Clinical trials are experiments or observations on a patient’s responses of different medical treatments to cure diseases. Such trials are heavily regulated and must achieve a certain quality standard of the trial and clinical adherence is a determining factor on the success of a study. However, it has historically been difficult to systematically follow and understand patient adherence to medical ordinations, predominately due to lack of proper tools. One new type of tools is a digital pillbox that can be used to supply pills to participants in clinical trials. This paper examines implementing two supervised machine learning models to detect if an object (a pill) is found in an encapsulated compartment (pillbox) based on electromagnetic radiation data from a proximity sensor. Support Vector Machine (SVM) and Random Forest (RF) were evaluated on a data set of N=1,485 observations, consisting of five classes: four different pills and ‘no pill’. RF performs best with accuracy of 98.0% and weighted average precision of 98.0%. SVM had 97.3% accuracy and 97.6% weighted average precision. Best performance was achieved at N=1,000 for RF and 1,100 for SVM. The conclusion was that a high accuracy and precision can be achieved using either RF or SVM. The classification model strengthens the value proposition of a digital pillbox and can improve clinical trials to achieve better data quality. However, for the model to contribute actual economical value, digital pillboxes must be a common practice in clinical trials. / Kliniska studier är experiment eller observationer av en patients reaktion på olika typer av medicinsk vård för behandling sjukdomar. Sådana studier är tungt reglerade och behöver uppnå en viss kvalitésstandard och klinisk följsamhet är en avgörande faktor för en studies framgång. Trots det har det historiskt varit svårt att systematiskt mäta och förstå en patients följsamhet av en medicinsk ordination, primärt på grund av brist av användbara verktyg. En ny typ av verktyg är en digital  pillerbox som försörjer piller till deltagare i kliniska studier. Denna studie undersöker implementation av två bevakade maskininlärningsmodeller för detektion om ett objekt (ett piller) befinner sig i ett slutet fack baserad på elektromagnetisk strålning från en närhetssensor. Support Vector Machine (SVM) och Random Forest (RF) utvärderades på ett dataset av N=1 485 observationer utgjort av fem klasser: fyra piller och ’inget piller’. RF presterar bäst med 98,0% i träffsäkerhet och 98,0% i viktad medelprecision. SVM fick 97,3% träffsäkerhet och 97,6% viktad medelprecision. Bäst prestation uppnåddes vid N=1 000 för RF och N=1 100 för SVM. Slutsatsen var att en hög träffsäkerhet och precision kan uppnås genom antingen RF eller SVM. Klassificeringsmodellen förstärker en digital pillerbox värdeerbjudande och kan hjälpa kliniska studier att uppnå högre datakvalité. Däremot, för klassificeringsmodellen ska bidra med faktiskt ekonomiskt värde, behöver digitala pillerboxar vara en vedertagen praxis.

Despite the unprecedented improvement in child health in last 15 years, burden of stillbirth and neonatal death remain the key challenge in Nepal and the reduction of these deaths will be crucial for reaching the health targets for Sustainable development goal by 2030. The aim of this thesis was to explore the risk factors for stillbirth and neonatal death and change in perinatal outcomes after the introduction of the Helping Babies Breathe Quality Improvement Cycle (HBB QIC) in Nepal. This was a prospective cohort study with a nested case-control design completed in a tertiary hospital in Nepal. Information were collected from the women who had experienced perinatal death and live birth among referent population; a video recording was done in the neonatal resuscitation corner to collect information on the health workers’ performance in neonatal resuscitation.  Lack of antenatal care had the highest association with antepartum stillbirth (aOR 4.2, 95% CI 3.2–5.4), births that had inadequate fetal heart rate monitoring were associated with intrapartum stillbirth (aOR 1.9, CI 95% 1.5–2.4), and babies who were born premature and small-for-gestational-age had the highest risk for neonatal death in the hospital (aOR 16.2, 95% CI 12.3–21.3). Before the introduction of the HBB QIC, health workers displayed poor adherence to the neonatal resuscitation protocol. After the introduction of HBB QIC, the health workers demonstrated improvement in their neonatal resuscitation skills and these were retained until six months after training. Daily bag-and-mask skill checks (RR 5.1 95% CI 1.9–13.5), preparation for birth (RR 2.4, 95% CI 1.0–5.6), self-evaluation checklists (RR 3.8, 95% CI 1.4–9.7) and weekly review and reflection meetings (RR 2.6, 95% 1.0–7.4) helped the health workers to retain their neonatal resuscitation skills. The health workers demonstrated improvement in ventilation of babies within one minute of birth and there was a reduction in intrapartum stillbirth (aOR 0.46, 95% CI 0.32–0.66) and first-day neonatal mortality (aOR 0.51, 95% CI 0.31–0.83).  The study provides information on challenges in reducing stillbirth and neonatal death in low income settings and provides a strategy to improve health workers adherence to neonatal resuscitation to reduce the mortality. The HBB QIC can be implemented in similar clinical settings to improve quality of care and survival in Nepal, but for primary care settings, the QIC need to be evaluated further.