emergency and needs ICU management. Neuroleptic malignant syndrome (NMS) is another medical emergency which needs high degree of clinical suspicion else mortality can be high. There is a paradox in co existence of myxedema coma and NMS. While one is hypometabolic state another is hypermetabolic state and both can be precipitated by antipsychotics use. Hypothermia and flaccidity commonly expected in myxedema coma may mask fever and rigidity of classical NMS contributing to diagnostic problem and treatment delay. Scientific literature on coexistance of myxedema coma and NMS is sparse. We hereby report first case with coexisting myxedema coma and NMS in a patient of schizophrenia treated with antipsychotic, where classical symptoms of NMS were masked by myxedema coma. Prompt diagnosis and effective management by a team resulted in favourable outcome in our patient. This case is reported to alert intensive care physicians to atypical manifestations of NMS in presence of hypothyroidism.

Valproate Induced Delirium due to Hyperammonemia in a Case of Acute Mania: A Diagnostic Dilemma.

Divalproex sodium is commonly used drug to treat variety of psychiatric and neurological disorders. Hyperammonemia is infrequent adverse affect of treatment with divalproex sodium. It needs high degree of clinical suspicion or else can lead to delirium of non hepatic origin in some group of patients and to medication errors or even death. We hereby report a case of mania who developed hyperammonemia with normal sodium valproate levels and liver function tests where delirium lead to diagnostic and medication errors. Withdrawal of divalproex sodium led to clinical recovery but delirium prolonged his hospital stay. This case report cautions the clinicians about hyperammonemia as the uncommon side effects and emphasizes the need of doing blood ammonia testing in patients treated with divalproex sodium where recovery is halted or clinical condition worsens despite normal liver function test and EEG.

A Case of SSRI Induced Irreversible Parkinsonism.

Serotonin specific reuptake inhibitors (SSRI) are widely used antidepressants for variety of clinical conditions and have found popularity. They are sometimes associated with extrapyramidal side effects including Parkinsonism. We report a case of generalized anxiety disorder on treatment with SSRI (fluoxetine / sertraline) who developed irreversible Parkinsonism. SSRI are known to cause reversible or irreversible motor disturbances through pathophysiological changes in basal ganglion motor system by altering the dopamine receptors postsynaptically. Clinician should keep risk benefit ratio in mind and change of antidepressant of different class may be considered. Case is reported to alert physicians to possibility of motor system damage while treating with SSRI.

Usefulness of Gamma Glutamyl Transferase as Reliable Biological Marker in Objective Corroboration of Relapse in Alcohol Dependent Patients.

INTRODUCTION: The development of reliable diagnostic tool for assessing alcoholism is an utmost necessity in treating and preventing damage due to alcoholism to both individual and armed forces as alcoholism represents a serious health issue with major socioeconomic consequences. AIM: To observe, gamma glutamyl transferase (GGT) can serve the practical utility of firmly establishing alcohol dependence /relapse in Armed Forces patients and aid in fair disposals. MATERIALS AND METHODS: Fifty two consecutive cases of alcohol dependence syndrome admitted to a peripheral hospital were evaluated for the biological marker gamma glutamyl transferase (GGT) and compared against the gold standard of psychiatrist assessment. The cases were followed up for one year at three months, six months, nine months and 12 months interval. The GGT value of the cases was correlated with the abstinent /relapse status to find the cutoff levels of the GGT as a biological marker. RESULTS: At cutoff level of 50 IU/lit GGT exhibited specificity of 100% and sensitivity varying from 56% to 100%. At lower cut off levels chances of false positive cases with adverse consequences on service prospects of the individuals are high. The mean difference in GGT levels across relapse and abstinent group reached significant statistical proportion at admission and during follow-up at 3 months /6 months/9 months and 12 months. CONCLUSION: GGT can serve the practical utility of firmly establishing alcohol dependence syndrome in armed forces to aid in fair disposal of cases. It helps in providing motivational inputs to patients. Clinician should pay due consideration to clinical profile, ward observation and unit report as the diagnosis of alcohol dependence syndrome has serious implications towards service prospects of a soldier.