Try : Insurtech, Application Development










Dev Ops(2)

Enterprise Solution(20)




AI in Insurance(27)


Product Innovation(36)


Augmented Reality(7)

Customer Journey(7)


User Experience(21)

Artificial Intelligence(95)



Cognitive Computing(7)

Computer Vision(6)

Data Science(14)


Intelligent Automation(25)

Machine Learning(43)

Natural Language Processing(10)




Telehealth Care(1)

Model selection with cross-validation: A quest for an elite model

3 minutes, 13 seconds read

What do you call a prediction model that performs tremendously well on the same data it was trained on? Technically, a tosh! It will perform feebly on unseen data, thus leading to a state called overfitting

To combat such a scenario, the dataset is split into train set and test set. The model is then trained on the train set and is kept deprived of the test set. This test set is utilized to estimate the efficacy of the model. To decide on the best train-test split, two competing cornerstones need to be focused on. Firstly, less training data will give rise to greater variance in the parameter estimates, and secondly, less testing data will lead to greater variance in the performance statistic. Conventionally, an 80/20 split is considered to be a suitable starting point such that neither variance is too high. 

Yet another problem arises when we try to fine-tune the hyperparameters. There is a possibility for the model to still overfit on the testing data due to data leakage. To prevent this, a dataset should typically be divided into train, validation, and test sets. The validation set acts as an intermediary between the training part and the final evaluation part. However, this indeed reduces the training examples, thus making it less likely for the model to generalize, and the performance rather depends merely on a random split. 

Here’s where cross-validation comes to our rescue!

Cross-validation (CV) eliminates the explicit requirement of a validation set. It facilitates the model selection and aids in gauging the generalizing capability of a model. The rudimentary modus operandi is the k-fold CV, where the dataset is split into k groups/folds and k-1 folds are used to train the model, while the held out kth fold is used to validate the model. Henceforth, each fold gets an opportunity to be used as a test set. This way, in each fold, the evaluation score is retained and the model is then discarded. The model’s skill is summarised by the mean of the evaluation scores. The variance of the evaluated scores is often expressed in terms of standard deviation.

5-fold cross validation

But is it feasible when the dataset is imbalanced? 

Probably not! In case of imbalanced data an extension to k-fold CV, called Stratified k-fold CV proves to be the magic bullet. It maintains the class proportion in all the folds as it was in the original dataset, thus making it available for the model to train on both, the minority as well as majority classes. 

stratified 5-fold cross validation

Determining the value of k

This is a baffling concern though!  Taking into account the bias-variance trade-off, the value of k should be decided carefully. Consequently, the k value should be chosen such that each fold can act as a representative of the dataset. Jumping on the bandwagon, it is preferred to set the k value as 5 or 10 since experimental success is observed with these values. 

There are some other variations of cross-validation viz.,

  1. Leave One Out CV (LOOCV): Only one sample is held out for the validation part
  2. Leave P Out CV (LPOCV): Similar to LOOCV, P samples are held out for the validation part
  3. Nested CV: Each fold involves cross-validation, making it a double cross-validation. It is generally used when tuning hyperparameters

Finally yet importantly, some tidbits that shouldn’t be ignored:

  • It is important to shuffle the data before moving ahead with cross-validation
  • To avoid data leakage, any data preparation step should be carried out on the training data within the cross-validation loop
  • It is preferable to repeat the cross-validation procedure by using repeated k-fold or repeated stratified k-fold CV for more reliable results especially, the variance in the performance metrics. 

Voila! We finally made it! If the model evaluation scores are acceptably high and have low variance, it’s time to party hard! Our mojo has worked! 

Further Readings:

  1.  5 Proven Strategies to Break Through the Data Silos
  2. Speech is the next UX
  3. The Next Big Thing for Big Tech: AI as a Service
  4. Insurtechs are Thriving with Machine Learning. Here’s how.


Knowledge thats worth delivered in your inbox

How to increase patient engagement on a healthcare app?

By :
4 minutes, 9 seconds read

Patient facing mobile apps have emerged as a viable alternative to interact with patients and help them execute several tasks related to healthcare without reaching the hospital. Patients are now increasingly glued to these healthcare apps and their time spent on mobile devices has increased significantly. From communication and information to executing business through mobile apps have become a common thing.

Still, there is a lot of gap in the healthcare market. Marketers are struggling to gauge the true value of mobile apps for the bottom line of healthcare organizations. Especially in terms of the value of the app viz-viz the efforts, cost, and time it would take to become a useful and engaging healthcare app for the patient.

To help you increase the patient engagement on a healthcare app, here are a few crucial ways that you need to know. It will not only increase the engagement but will also help you meet your organizational goals at a faster pace.

1. Reduce Readmissions

Healthcare provider’s biggest pain point these days is to avoid readmission of preventable cases. It is crucial for healthcare organizations to reduce this number to enhance patient outcome and improve their revenue growth. Customized healthcare applications can assist hospitals in reducing the number of readmissions.

Here is how:

  • Offer personalized post-release information and instructions
  • Reminder for regular follow-up visits
  • Enforce stricter adherence to post-release prescription and regiment
  • Easier access to healthcare resources and information
  • Lesser cost and time of reaching out
  • Greater engagement to reduce readmission rates

2. Encourage Patients to Proactively Manage Their Health

Encouraging the patient to become proactive in managing their own health can help in improving the outcome and also enhance the reputation of your hospital. With easier access to the required resources and tools, patients are more likely to stay in touch with healthcare professionals and practice the wellness regimen. A properly optimized mobile app can deliver a better wellness experience to the patient and a greater sense of satisfaction.

Here is how an app can help the patient in managing their health proactively:

  • Keeps the patient informed and connected with relevant services
  • Encourages regular health tracking
  • Helps in developing healthy habits and exercises
  • Promotion of health education by streaming informations

3. Improve Trust and Build Relationships

Establishing trust between the patient and doctor is one of the difficult things that hospitals face. Due to long wait times, complex processes, or lack of communication between healthcare team; patients are not willing to attend healthcare appointments.

However, when you give all the relevant tools and information in the smartphone of the patient and empower them, the trust develops between the two parties and the patient proactively takes charge of their treatment. Hospitals can also gain competitive advantage by streamlining patient referrals and building stronger relationships with physicians.

Here is how apps can help:

  • You can provide access to a larger pool of specialists 
  • Help in easily accessing credentials, studies, and information from the mobile app
  • Recommend, network, and connect
  • Improve efficiency and workflow

4. Boost Brand Image and Reputation

Today patients can not be treated less than consumers. Hospitals are competing with each other to provide better care facilities and infrastructure at affordable prices. Hence, it has become crucial to achieve patient satisfaction and engagement. Through mobile apps, hospitals can make the existing information easily accessible along with brand awareness features including social media, photo galleries, virtual tours, and more.

Here is how mobile app can help:

  • Easier access to communication and information
  • Intuitive presentation of the hospital through immersive galleries
  • Stream ER wait time and other relevant information
  • Greater social media engagement

What more factors can increase engagement?

Several patients come to healthcare app once and then dump them after a few logins. One of the major reasons for such low engagement rates is that either the app is difficult to navigate or it is not immersive for the patient.

Consider these few points to make your app more engaging:

  • Customize the app as per the patient group. An app can appear differently to a child and an old age person. Develop an app that is easy to use for all users. Sit with your QA engineers to validate the functionality of your application thoroughly.
  • Build an app that is scalable and can be evolved over a period of time. Leave the possibility of enhancements and customizations that you would need in the future to keep the application viable.
  • It is a no brainer to give multiple options to your patients. Develop a cross-platform application that is compatible with both iOS and Android platforms and offers a rich user experience.

Wrapping Up

With the COVID-19 pandemic, people are more worried about visiting hospitals. Social distancing has become the norm and patients are more inclined towards telemedicine for their treatment. In such a tricky situation, it has become more crucial for hospitals to provide a robust, secure, and engaging mobile app to patients to interact with doctors, access information, and stay connected with the healthcare system.

About the Author

Erna Clayton is a techie with over 12 years of experience in several technological domains including quality assurance and software testing. In her free time, she loves travelling and writing on technology.

Further Readings:

  1. Building Consumer Trust in the Digital Healthcare Era
  2. HealthTech 101: How are Healthcare Technologies Reinventing Patient Care
  3. Virtual health: Delivering care through technology
  4. How Mobile Micro-Health Insurance can unlock ‘Digital for Bharat’?

Knowledge thats worth delivered in your inbox

Loading More Posts ...
Go Top

May i help you?

bot shadow